Article(id=1153375942681547170, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1153375932170621317, articleNumber=null, orderNo=null, doi=10.13234/j.issn.2095-2805.2024.6.139, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1628006400000, receivedDateStr=2021-08-04, revisedDate=1635264000000, revisedDateStr=2021-10-27, acceptedDate=1635609600000, acceptedDateStr=2021-10-31, onlineDate=1752915853424, onlineDateStr=2025-07-19, pubDate=1732896000000, pubDateStr=2024-11-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752915853424, onlineIssueDateStr=2025-07-19, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752915853424, creator=13701087609, updateTime=1752915853424, updator=13701087609, issue=Issue{id=1153375932170621317, tenantId=1146029695717560320, journalId=1146031654075715584, year='2024', volume='22', issue='6', pageStart='1', pageEnd='326', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752915850917, creator=13701087609, updateTime=1753780959263, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1157004459600597839, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1153375932170621317, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1157004459600597840, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1153375932170621317, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=139, endPage=152, ext={EN=ArticleExt(id=1153375943352635818, articleId=1153375942681547170, tenantId=1146029695717560320, journalId=1146031654075715584, language=EN, title=Research on Prediction of Virtual Impedance in Low-voltage Microgrid Based on Partial Least Squares Regression, columnId=1152281492550987902, journalTitle=Journal of Power Supply, columnName=Renewable Energy System, runingTitle=null, highlight=null, articleAbstract=

When the improved droop control based on virtual impedance is adopted in island microgrid, the problem of inaccurate distribution of reactive power and reactive power circulation will still occur with the changing line impedance due to the fixed value of virtual impedance. To solve this problem, a virtual impedance prediction model based on partial least squares regression (PLSR) is proposed, which uses the line impedance value and the system impedance value before compensation to predict the virtual impedance value and realizes the adaptive virtual impedance, thus overcoming the problem in the improved droop control based on virtual impedance. There is no need to detect the real-time power value and circulation value, and the use of communication network is not required. Furthermore, from a comparison with the prediction results obtained by neural network models, it is proved that the prediction accuracy of the virtual impedance prediction model based on PLSR is better. At last, a simulation system of microgrid is constructed in MATLAB/Simulink to verify the adaptive virtual impedance, and simulation results show the superiority of the proposed model.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Jinpeng QIAO), CN=ArticleExt(id=1153376128711512884, articleId=1153375942681547170, tenantId=1146029695717560320, journalId=1146031654075715584, language=CN, title=基于偏最小二乘回归的低压微电网虚拟阻抗预测研究, columnId=1149829992055595012, journalTitle=电源学报, columnName=新能源系统, runingTitle=null, highlight=null, articleAbstract=

针对孤岛微电网在采用基于虚拟阻抗的改进下垂控制时由于虚拟阻抗为固定值,当线路阻抗发生变化时仍存在无功功率不能精确分配和无功环流的问题,提出1种基于偏最小二乘回归的虚拟阻抗预测模型,采用线路阻抗值和补偿前系统阻抗值来预测虚拟阻抗值,实现自适应虚拟阻抗,从而克服基于虚拟阻抗的改进下垂控制存在的问题。该模型无需检测实时功率值和环流值,也无需借助通信网络。通过与神经网络模型的预测结果进行对比,证明了所提偏最小二乘回归虚拟阻抗预测模型的预测准确性优于神经网络模型。最后在MATLAB/Simulink下搭建微电网仿真系统对自适应虚拟阻抗进行仿真验证,仿真结果证明了所提模型的优越性。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=VrSaknJst3hFf6sh+u1Rcg==, magXml=kcHxCy5J7MhoDpakFJJDqQ==, pdfUrl=null, pdf=FhR7WpPT8Z1jqate92ZWbg==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=DgTEi+7SM3ClUug1CWD4VA==, mapNumber=null, authorCompany=null, fund=null, authors=

乔金朋(1992-),男,通信作者,硕士研究生。研究方向:微电网技术。E-mail: 2191840042@qq.com。

, authorsList=乔金朋)}, authors=[Author(id=1154032484506395249, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2191840042@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154032484611252850, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, authorId=1154032484506395249, language=EN, stringName=Jinpeng QIAO, firstName=Jinpeng, middleName=null, lastName=QIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Electrical and Information Engineering Anhui University of Science & Technology Huainan 232001 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154032484678361716, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, authorId=1154032484506395249, language=CN, stringName=乔金朋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=安徽理工大学 电气与信息工程学院 淮南 232001, bio={"img":"LKLMg/grD6NGBBYPQnUSBA==","content":"

乔金朋(1992-),男,通信作者,硕士研究生。研究方向:微电网技术。E-mail: 2191840042@qq.com。

"}, bioImg=LKLMg/grD6NGBBYPQnUSBA==, bioContent=

乔金朋(1992-),男,通信作者,硕士研究生。研究方向:微电网技术。E-mail: 2191840042@qq.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154032484380566124, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, xref=null, ext=[AuthorCompanyExt(id=1154032484388954733, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, companyId=1154032484380566124, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical and Information Engineering Anhui University of Science & Technology Huainan 232001 China), AuthorCompanyExt(id=1154032484405731951, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, companyId=1154032484380566124, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=安徽理工大学 电气与信息工程学院 淮南 232001)])])], keywords=[Keyword(id=1154032485034877560, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, orderNo=1, keyword=Microgrid), Keyword(id=1154032485110375038, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, orderNo=2, keyword=virtual impedance), Keyword(id=1154032485169095298, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, orderNo=3, keyword=multi-correlation), Keyword(id=1154032485232009861, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, orderNo=4, keyword=partial least squares regression (PLSR)), Keyword(id=1154032485290730119, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, orderNo=1, keyword=微电网), Keyword(id=1154032485374616200, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, orderNo=2, keyword=虚拟阻抗), Keyword(id=1154032485437530761, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, orderNo=3, keyword=多重相关性), Keyword(id=1154032485500445322, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, orderNo=4, keyword=偏最小二乘回归)], refs=[Reference(id=1154032489757664001, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=175, pageEnd=179, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=null, journalName=2017 International Conference on System Science and Engineering(ICSSE), refType=null, unstructuredReference=Le Minh P, Duc D H V, Xuan H P T, et al. A new control strategy of power sharing in islanded microgrids[C]// 2017 International Conference on System Science and Engineering(ICSSE). Ho Chi Minh City, Vietnam, 2017: 175-179., articleTitle=A new control strategy of power sharing in islanded microgrids, refAbstract=null), Reference(id=1154032489828967171, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=3419, pageEnd=3426, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=null, journalName=2016 IEEE 8th International Power Electronics and Motion Control Conference(IPEMC-ECCE Asia), refType=null, unstructuredReference=Guan Yajuan, Guerrero J M, Zhao Xin, et al. Comparison of a synchronous reference frame virtual impedance-based autonomous current sharing control with conventional droop control for parallel-connected inverters[C]// 2016 IEEE 8th International Power Electronics and Motion Control Conference(IPEMC-ECCE Asia). Hefei, China, 2016: 3419-3426., articleTitle=Comparison of a synchronous reference frame virtual impedance-based autonomous current sharing control with conventional droop control for parallel-connected inverters, refAbstract=null), Reference(id=1154032489908658950, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=154, pageEnd=159, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=null, journalName=2017 International Conference on System Science and Engineering(ICSSE), refType=null, unstructuredReference=Minh P L, Xuan H P T, Duc D H V, et al. Control of power sharing in an island microgrid using virtual impedance[C]// 2017 International Conference on System Science and Engineering(ICSSE). Ho Chi Minh City, Vietnam, 2017: 154-159., articleTitle=Control of power sharing in an island microgrid using virtual impedance, refAbstract=null), Reference(id=1154032489996739337, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2018, volume=12, issue=11, pageStart=2566, pageEnd=2576, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=Zhang Jiyuan, Shu Jie, Ning Jia, journalName=IET Generation, Transmission & Distribution, refType=null, unstructuredReference=Zhang Jiyuan, Shu Jie, Ning Jia, et al. Enhanced proportional power sharing strategy based on adaptive virtual impedance in low-voltage networked microgrid[J]. IET Generation, Transmission & Distribution, 2018. 12(11): 2566-2576., articleTitle=Enhanced proportional power sharing strategy based on adaptive virtual impedance in low-voltage networked microgrid, refAbstract=null), Reference(id=1154032490059653900, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2017, volume=11, issue=4, pageStart=1046, pageEnd=1054, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=Dou Chunxia, Zhang Zhanqiang, Yue Dong, journalName=IET Generation, Transmission & Distribution, refType=null, unstructuredReference=Dou Chunxia, Zhang Zhanqiang, Yue Dong, et al. Improved droop control based on virtual impedance and virtual power source in low-voltage microgrid[J]. IET Generation, Transmission & Distribution, 2017. 11(4): 1046-1054., articleTitle=Improved droop control based on virtual impedance and virtual power source in low-voltage microgrid, refAbstract=null), Reference(id=1154032490143539982, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2023, volume=21, issue=5, pageStart=101, pageEnd=109, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=潘健, 陈凤娇, 张琦, journalName=电源学报, refType=null, unstructuredReference=潘健, 陈凤娇, 张琦, 等. 基于抑制环流的自适应下垂控制改进策略[J]. 电源学报, 2023. 21(5): 101-109., articleTitle=基于抑制环流的自适应下垂控制改进策略, refAbstract=null), Reference(id=1154032490235814672, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2023, volume=21, issue=5, pageStart=101, pageEnd=109, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=Pan Jian, Chen Fengjiao, Zhang Qi, journalName=Journal of Power Supply, refType=null, unstructuredReference=Pan Jian, Chen Fengjiao, Zhang Qi, et al. Improved strategy for adaptive droop control based on suppressing circulating current[J]. Journal of Power Supply, 2023. 21(5): 101-109 (in Chinese)., articleTitle=Improved strategy for adaptive droop control based on suppressing circulating current, refAbstract=null), Reference(id=1154032490311312146, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2017, volume=29, issue=4, pageStart=49, pageEnd=54, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=李红萍, 杨洪耕, 曾巧燕, journalName=电力系统及其自动化学报, refType=null, unstructuredReference=李红萍, 杨洪耕, 曾巧燕, 等. 孤岛型微电网中改进下垂控制策略[J]. 电力系统及其自动化学报, 2017. 29(4): 49-54., articleTitle=孤岛型微电网中改进下垂控制策略, refAbstract=null), Reference(id=1154032490437141269, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2017, volume=29, issue=4, pageStart=49, pageEnd=54, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Li Hongping, Yang Honggeng, Zeng Qiaoyan, journalName=Proceedings of the CSU-EPSA, refType=null, unstructuredReference=Li Hongping, Yang Honggeng, Zeng Qiaoyan, et al. Improved droop control strategy for islanded microgrid[J]. Proceedings of the CSU-EPSA, 2017. 29(4): 49-54 (in Chinese)., articleTitle=Improved droop control strategy for islanded microgrid, refAbstract=null), Reference(id=1154032490504250136, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2017, volume=32, issue=2, pageStart=77, pageEnd=82, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=郭通, 李燕青, 仝年, journalName=电力科学与技术学报, refType=null, unstructuredReference=郭通, 李燕青, 仝年, 等. 基于自调节下垂系数的微电网控制策略[J]. 电力科学与技术学报, 2017. 32(2): 77-82, 91., articleTitle=基于自调节下垂系数的微电网控制策略, refAbstract=null), Reference(id=1154032490567164700, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2017, volume=32, issue=2, pageStart=77, pageEnd=82, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=Guo Tong, Li Yanqing, Tong Nian, journalName=Journal of Electric Power Science and Technology, refType=null, unstructuredReference=Guo Tong, Li Yanqing, Tong Nian, et al. Control strategy of micro-grid based on self-adjustable droop coefficient[J]. Journal of Electric Power Science and Technology, 2017. 32(2): 77-82, 91 (in Chinese)., articleTitle=Control strategy of micro-grid based on self-adjustable droop coefficient, refAbstract=null), Reference(id=1154032490634273564, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=23, pageStart=52, pageEnd=56, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=王二永, 王帅, journalName=电力系统保护与控制, refType=null, unstructuredReference=王二永, 王帅. 自适应下垂系数的低压微电网功率控制策略[J]. 电力系统保护与控制, 2019. 47(23): 52-56., articleTitle=自适应下垂系数的低压微电网功率控制策略, refAbstract=null), Reference(id=1154032490697188127, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=23, pageStart=52, pageEnd=56, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=Wang Eryong, Wang Shuai, journalName=Power System Protection and Control, refType=null, unstructuredReference=Wang Eryong, Wang Shuai. Power control strategy of low voltage microgrid based on adaptive droop coefficient[J]. Power System Protection and Control, 2019. 47(23): 52-56 (in Chinese)., articleTitle=Power control strategy of low voltage microgrid based on adaptive droop coefficient, refAbstract=null), Reference(id=1154032490755908385, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=37, issue=12, pageStart=1800, pageEnd=1804, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=史卫卫, 寻鲁宁, 曹亚景, journalName=中国公共卫生, refType=null, unstructuredReference=史卫卫, 寻鲁宁, 曹亚景, 等. 河北省居民 2015—2018 年脑梗死流行特征分析及时间序列预测[J]. 中国公共卫生, 2021. 37(12): 1800-1804., articleTitle=河北省居民 2015—2018 年脑梗死流行特征分析及时间序列预测, refAbstract=null), Reference(id=1154032490831405859, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=37, issue=12, pageStart=1800, pageEnd=1804, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=Shi Weiwei, Xun Luning, Cao Yajing, journalName=Chinese Journal of Public Health, refType=null, unstructuredReference=Shi Weiwei, Xun Luning, Cao Yajing, et al. Prevalence characteristics of cerebral infarction among residents in Hebei province, 2015—2018: A time series analysis[J]. Chinese Journal of Public Health, 2021. 37(12): 1800-1804 (in Chinese)., articleTitle=Prevalence characteristics of cerebral infarction among residents in Hebei province, 2015—2018: A time series analysis, refAbstract=null), Reference(id=1154032490919486245, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=28, issue=5, pageStart=88, pageEnd=94, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=周生辉, 刘廷玺, 段利民, journalName=水土保持研究, refType=null, unstructuredReference=周生辉, 刘廷玺, 段利民, 等. 基于时间序列的海流兔河流域降水量模拟预测分析[J]. 水土保持研究, 2021. 28(5): 88-94., articleTitle=基于时间序列的海流兔河流域降水量模拟预测分析, refAbstract=null), Reference(id=1154032490999178024, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=28, issue=5, pageStart=88, pageEnd=94, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=Zhou Shenghui, Liu Tingxi, Duan Limin, journalName=Research of Soil and Water Conservation, refType=null, unstructuredReference=Zhou Shenghui, Liu Tingxi, Duan Limin, et al. Simulation and prediction of precipitation in Hailiutu river basin based on time series[J]. Research of Soil and Water Conservation, 2021. 28(5): 88-94 (in Chinese)., articleTitle=Simulation and prediction of precipitation in Hailiutu river basin based on time series, refAbstract=null), Reference(id=1154032491078869803, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2019, volume=40, issue=9, pageStart=2594, pageEnd=2600, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=苏卫星, 任欢, journalName=计算机工程与设计, refType=null, unstructuredReference=苏卫星, 任欢. 基于改进偏最小二乘回归的矿浆元素含量预测[J]. 计算机工程与设计, 2019. 40(9): 2594-2600., articleTitle=基于改进偏最小二乘回归的矿浆元素含量预测, refAbstract=null), Reference(id=1154032491133395758, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2019, volume=40, issue=9, pageStart=2594, pageEnd=2600, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=Su Weixing, Ren Huan, journalName=Computer Engineering and Design, refType=null, unstructuredReference=Su Weixing, Ren Huan. Prediction of slurry element content based on improved partial least squares regression[J]. Computer Engineering and Design, 2019. 40(9): 2594-2600 (in Chinese)., articleTitle=Prediction of slurry element content based on improved partial least squares regression, refAbstract=null), Reference(id=1154032491196310321, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2018, volume=38, issue=3, pageStart=133, pageEnd=139, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=王雁凌, 吴梦凯, journalName=电力自动化设备, refType=null, unstructuredReference=王雁凌, 吴梦凯. 经济新常态下基于偏最小二乘回归的中长期负荷预测模型[J]. 电力自动化设备, 2018. 38(3): 133-139., articleTitle=经济新常态下基于偏最小二乘回归的中长期负荷预测模型, refAbstract=null), Reference(id=1154032491259224886, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2018, volume=38, issue=3, pageStart=133, pageEnd=139, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=Wang Yanling, Wu Mengkai, journalName=Electric Power Automation Equipment, refType=null, unstructuredReference=Wang Yanling, Wu Mengkai. Medium and long term load forecasting model based on partial least-square regression under new normal economy[J]. Electric Power Automation Equipment, 2018. 38(3): 133-139 (in Chinese)., articleTitle=Medium and long term load forecasting model based on partial least-square regression under new normal economy, refAbstract=null), Reference(id=1154032491351499578, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=4, pageStart=175, pageEnd=179, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=高腾, 许焕敏, journalName=水运工程, refType=null, unstructuredReference=高腾, 许焕敏. 基于偏最小二乘回归的疏浚产量预测方法[J]. 水运工程, 2020. 4): 175-179., articleTitle=基于偏最小二乘回归的疏浚产量预测方法, refAbstract=null), Reference(id=1154032491456357180, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=4, pageStart=175, pageEnd=179, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=Gao Teng, Xu Huanmin, journalName=Port & Waterway Engineering, refType=null, unstructuredReference=Gao Teng, Xu Huanmin. Prediction method for dredging production based on partial least squares regression[J]. Port & Waterway Engineering, 2020. 4): 175-179 (in Chinese)., articleTitle=Prediction method for dredging production based on partial least squares regression, refAbstract=null), Reference(id=1154032491531854655, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2019, volume=31, issue=1, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=李泽文, 邹彬, 赵廷, journalName=电力系统及其自动化学报, refType=null, unstructuredReference=李泽文, 邹彬, 赵廷, 等. 基于偏最小二乘回归的高精度同步时钟[J]. 电力系统及其自动化学报, 2019. 31(1): 1-6., articleTitle=基于偏最小二乘回归的高精度同步时钟, refAbstract=null), Reference(id=1154032491590574913, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2019, volume=31, issue=1, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=Li Zewen, Zou Bin, Zhao Ting, journalName=Proceedings of the CSU-EPSA, refType=null, unstructuredReference=Li Zewen, Zou Bin, Zhao Ting, et al. High-precision synchronous clock based on partial least squares regression[J]. Proceedings of the CSU-EPSA, 2019. 31(1): 1-6 (in Chinese)., articleTitle=High-precision synchronous clock based on partial least squares regression, refAbstract=null), Reference(id=1154032491653489476, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2017, volume=32, issue=5, pageStart=62, pageEnd=69, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=张志勇, 张飞, 刘志强, journalName=电工技术学报, refType=null, unstructuredReference=张志勇, 张飞, 刘志强, 等. 无刷直流电机输出转矩的非线性偏最小二乘回归估计[J]. 电工技术学报, 2017. 32(5): 62-69., articleTitle=无刷直流电机输出转矩的非线性偏最小二乘回归估计, refAbstract=null), Reference(id=1154032491741569863, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2017, volume=32, issue=5, pageStart=62, pageEnd=69, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=Zhang Zhiyong, Zhang Fei, Liu Zhiqiang, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=Zhang Zhiyong, Zhang Fei, Liu Zhiqiang, et al. Brushless DC motor torque estimation based on nonlinear partial least square method[J]. Transactions of China Electrotechnical Society, 2017. 32(5): 62-69 (in Chinese)., articleTitle=Brushless DC motor torque estimation based on nonlinear partial least square method, refAbstract=null), Reference(id=1154032491833844556, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=58, issue=3, pageStart=118, pageEnd=125, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=王胜, 冯兴明, 周宇, journalName=电测与仪表, refType=null, unstructuredReference=王胜, 冯兴明, 周宇, 等. 基于BP神经网络预测的微网系统 dq 轴谐波阻抗的主动测量策略[J]. 电测与仪表, 2021. 58(3): 118-125., articleTitle=基于BP神经网络预测的微网系统 dq 轴谐波阻抗的主动测量策略, refAbstract=null), Reference(id=1154032491892564813, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=58, issue=3, pageStart=118, pageEnd=125, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=Wang Sheng, Feng Xingming, Zhou Yu, journalName=Electrical Measurement & Instrumentation, refType=null, unstructuredReference=Wang Sheng, Feng Xingming, Zhou Yu, et al. An active measurement strategy of dq-axis harmonic impedance in micro-gridsystem based on BP neural network prediction[J]. Electrical Measurement & Instrumentation, 2021. 58(3): 118-125 (in Chinese)., articleTitle=An active measurement strategy of dq-axis harmonic impedance in micro-gridsystem based on BP neural network prediction, refAbstract=null), Reference(id=1154032491959673678, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=39, issue=3, pageStart=74, pageEnd=77, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=邱勇, 杨泽文, 周鑫宇, journalName=水电能源科学, refType=null, unstructuredReference=邱勇, 杨泽文, 周鑫宇, 等. 基于BP神经网络的直角折线堰过流能力预测[J]. 水电能源科学, 2021. 39(3): 74-77., articleTitle=基于BP神经网络的直角折线堰过流能力预测, refAbstract=null), Reference(id=1154032492051948365, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=39, issue=3, pageStart=74, pageEnd=77, url=null, language=null, rfNumber=[18], rfOrder=30, authorNames=Qiu Yong, Yang Zewen, Zhou Xinyu, journalName=Water Resources and Power, refType=null, unstructuredReference=Qiu Yong, Yang Zewen, Zhou Xinyu, et al. Prediction of overflow capability of right-angle polyline weir based on BP neural network[J]. Water Resources and Power, 2021. 39(3): 74-77 (in Chinese)., articleTitle=Prediction of overflow capability of right-angle polyline weir based on BP neural network, refAbstract=null), Reference(id=1154032492127445839, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=28, issue=7, pageStart=1437, pageEnd=1445, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=王晓辉, 刘静蕾, 边会娟, journalName=控制工程, refType=null, unstructuredReference=王晓辉, 刘静蕾, 边会娟, 等. 基于改进BP神经网络的室内环境热舒适度预测与分析[J]. 控制工程, 2021. 28(7): 1437-1445., articleTitle=基于改进BP神经网络的室内环境热舒适度预测与分析, refAbstract=null), Reference(id=1154032492177777489, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=28, issue=7, pageStart=1437, pageEnd=1445, url=null, language=null, rfNumber=[19], rfOrder=32, authorNames=Wang Xiaohui, Liu Jinglei, Bian Huijuan, journalName=Control Engineering of China, refType=null, unstructuredReference=Wang Xiaohui, Liu Jinglei, Bian Huijuan, et al. Prediction and analysis of indoor environmental thermal comfort based on improved BP neural network[J]. Control Engineering of China, 2021. 28(7): 1437-1445 (in Chinese)., articleTitle=Prediction and analysis of indoor environmental thermal comfort based on improved BP neural network, refAbstract=null), Reference(id=1154032492236497747, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=3, pageStart=171, pageEnd=178, url=null, language=null, rfNumber=[20], rfOrder=33, authorNames=关鹏, 焦玉勇, 段新胜, journalName=太阳能学报, refType=null, unstructuredReference=关鹏, 焦玉勇, 段新胜. 基于 RBF 神经网络的土体导热系数非线性预测[J]. 太阳能学报, 2021. 42(3): 171-178., articleTitle=基于 RBF 神经网络的土体导热系数非线性预测, refAbstract=null), Reference(id=1154032492324578134, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=3, pageStart=171, pageEnd=178, url=null, language=null, rfNumber=[20], rfOrder=34, authorNames=Guan Peng, Jiao YuYong, Duan Xinsheng, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=Guan Peng, Jiao YuYong, Duan Xinsheng. Non-liner prediction of soil thermal conductivity based on RBF neural network[J]. Acta Energiae Solaris Sinica, 2021. 42(3): 171-178 (in Chinese)., articleTitle=Non-liner prediction of soil thermal conductivity based on RBF neural network, refAbstract=null), Reference(id=1154032492387492697, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2019, volume=38, issue=12, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=[21], rfOrder=35, authorNames=叶佳卓, 杨力, 伍诗雨, journalName=电工电能新技术, refType=null, unstructuredReference=叶佳卓, 杨力, 伍诗雨, 等. 孤岛微电网自适应虚拟阻抗控制策略[J]. 电工电能新技术, 2019. 38(12): 1-9., articleTitle=孤岛微电网自适应虚拟阻抗控制策略, refAbstract=null), Reference(id=1154032492479767387, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2019, volume=38, issue=12, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=[21], rfOrder=36, authorNames=Ye Jiazhuo, Yang Li, Wu Shiyu, journalName=Advanced Technology of Electrical Engineering and Energy, refType=null, unstructuredReference=Ye Jiazhuo, Yang Li, Wu Shiyu, et al. Adaptive virtual impedance control strategy for island microgrid[J]. Advanced Technology of Electrical Engineering and Energy, 2019. 38(12): 1-9 (in Chinese)., articleTitle=Adaptive virtual impedance control strategy for island microgrid, refAbstract=null), Reference(id=1154032492563653469, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[22], rfOrder=37, authorNames=null, journalName=2017 IEEE Conference on Energy Internet and Energy System Integration(EI2), refType=null, unstructuredReference=An improved droop control strategy for parallel inverters in microgrid[C]// 2017 IEEE Conference on Energy Internet and Energy System Integration(EI2), 2017: 1-5., articleTitle=An improved droop control strategy for parallel inverters in microgrid, refAbstract=null), Reference(id=1154032492630762335, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[23], rfOrder=38, authorNames=null, journalName=2016 China International Conference on Electricity Distribution(CICED), refType=null, unstructuredReference=Huang Jing, Liu Xiaohua, Li Hongping. Control method of islanded microgrid to improve reactive power sharing and power quality[C]// 2016 China International Conference on Electricity Distribution(CICED). Xi’an, China, 2016: 1-5., articleTitle=Control method of islanded microgrid to improve reactive power sharing and power quality, refAbstract=null), Reference(id=1154032492702065506, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=39, authorNames=何瑞, journalName=null, refType=null, unstructuredReference=何瑞. 基于虚拟阻抗的并网变流器并联控制策略的研究[D]. 西安: 西安理工大学, 2019., articleTitle=基于虚拟阻抗的并网变流器并联控制策略的研究, refAbstract=null), Reference(id=1154032492756591460, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=40, authorNames=He Rui, journalName=null, refType=null, unstructuredReference=He Rui. Research on parallel control strategy of grid-connected converter based on virtual impedance[D]. Xi'an: Xi'an University of Technology, 2019. (in Chinese)., articleTitle=Research on parallel control strategy of grid-connected converter based on virtual impedance, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1154032484380566124, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, xref=null, ext=[AuthorCompanyExt(id=1154032484388954733, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, companyId=1154032484380566124, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical and Information Engineering Anhui University of Science & Technology Huainan 232001 China), AuthorCompanyExt(id=1154032484405731951, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, companyId=1154032484380566124, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=安徽理工大学 电气与信息工程学院 淮南 232001)])], figs=[ArticleFig(id=1154032486280585888, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 1, caption=Microgrid structure, figureFileSmall=8f0SEOJAUK4/fP1yGLYq0Q==, figureFileBig=1H4Thz/srUPXoWQq8oDiwA==, tableContent=null), ArticleFig(id=1154032486343500449, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图1, caption=微电网结构, figureFileSmall=8f0SEOJAUK4/fP1yGLYq0Q==, figureFileBig=1H4Thz/srUPXoWQq8oDiwA==, tableContent=null), ArticleFig(id=1154032486439969444, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 2, caption=Control block diagram of inverter with virtual impedance control loop, figureFileSmall=j6T/+Tb9WIHvZ5qf5I2Zbg==, figureFileBig=/W1aAgSUO6MvFqt5VjjfxQ==, tableContent=null), ArticleFig(id=1154032486507078310, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图2, caption=带有虚拟阻抗控制环的逆变器控制框图, figureFileSmall=j6T/+Tb9WIHvZ5qf5I2Zbg==, figureFileBig=/W1aAgSUO6MvFqt5VjjfxQ==, tableContent=null), ArticleFig(id=1154032486574187176, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 3, caption=Virtual impedance realization method in ${dq}$ coordinate system, figureFileSmall=EzVRebJ7kSIegsBQ6tlpJA==, figureFileBig=MWAFwjz1vC+HA4Sj5FokGg==, tableContent=null), ArticleFig(id=1154032486649684652, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图3, caption=$\mathrm{\;}{dq}$ 坐标系下虚拟阻抗实现方法, figureFileSmall=EzVRebJ7kSIegsBQ6tlpJA==, figureFileBig=MWAFwjz1vC+HA4Sj5FokGg==, tableContent=null), ArticleFig(id=1154032486712599215, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=null, caption=null, figureFileSmall=lh0b3rkWPnBubADKyOu9IA==, figureFileBig=A8r8tVaITlinu8xOkVwSUw==, tableContent=null), ArticleFig(id=1154032486779708082, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图4, caption=${T}^{2}$ 椭圆 Fig. $4{T}^{2}$ ellipse, figureFileSmall=lh0b3rkWPnBubADKyOu9IA==, figureFileBig=A8r8tVaITlinu8xOkVwSUw==, tableContent=null), ArticleFig(id=1154032486838428343, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 5, caption=VIP histogram of independent variables, figureFileSmall=VXNcfsqXnK3RyTZizy2fxg==, figureFileBig=xpVRu4qdeP3jbdbhVLvohQ==, tableContent=null), ArticleFig(id=1154032486976840378, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图5, caption=自变量 VIP 直方图, figureFileSmall=VXNcfsqXnK3RyTZizy2fxg==, figureFileBig=xpVRu4qdeP3jbdbhVLvohQ==, tableContent=null), ArticleFig(id=1154032487060726459, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 6, caption=Virtual impedance prediction based on PLSR, figureFileSmall=d4UqWTp51YJOb9dYvrk4AQ==, figureFileBig=gcuXHkAyuumETwU9O+0CDA==, tableContent=null), ArticleFig(id=1154032487136223934, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图6, caption=PLSR 虚拟阻抗预测, figureFileSmall=d4UqWTp51YJOb9dYvrk4AQ==, figureFileBig=gcuXHkAyuumETwU9O+0CDA==, tableContent=null), ArticleFig(id=1154032487207527105, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 7, caption=Absolute error and relative error of PLSR model, figureFileSmall=bDs7+UJ/LxYM6q8bVVEGEA==, figureFileBig=O8skPV2AkV8v+wNVH5a8Sg==, tableContent=null), ArticleFig(id=1154032487295607492, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图7, caption=PLSR 模型绝对误差和相对误差, figureFileSmall=bDs7+UJ/LxYM6q8bVVEGEA==, figureFileBig=O8skPV2AkV8v+wNVH5a8Sg==, tableContent=null), ArticleFig(id=1154032487366910663, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 8, caption=Virtual impedance prediction by BP neural network, figureFileSmall=3YrG6Z92sYXKqMeQsQmYqg==, figureFileBig=Wx1vFWttL7V42Kpai1TM5g==, tableContent=null), ArticleFig(id=1154032487463379659, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图8, caption=BP 神经网络虚拟阻抗预测, figureFileSmall=3YrG6Z92sYXKqMeQsQmYqg==, figureFileBig=Wx1vFWttL7V42Kpai1TM5g==, tableContent=null), ArticleFig(id=1154032487547265741, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 9, caption=Absolute error and relative error of BP neural, figureFileSmall=YowtxDGLl+nc5ghl1F3V3A==, figureFileBig=6FPSG7WZYKZJWyt5EAbzAQ==, tableContent=null), ArticleFig(id=1154032487622763216, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图9, caption=BP 神经网络模型绝对误差和相对误差, figureFileSmall=YowtxDGLl+nc5ghl1F3V3A==, figureFileBig=6FPSG7WZYKZJWyt5EAbzAQ==, tableContent=null), ArticleFig(id=1154032487685677778, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 10, caption=Virtual impedance prediction by RBF neural network, figureFileSmall=1Tmf+p3sSks4ip/3qw+11g==, figureFileBig=zDsU5vyuj/hEisl0Uht/VQ==, tableContent=null), ArticleFig(id=1154032487744398036, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图10, caption=RBF 神经网络虚拟阻抗预测, figureFileSmall=1Tmf+p3sSks4ip/3qw+11g==, figureFileBig=zDsU5vyuj/hEisl0Uht/VQ==, tableContent=null), ArticleFig(id=1154032487807312598, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 11, caption=Absolute error and relative error of RBF neural network model, figureFileSmall=b3CdDpblXnX1dpwhWj0VWQ==, figureFileBig=zNqY6kIZB9jw4HRfrvramQ==, tableContent=null), ArticleFig(id=1154032487949918935, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图11, caption=RBF 神经网络模型绝对误差和相对误差, figureFileSmall=b3CdDpblXnX1dpwhWj0VWQ==, figureFileBig=zNqY6kIZB9jw4HRfrvramQ==, tableContent=null), ArticleFig(id=1154032488029610712, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 12, caption=Simulation of power, figureFileSmall=lbhEUtkETuKR3WHqueST+A==, figureFileBig=73LanBF03arkbo7PzJRSsw==, tableContent=null), ArticleFig(id=1154032488096719578, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图12, caption=仿真功率, figureFileSmall=lbhEUtkETuKR3WHqueST+A==, figureFileBig=73LanBF03arkbo7PzJRSsw==, tableContent=null), ArticleFig(id=1154032488159634138, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Fig. 13, caption=Simulation of reactive power circulation, figureFileSmall=G74sT8gd+lGoUrTQP9QyUA==, figureFileBig=iY1Q37ZURSdgiW+GNcAfdQ==, tableContent=null), ArticleFig(id=1154032488239325915, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=图13, caption=仿真无功环流, figureFileSmall=G74sT8gd+lGoUrTQP9QyUA==, figureFileBig=iY1Q37ZURSdgiW+GNcAfdQ==, tableContent=null), ArticleFig(id=1154032488323211996, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Tab. 1, caption=Selection of parameters, figureFileSmall=null, figureFileBig=null, tableContent=
${x}_{1}$ ${x}_{2}$ ${x}_{3}$ ${x}_{4}$ ${x}_{5}$ ${x}_{6}$ ${x}_{7}$ ${x}_{8}$ ${y}_{1}$ ${y}_{2}$ ${y}_{3}$ ${y}_{4}$
${R}_{\mathrm{L}1}/$ ${X}_{\mathrm{L}1}/$ ${R}_{\mathrm{L}2}/$ ${X}_{\mathrm{L}2}/$ $\angle {G}_{z1}\cdot$ $\angle {G}_{\mathrm{z}2}$ . ${G}_{z1}$ . ${G}_{z2}$ . ${R}_{\mathrm{v}1}/$ ${X}_{\mathrm{v}1}/$ ${R}_{\mathrm{v}2}/$ ${X}_{\mathrm{v}2}$
Ω Ω Ω Ω $\left({\mathrm{j}{\omega }_{\mathrm{b}}}\right)/\left({}^{\mathrm{o}}\right)$ $\left({\mathrm{j}{\omega }_{\mathrm{b}}}\right)/\left({}^{\mathrm{o}}\right)$ $\left({\mathrm{j}{\omega }_{\mathrm{b}}}\right)/\Omega$ $\left({\mathrm{j}{\omega }_{\mathrm{b}}}\right)/\Omega$ Ω Ω Ω Ω
), ArticleFig(id=1154032488423875294, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=表1, caption=参量的选取, figureFileSmall=null, figureFileBig=null, tableContent=
${x}_{1}$ ${x}_{2}$ ${x}_{3}$ ${x}_{4}$ ${x}_{5}$ ${x}_{6}$ ${x}_{7}$ ${x}_{8}$ ${y}_{1}$ ${y}_{2}$ ${y}_{3}$ ${y}_{4}$
${R}_{\mathrm{L}1}/$ ${X}_{\mathrm{L}1}/$ ${R}_{\mathrm{L}2}/$ ${X}_{\mathrm{L}2}/$ $\angle {G}_{z1}\cdot$ $\angle {G}_{\mathrm{z}2}$ . ${G}_{z1}$ . ${G}_{z2}$ . ${R}_{\mathrm{v}1}/$ ${X}_{\mathrm{v}1}/$ ${R}_{\mathrm{v}2}/$ ${X}_{\mathrm{v}2}$
Ω Ω Ω Ω $\left({\mathrm{j}{\omega }_{\mathrm{b}}}\right)/\left({}^{\mathrm{o}}\right)$ $\left({\mathrm{j}{\omega }_{\mathrm{b}}}\right)/\left({}^{\mathrm{o}}\right)$ $\left({\mathrm{j}{\omega }_{\mathrm{b}}}\right)/\Omega$ $\left({\mathrm{j}{\omega }_{\mathrm{b}}}\right)/\Omega$ Ω Ω Ω Ω
), ArticleFig(id=1154032488503567073, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Tab. 2, caption=Sample data of the same capacity, figureFileSmall=null, figureFileBig=null, tableContent=
序号 ${x}_{1}$ ${x}_{2}$ ${x}_{3}$ ${x}_{4}$ ${x}_{5}$ ${x}_{6}$ ${x}_{7}$ ${x}_{8}$ ${y}_{1}$ ${y}_{2}$ ${y}_{3}$ ${y}_{4}$
1 0.3852 0.0498 0.3852 0.0498 65.7363 65.7363 1.4236 1.4236 0.2800 0.1438 0.2800 0.1438
2 0.3852 0.0498 0.8988 0.1162 65.7363 51.1556 1.4236 1.7516 0.6336 0.7332 0.1200 0.6668
3 0.0642 0.0083 0.8988 0.1162 78.1327 51.1556 1.2838 1.7516 0.9546 0.7747 0.1200 0.6668
4 0.1926 0.0249 0.1284 0.0166 72.8672 75.4514 1.3320 1.3065 0.2958 -0.1259 0.3600 -0.1176
5 0.5778 0.0747 0.2568 0.0332 59.5496 70.3850 1.5344 1.3601 -0.0010 -0.0284 0.3200 0.0131
6 0.7704 0.0996 0.3852 0.0498 54.2485 65.7363 1.6605 1.4236 -0.1052 0.0940 0.2800 0.1438
7 0.2568 0.0332 0.9630 0.1245 70.3850 49.7287 1.3601 1.7989 0.8062 0.8234 0.1000 0.7321
8 0.7062 0.0913 0.1926 0.0249 55.9231 72.8672 1.6170 1.3320 -0.1736 -0.1187 0.3400 -0.0523
9 0.4494 0.0581 0.7704 0.0996 63.5706 54.2485 1.4586 1.6605 0.4810 0.5775 0.1600 0.5360
10 0.6420 0.0830 0.5136 0.0664 57.6888 61.5091 1.5749 1.4955 0.1116 0.2580 0.2400 0.2746
11 0.9630 0.1245 0.3210 0.0415 49.7287 68.0077 1.7989 1.3907 -0.3420 $-{0.004}\;5$ 0.3000 0.0785
12 0.5136 0.0664 0.1284 0.0166 61.5091 75.4514 1.4955 1.3065 -0.0252 -0.1674 0.3600 -0.1176
13 0.7704 0.0996 0.1926 0.0249 54.2485 72.8672 1.6605 1.3320 -0.2378 -0.1270 0.3400 -0.0523
14 0.3852 0.0498 0.1284 0.0166 65.7363 75.4514 1.4236 1.3065 0.1032 -0.1508 0.3600 -0.1176
15 0.0642 0.0083 0.3852 0.0498 78.1327 65.7363 1.2838 1.4236 0.6010 0.1853 0.2800 0.1438
16 0.0642 0.0083 0.8346 0.1079 78.1327 52.6608 1.2838 1.7054 0.9104 0.7010 0.1400 0.6014
17 0.7062 0.0913 0.0642 0.0083 55.9231 78.1327 1.6170 1.2838 -0.2620 -0.2660 0.3800 -0.1830
18 0.8346 0.1079 0.5136 0.0664 52.6608 61.5091 1.7054 1.4955 -0.0810 0.2331 0.2400 0.2746
19 0.1284 0.0166 0.1926 0.0249 75.4514 72.8672 1.3065 1.3320 0.4042 -0.0440 0.3400 -0.0523
20 0.5778 0.0747 0.7704 0.0996 59.5496 54.2485 1.5344 1.6605 0.3526 0.5609 0.1600 0.5360
21 0.0642 0.0083 0.3210 0.0415 78.1327 68.0077 1.2838 1.3907 0.5568 0.1117 0.3000 0.0785
22 0.1284 0.0166 0.5136 0.0664 75.4514 61.5091 1.3065 1.4955 0.6252 0.3244 0.2400 0.2746
23 0.6420 0.0830 0.3210 0.0415 57.6888 68.0077 1.5749 1.3907 -0.0210 0.0370 0.3000 0.0785
24 0.3210 0.0415 0.8346 0.1079 68.0077 52.6608 1.3907 1.7054 0.6536 0.6678 0.1400 0.6014
25 0.3852 0.0498 0.9630 0.1245 65.7363 49.7287 1.4236 1.7989 0.6778 0.8068 0.1000 0.7321
26 0.5136 0.0664 0.2568 0.0332 61.5091 70.3850 1.4955 1.3601 0.0632 -0.0201 0.3200 0.0131
27 0.3210 0.0415 0.8988 0.1162 68.0077 51.1556 1.3907 1.7516 0.6978 0.7415 0.1200 0.6668
28 0.7062 0.0913 0.3210 0.0415 55.9231 68.0077 1.6170 1.3907 -0.0852 0.0287 0.3000 0.0785
29 0.7704 0.0996 0.5136 0.0664 54.2485 61.5091 1.6605 1.4955 -0.0168 0.2414 0.2400 0.2746
30 0.9630 0.1245 0.0642 0.0083 49.7287 78.1327 1.7989 1.2838 -0.5188 -0.2992 0.3800 -0.1830
), ArticleFig(id=1154032488591647459, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=表2, caption=相同容量样本数据, figureFileSmall=null, figureFileBig=null, tableContent=
序号 ${x}_{1}$ ${x}_{2}$ ${x}_{3}$ ${x}_{4}$ ${x}_{5}$ ${x}_{6}$ ${x}_{7}$ ${x}_{8}$ ${y}_{1}$ ${y}_{2}$ ${y}_{3}$ ${y}_{4}$
1 0.3852 0.0498 0.3852 0.0498 65.7363 65.7363 1.4236 1.4236 0.2800 0.1438 0.2800 0.1438
2 0.3852 0.0498 0.8988 0.1162 65.7363 51.1556 1.4236 1.7516 0.6336 0.7332 0.1200 0.6668
3 0.0642 0.0083 0.8988 0.1162 78.1327 51.1556 1.2838 1.7516 0.9546 0.7747 0.1200 0.6668
4 0.1926 0.0249 0.1284 0.0166 72.8672 75.4514 1.3320 1.3065 0.2958 -0.1259 0.3600 -0.1176
5 0.5778 0.0747 0.2568 0.0332 59.5496 70.3850 1.5344 1.3601 -0.0010 -0.0284 0.3200 0.0131
6 0.7704 0.0996 0.3852 0.0498 54.2485 65.7363 1.6605 1.4236 -0.1052 0.0940 0.2800 0.1438
7 0.2568 0.0332 0.9630 0.1245 70.3850 49.7287 1.3601 1.7989 0.8062 0.8234 0.1000 0.7321
8 0.7062 0.0913 0.1926 0.0249 55.9231 72.8672 1.6170 1.3320 -0.1736 -0.1187 0.3400 -0.0523
9 0.4494 0.0581 0.7704 0.0996 63.5706 54.2485 1.4586 1.6605 0.4810 0.5775 0.1600 0.5360
10 0.6420 0.0830 0.5136 0.0664 57.6888 61.5091 1.5749 1.4955 0.1116 0.2580 0.2400 0.2746
11 0.9630 0.1245 0.3210 0.0415 49.7287 68.0077 1.7989 1.3907 -0.3420 $-{0.004}\;5$ 0.3000 0.0785
12 0.5136 0.0664 0.1284 0.0166 61.5091 75.4514 1.4955 1.3065 -0.0252 -0.1674 0.3600 -0.1176
13 0.7704 0.0996 0.1926 0.0249 54.2485 72.8672 1.6605 1.3320 -0.2378 -0.1270 0.3400 -0.0523
14 0.3852 0.0498 0.1284 0.0166 65.7363 75.4514 1.4236 1.3065 0.1032 -0.1508 0.3600 -0.1176
15 0.0642 0.0083 0.3852 0.0498 78.1327 65.7363 1.2838 1.4236 0.6010 0.1853 0.2800 0.1438
16 0.0642 0.0083 0.8346 0.1079 78.1327 52.6608 1.2838 1.7054 0.9104 0.7010 0.1400 0.6014
17 0.7062 0.0913 0.0642 0.0083 55.9231 78.1327 1.6170 1.2838 -0.2620 -0.2660 0.3800 -0.1830
18 0.8346 0.1079 0.5136 0.0664 52.6608 61.5091 1.7054 1.4955 -0.0810 0.2331 0.2400 0.2746
19 0.1284 0.0166 0.1926 0.0249 75.4514 72.8672 1.3065 1.3320 0.4042 -0.0440 0.3400 -0.0523
20 0.5778 0.0747 0.7704 0.0996 59.5496 54.2485 1.5344 1.6605 0.3526 0.5609 0.1600 0.5360
21 0.0642 0.0083 0.3210 0.0415 78.1327 68.0077 1.2838 1.3907 0.5568 0.1117 0.3000 0.0785
22 0.1284 0.0166 0.5136 0.0664 75.4514 61.5091 1.3065 1.4955 0.6252 0.3244 0.2400 0.2746
23 0.6420 0.0830 0.3210 0.0415 57.6888 68.0077 1.5749 1.3907 -0.0210 0.0370 0.3000 0.0785
24 0.3210 0.0415 0.8346 0.1079 68.0077 52.6608 1.3907 1.7054 0.6536 0.6678 0.1400 0.6014
25 0.3852 0.0498 0.9630 0.1245 65.7363 49.7287 1.4236 1.7989 0.6778 0.8068 0.1000 0.7321
26 0.5136 0.0664 0.2568 0.0332 61.5091 70.3850 1.4955 1.3601 0.0632 -0.0201 0.3200 0.0131
27 0.3210 0.0415 0.8988 0.1162 68.0077 51.1556 1.3907 1.7516 0.6978 0.7415 0.1200 0.6668
28 0.7062 0.0913 0.3210 0.0415 55.9231 68.0077 1.6170 1.3907 -0.0852 0.0287 0.3000 0.0785
29 0.7704 0.0996 0.5136 0.0664 54.2485 61.5091 1.6605 1.4955 -0.0168 0.2414 0.2400 0.2746
30 0.9630 0.1245 0.0642 0.0083 49.7287 78.1327 1.7989 1.2838 -0.5188 -0.2992 0.3800 -0.1830
), ArticleFig(id=1154032488696505062, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Tab. 3, caption=Cross validity test results, figureFileSmall=null, figureFileBig=null, tableContent=
主成分 对模型解释能力 对模型累积解释能力 交叉有效性 累积交叉有效性
Comp1 0.877845 0.877845 0.867772 0.867772
Comp2 0.122152 0.999997 0.999958 0.999995
Comp3 ${2.12755}\times {10}^{-6}$ 0.999999 0.575664 0.999998
Comp4 ${6.337}\;{17}\times {10}^{-8}$ 0.999999 -0.111784 0.999997
), ArticleFig(id=1154032488788779749, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=表3, caption=交叉有效性检验结果, figureFileSmall=null, figureFileBig=null, tableContent=
主成分 对模型解释能力 对模型累积解释能力 交叉有效性 累积交叉有效性
Comp1 0.877845 0.877845 0.867772 0.867772
Comp2 0.122152 0.999997 0.999958 0.999995
Comp3 ${2.12755}\times {10}^{-6}$ 0.999999 0.575664 0.999998
Comp4 ${6.337}\;{17}\times {10}^{-8}$ 0.999999 -0.111784 0.999997
), ArticleFig(id=1154032488952357609, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Tab. 4, caption=Cross validity test results with different sample lengths, figureFileSmall=null, figureFileBig=null, tableContent=
样本长度 主成分数 交叉有效性
15 组 8 0.0900750
20 组 4 -0.1117840
25 组 4 -0.0827418
30 组 4 $-{0.145}\;{137}\;0$
), ArticleFig(id=1154032489032049388, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=表4, caption=不同样本长度交叉有效性检验结果, figureFileSmall=null, figureFileBig=null, tableContent=
样本长度 主成分数 交叉有效性
15 组 8 0.0900750
20 组 4 -0.1117840
25 组 4 -0.0827418
30 组 4 $-{0.145}\;{137}\;0$
), ArticleFig(id=1154032489128518381, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Tab. 5, caption=Maximum deviation of absolute error, figureFileSmall=null, figureFileBig=null, tableContent=
模型 ${R}_{\mathrm{v}1}/\Omega$ ${X}_{\mathrm{v}1}/\Omega$ ${R}_{\mathrm{v}2}/\Omega$ ${X}_{\mathrm{v}2}/\Omega$
PLSR -0.0016 $-{0.001}\;5$ ${3.8914}\times {10}^{-4}$ -0.0013
BP 0.0652 0.0322 $-{0.024}\;4$ 0.0827
RBF -0.0261 $-{0.054}\;4$ 0.0136 -0.0446
), ArticleFig(id=1154032489224987376, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=表5, caption=绝对误差最大偏差值, figureFileSmall=null, figureFileBig=null, tableContent=
模型 ${R}_{\mathrm{v}1}/\Omega$ ${X}_{\mathrm{v}1}/\Omega$ ${R}_{\mathrm{v}2}/\Omega$ ${X}_{\mathrm{v}2}/\Omega$
PLSR -0.0016 $-{0.001}\;5$ ${3.8914}\times {10}^{-4}$ -0.0013
BP 0.0652 0.0322 $-{0.024}\;4$ 0.0827
RBF -0.0261 $-{0.054}\;4$ 0.0136 -0.0446
), ArticleFig(id=1154032489304679156, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Tab. 6, caption=Maximum deviation of relative error, figureFileSmall=null, figureFileBig=null, tableContent=
模型 ${R}_{\mathrm{v}1}/\%$ ${X}_{\mathrm{v}1}/\%$ ${R}_{\mathrm{v}2}/\%$ ${X}_{\mathrm{v}2}/\%$
PLSR -0.0320 -0.0334 -0.0021 0.0451
BP -1.911 0.6603 -0.1478 0.9246
RBF $-{0.876}\;6$ 0.1819 -0.058 0.2436
), ArticleFig(id=1154032489375982326, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=表6, caption=相对误差最大偏差值, figureFileSmall=null, figureFileBig=null, tableContent=
模型 ${R}_{\mathrm{v}1}/\%$ ${X}_{\mathrm{v}1}/\%$ ${R}_{\mathrm{v}2}/\%$ ${X}_{\mathrm{v}2}/\%$
PLSR -0.0320 -0.0334 -0.0021 0.0451
BP -1.911 0.6603 -0.1478 0.9246
RBF $-{0.876}\;6$ 0.1819 -0.058 0.2436
), ArticleFig(id=1154032489451479800, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=EN, label=Tab. 7, caption=Simulation parameters of microgrid consisting of two inverters, figureFileSmall=null, figureFileBig=null, tableContent=
参数 数值
逆变器输出额定电压/V 311
逆变器输出额定频率/Hz 50
逆变器直流侧电压${U}_{\mathrm{{dc}}}/\mathrm{V}$ 800
滤波电感${L}_{\mathrm{f}}/\mathrm{H}$ $2 \times {10}^{-3}$
等效滤波电阻${R}_{\mathrm{f}}/\Omega$ 0.02
滤波电容${C}_{\mathrm{f}}/\mathrm{F}$ $5 \times {10}^{-5}$
$\mathrm{{PCC}}$ 点阻感负载${R}_{1}/\Omega$ ${20}+ {j5}$
开关频率${f}_{\mathrm{s}}/\mathrm{{Hz}}$ $5 \times {10}^{3}$
PWM 调制增益${K}_{\mathrm{{pwm}}}$ 1
电流控制器比例系数${K}_{\mathrm{p}1}$ 20
电流控制器积分系数${K}_{\mathrm{i}1}$ 200
电压控制器比例系数${K}_{\mathrm{p}2}$ 0.5
电压控制器积分系数${K}_{\mathrm{i}2}$ 150
有功下垂系数${m}_{1}/\left({\mathrm{{rad}}/\mathrm{s}/\mathrm{W}}\right)$ $1 \times {10}^{-5}$
无功下垂系数${n}_{1}/\left({\mathrm{V}/\mathrm{{var}}}\right)$ $3 \times {10}^{-4}$
有功下垂系数${m}_{2}$ /(rad/s/W) $1 \times {10}^{-5}$
无功下垂系数${n}_{2}/\left({\mathrm{V}/\mathrm{{var}}}\right)$ $3 \times {10}^{-4}$
), ArticleFig(id=1154032489518588666, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1153375942681547170, language=CN, label=表7, caption=2台逆变器组成微电网的仿真参数, figureFileSmall=null, figureFileBig=null, tableContent=
参数 数值
逆变器输出额定电压/V 311
逆变器输出额定频率/Hz 50
逆变器直流侧电压${U}_{\mathrm{{dc}}}/\mathrm{V}$ 800
滤波电感${L}_{\mathrm{f}}/\mathrm{H}$ $2 \times {10}^{-3}$
等效滤波电阻${R}_{\mathrm{f}}/\Omega$ 0.02
滤波电容${C}_{\mathrm{f}}/\mathrm{F}$ $5 \times {10}^{-5}$
$\mathrm{{PCC}}$ 点阻感负载${R}_{1}/\Omega$ ${20}+ {j5}$
开关频率${f}_{\mathrm{s}}/\mathrm{{Hz}}$ $5 \times {10}^{3}$
PWM 调制增益${K}_{\mathrm{{pwm}}}$ 1
电流控制器比例系数${K}_{\mathrm{p}1}$ 20
电流控制器积分系数${K}_{\mathrm{i}1}$ 200
电压控制器比例系数${K}_{\mathrm{p}2}$ 0.5
电压控制器积分系数${K}_{\mathrm{i}2}$ 150
有功下垂系数${m}_{1}/\left({\mathrm{{rad}}/\mathrm{s}/\mathrm{W}}\right)$ $1 \times {10}^{-5}$
无功下垂系数${n}_{1}/\left({\mathrm{V}/\mathrm{{var}}}\right)$ $3 \times {10}^{-4}$
有功下垂系数${m}_{2}$ /(rad/s/W) $1 \times {10}^{-5}$
无功下垂系数${n}_{2}/\left({\mathrm{V}/\mathrm{{var}}}\right)$ $3 \times {10}^{-4}$
)], attaches=null, journal=Journal(id=1046111678587809797, delFlag=0, nameCn=电源学报, nameEn=Journal of Power Supply, nameHistory1=null, nameHistory2=null, issn=2095-2805, eissn=, cn=12-1420/TM, coden=null, periodic=bio-monthly, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=Mx+A2dn+ULnPHuEAI1LruQ==, journalPrice=null, startedYear=null, abbrevIsoEn=J Power Supp, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1759802942253, createdBy=null, updatedBy=18614031015, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=Mx+A2dn+ULnPHuEAI1LruQ==, picEn=yHt2vwjzkDgqh+JDCfJKoQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1162453073839375337, language=CN, name=电源学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.jops.cn/EN/home, createdTime=1755080010137, updatedTime=1755080010137, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.jops.cn/CN/column/column7.shtml, submissionAuthorUrl=https://mc03.manuscriptcentral.com/jops, submissionEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionReviewUrl=https://mc03.manuscriptcentral.com/jops, submissionCeEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionAeEditorUrl=https://mc03.manuscriptcentral.com/jops, option={"copyright":""}), JournalExt(id=1162453073902289898, language=EN, name=Journal of Power Supply, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.jops.cn/CN/home, createdTime=1755080010152, updatedTime=1755080010152, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.jops.cn/EN/column/column7.shtml, submissionAuthorUrl=https://mc03.manuscriptcentral.com/jops, submissionEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionReviewUrl=https://mc03.manuscriptcentral.com/jops, submissionCeEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionAeEditorUrl=https://mc03.manuscriptcentral.com/jops, option={"copyright":""})], databaseList=null, tenantJournalId=1146031654075715584, websiteList=[Website(id=1146832214672683008, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031654075715584, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/dyxb/EN, language=EN, createTime=1751355707101, createBy=18614031015, updateTime=1753435268747, updateBy=18614031015, name=电源学报-英文站点, tplId=1146101810881728533, title=电源学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155559379819679852, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=articleTextType, value=kx, createTime=1753436425404, updateTime=1753436425404, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379798708329, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=banner, value=null, createTime=1753436425399, updateTime=1753436425399, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379781931112, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=efYTu4aDDzS8GgTA1MjEKw==, createTime=1753436425396, updateTime=1753436425396, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379811291243, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753436425402, updateTime=1753436425402, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379802902634, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753436425400, updateTime=1753436425400, creator=18614031015, updator=18614031015)]), Website(id=1148243202240405915, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031654075715584, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/dyxb/CN, language=CN, createTime=1751692112741, createBy=18614031015, updateTime=1753435242839, updateBy=18614031015, name=电源学报-中文站点, tplId=1146099689490845704, title=电源学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618015060553758, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=articleTextType, value=kx, createTime=1751781475081, updateTime=1751781475081, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015035387931, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=banner, value=null, createTime=1751781475075, updateTime=1751781475075, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015022805018, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=efYTu4aDDzS8GgTA1MjEKw==, createTime=1751781475072, updateTime=1751781475072, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015052165149, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781475079, updateTime=1751781475079, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015043776540, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781475077, updateTime=1751781475077, creator=18614031015, updator=18614031015)])], journalTitle=电源学报, weixinUrl=null, journalUrl=http://www.jops.cn/CN/home, iacademicId=null, status=0, seqNo=null, journalTitleEn=Journal of Power Supply, journalPhotoCn=Mx+A2dn+ULnPHuEAI1LruQ==, journalPhotoEn=yHt2vwjzkDgqh+JDCfJKoQ==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2024.6.139, detailUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/10.13234/j.issn.2095-2805.2024.6.139, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dyxb/CN/PDF/10.13234/j.issn.2095-2805.2024.6.139, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/PDF/10.13234/j.issn.2095-2805.2024.6.139, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于偏最小二乘回归的低压微电网虚拟阻抗预测研究
收藏切换
PDF下载
乔金朋
电源学报 | 新能源系统 2024,22(6): 139-152
收起
收藏切换
电源学报 | 新能源系统 2024, 22(6): 139-152
基于偏最小二乘回归的低压微电网虚拟阻抗预测研究
全屏
乔金朋
作者信息
  • 安徽理工大学 电气与信息工程学院 淮南 232001
  • 乔金朋(1992-),男,通信作者,硕士研究生。研究方向:微电网技术。E-mail: 2191840042@qq.com。

Research on Prediction of Virtual Impedance in Low-voltage Microgrid Based on Partial Least Squares Regression
Jinpeng QIAO
Affiliations
  • College of Electrical and Information Engineering Anhui University of Science & Technology Huainan 232001 China
出版时间: 2024-11-30 doi: 10.13234/j.issn.2095-2805.2024.6.139
文章导航
收藏切换

针对孤岛微电网在采用基于虚拟阻抗的改进下垂控制时由于虚拟阻抗为固定值,当线路阻抗发生变化时仍存在无功功率不能精确分配和无功环流的问题,提出1种基于偏最小二乘回归的虚拟阻抗预测模型,采用线路阻抗值和补偿前系统阻抗值来预测虚拟阻抗值,实现自适应虚拟阻抗,从而克服基于虚拟阻抗的改进下垂控制存在的问题。该模型无需检测实时功率值和环流值,也无需借助通信网络。通过与神经网络模型的预测结果进行对比,证明了所提偏最小二乘回归虚拟阻抗预测模型的预测准确性优于神经网络模型。最后在MATLAB/Simulink下搭建微电网仿真系统对自适应虚拟阻抗进行仿真验证,仿真结果证明了所提模型的优越性。

微电网  /  虚拟阻抗  /  多重相关性  /  偏最小二乘回归

When the improved droop control based on virtual impedance is adopted in island microgrid, the problem of inaccurate distribution of reactive power and reactive power circulation will still occur with the changing line impedance due to the fixed value of virtual impedance. To solve this problem, a virtual impedance prediction model based on partial least squares regression (PLSR) is proposed, which uses the line impedance value and the system impedance value before compensation to predict the virtual impedance value and realizes the adaptive virtual impedance, thus overcoming the problem in the improved droop control based on virtual impedance. There is no need to detect the real-time power value and circulation value, and the use of communication network is not required. Furthermore, from a comparison with the prediction results obtained by neural network models, it is proved that the prediction accuracy of the virtual impedance prediction model based on PLSR is better. At last, a simulation system of microgrid is constructed in MATLAB/Simulink to verify the adaptive virtual impedance, and simulation results show the superiority of the proposed model.

Microgrid  /  virtual impedance  /  multi-correlation  /  partial least squares regression (PLSR)
乔金朋. 基于偏最小二乘回归的低压微电网虚拟阻抗预测研究. 电源学报, 2024 , 22 (6) : 139 -152 . DOI: 10.13234/j.issn.2095-2805.2024.6.139
Jinpeng QIAO. Research on Prediction of Virtual Impedance in Low-voltage Microgrid Based on Partial Least Squares Regression[J]. Journal of Power Supply, 2024 , 22 (6) : 139 -152 . DOI: 10.13234/j.issn.2095-2805.2024.6.139
随着风电、光伏等新能源的快速发展, 分布式电源 DG(distributed generation)以微电网的形式得到了广泛应用[1-2]。低压微电网以孤岛模式运行时, 通常采用有功/频率、无功/电压的下垂控制策略。 当各 DG 的线路阻抗不一致时, 会导致无功功率不能按逆变器容量比例分配和无功环流问题, 影响微电网系统的电能质量和稳定性。因此, 无功功率的合理分配和环流抑制问题成为微电网研究的热点之一。
文献[3-5]采用基于虚拟阻抗的改进下垂控制, 有效改善了因线路阻抗不匹配造成的无功功率分配不平衡问题, 但虚拟阻抗均采用固定值, 当线路阻抗发生改变时无法有效补偿, 仍存在无功功率分配不平衡和无功环流问题; 文献[6]提出自适应虚拟阻抗方法, 将坐标旋转的环流构成虚拟阻抗, 并通过 PI 控制使线路等效阻抗值趋于相等, 实现了功率均衡分配, 但需要实时采集环流且环流值计算复杂;文献[7]将实时无功功率与设定无功功率的差值构成虚拟阻抗, 并通过积分器调整虚拟阻抗值, 不仅补偿了电压降落, 还实现了无功功率均分, 但需要实时采集无功功率值并依靠通信线路, 实时性不高;文献[8-9]均用动态调整下垂系数的方法, 从而使功率均衡分配, 但下垂系数的改变会降低系统稳定性, 且文献[8]的动态下垂系数计算复杂, 不易实现; 文献[9]方法在大功率场合时, 电压和频率较容易超出其限幅范围。在上述改进方法中, 对于同样的功率分配误差时, 相较于固定值虚拟阻抗法和动态下垂系数法, 自适应虚拟阻抗改进策略拥有更高的系统稳定性。
随着机器学习、深度学习算法在诸多领域的广泛应用, 出现了多种基于机器学习和深度学习的预测模型, 其中时间序列、回归分析、神经网络是目前较为主流的预测算法。时间序列预测算法可以从时间序列中找出变量变化的特征、趋势及发展规律, 从而对变量的未来变化进行有效预测[10-11]。多元线性回归是对变量间的相关性进行定量分析的方法, 多用于多输入、单输出回归分析, 在样本个数与自变量个数相对较少情况下一般选择最小二乘法、向前选择变量法、逐步回归法, 但在进行回归分析时会出现多重共线性现象,导致伪回归[12]。 偏最小二乘回归 PLSR(partial least squares regression)是 1 种多对多线性回归建模方法, 尤其是当 2 组变量数量较多且均存在多重相关性, 而观测数据的数量又较少时, 用 PLSR 建立的模型具有传统的经典回归分析等方法所没有的优点[13-14]。偏最小二乘回归分析具有主成分分析、典型相关分析和线性回归分析等方法的特点[15-16],在数据分析中不仅可以建立 1 个更为合理的回归模型, 还可以同时进行一些类似于主成分分析和典型相关分析的研究内容, 可提供更为丰富和深入的信息。反向传播 BP(back propagation) 神经网络是 1 种具有 3 层结构的前馈神经网络, 在训练过程中利用梯度下降法更新权值, 直到网络输出误差小于预先设定的阈值, 或进行到预先设定的学习次数为止, 具有很强的非线性映射能力和泛化能力[17-18]。与 BP 神经网络相比,径向基函数 RBF(radial basis function)神经网络具有训练时间更短、不存在局部极小值等优点, 并且仅有 1 个隐含层, 因此通过调整隐含层神经元的个数即可提高预测精度[19-20]。
为了解决采用固定值虚拟阻抗改进下垂控制存在的问题, 本文结合机器学习的预测算法, 提出 1 种基于偏最小二乘回归的虚拟阻抗预测模型, 实现了自适应虚拟阻抗。该模型具有运算速度快、模型简单、无需通信链路、无需采集环流值和功率值、 不影响系统稳定性的优点。
微电网结构如图1所示, 其基本结构包括: DG 和公共连接点 PCC(point of common coupling)。
各 DG 单元在孤岛运行模式时通常采用基于虚拟阻抗的改进下垂控制策略[21-23],其下垂控制方程为
$\left\{\begin{array}{l} f ={f}_{\mathrm{o}}- m\left({P -{P}_{\mathrm{o}}}\right)\\ U ={U}_{\mathrm{o}}- n\left({Q -{Q}_{\mathrm{o}}}\right)\end{array}\right.$
式中:$f$ 为实时频率;${f}_{0}$ 为额定电压频率;$m$ 为有功下垂系数;$U$ 为实时电压;${U}_{0}$ 为额定电压幅值;$P$$Q$ 分别为实时有功功率和无功功率;$n$ 为无功下垂系数;${P}_{\mathrm{o}}$${Q}_{\mathrm{o}}$ 分别为额定有功功率和无功功率。
带有虚拟阻抗控制环的逆变器控制框图如图2所示。首先, 通过前一级下垂控制环节得到参考电压${u}_{\mathrm{r}}$; 然后,分别通过电压控制环${G}_{2}\left( s\right)$ 和电流控制环${G}_{1}\left( s\right)$ 得到调制波,经过 SPWM 调制环节得到滤波前的逆变器的输出电压${u}_{1}$; 最后,通过$\mathrm{{LC}}$ 滤波网络得到最终的输出电压$u$。逆变器控制框图考虑了线路阻抗引起的电压降落问题, 如图中虚线所示,最终得到逆变器接入$\mathrm{{PCC}}$ 处的电压${u}_{0}$。虚拟阻抗法是在电压、电流双环控制器中加入逆变器负载电流${i}_{\mathrm{o}}$ 的负反馈构成虚拟阻抗环。
采用虚拟阻抗后系统阻抗传递函数表示为
${G}_{\mathrm{z}}\left( s\right)= {G}_{\mathrm{u}}\left( s\right){Z}_{\mathrm{v}}\left( s\right)+ {Z}_{\mathrm{o}}\left( s\right)+ {Z}_{\mathrm{l}}\left( s\right)$
式中:${G}_{\mathrm{u}}\left( s\right)$ 为前向通道传递函数 (电压闭环传递函
数);${Z}_{\mathrm{v}}\left( s\right)$ 为虚拟阻抗传递函数;${Z}_{\mathrm{o}}\left( s\right)$ 为逆变器输
出阻抗传递函数;${Z}_{l}\left( s\right)$ 为线路阻抗传递函数。各项
传递函数表达式为
$\left\{\begin{array}{l}{G}_{\mathrm{u}}\left( s\right)= \frac{{K}_{\mathrm{{pwm}}}{G}_{1}\left( s\right){G}_{2}\left( s\right)}{{C}_{\mathrm{f}}{L}_{\mathrm{f}}T{s}^{3}+ \left({{C}_{\mathrm{f}}{L}_{\mathrm{f}}+ {C}_{\mathrm{f}}{R}_{\mathrm{f}}T}\right){s}^{2}+ \left\lbrack {T +{C}_{\mathrm{f}}{R}_{\mathrm{f}}+ {C}_{\mathrm{f}}{R}_{\mathrm{{pwm}}}{G}_{1}\left( s\right)}\right\rbrack s +{K}_{\mathrm{{pwm}}}{G}_{1}\left( s\right){G}_{2}\left( s\right)+ 1}\\{Z}_{\mathrm{o}}\left( s\right)= \frac{{L}_{\mathrm{f}}{T}_{\mathrm{s}}{Z}^{3}+ \left({{L}_{\mathrm{f}}+ {R}_{\mathrm{f}}T}\right) s +{K}_{\mathrm{{pwm}}}{G}_{1}\left( s\right)+ {R}_{\mathrm{f}}}{{C}_{\mathrm{f}}{L}_{\mathrm{f}}{L}_{\mathrm{f}}{T}^{3}+ \left({{C}_{\mathrm{f}}{L}_{\mathrm{f}}+ {C}_{\mathrm{f}}{R}_{\mathrm{f}}T}\right){s}^{2}+ \left\lbrack {T +{C}_{\mathrm{f}}{R}_{\mathrm{f}}+ {C}_{\mathrm{f}}{R}_{\mathrm{{pwm}}}{G}_{1}\left( s\right)}\right\rbrack s +{K}_{\mathrm{{pwm}}}{G}_{1}\left( s\right){G}_{2}\left( s\right)+ 1}\\{Z}_{\mathrm{i}}\left( s\right)= {R}_{\mathrm{i}}+ {L}_{\mathrm{v}}S \\{Z}_{\mathrm{v}}\left( s\right)= {R}_{\mathrm{v}}+ {L}_{\mathrm{v}}S \end{array}\right.$
式中:${K}_{\mathrm{{pwm}}}$ 为逆变器增益;${C}_{\mathrm{f}}\text{、}{L}_{\mathrm{f}}\text{、}{R}_{\mathrm{f}}$ 分别为滤波电容、滤波电感、寄生电阻;$T$ 为时间常数;${R}_{1}\text{、}{L}_{1}$ 为线路阻抗;${R}_{\mathrm{v}}\text{、}{L}_{\mathrm{v}}$ 为虚拟阻抗。
1.1 节基于虚拟阻抗的改进下垂控制中, 虚拟阻抗均在${dq}$ 坐标系实现,因此本文也将在${dq}$ 坐标系下实现虚拟阻抗。设虚拟阻抗引起的电压降落为${\Delta u}$,则${\Delta u}= {Z}_{\mathrm{v}}{i}_{\mathrm{o}}= \left({{R}_{\mathrm{v}}+ \mathrm{j}{L}_{\mathrm{v}}\omega }\right)\left({{i}_{\mathrm{o}d}+ \mathrm{j}{i}_{\mathrm{o}q}}\right)= \left({{R}_{\mathrm{v}}{i}_{\mathrm{o}d}- }\right.$ $\left.{{L}_{\mathrm{v}}\omega {i}_{\mathrm{o}q}}\right)+ \mathrm{j}\left({{R}_{\mathrm{v}}{i}_{\mathrm{o}q}+ {L}_{\mathrm{v}}\omega {i}_{\mathrm{o}d}}\right)= \Delta {u}_{d}+ \mathrm{j}\Delta {u}_{q}$,最终得到电压降落纵分量$\Delta {u}_{d}$ 和横分量$\Delta {u}_{q}$ 分别为
$\left\{\begin{array}{l}\Delta {u}_{d}= {R}_{\mathrm{v}}{i}_{\mathrm{o}d}- {L}_{\mathrm{v}}\omega {i}_{\mathrm{o}q}\\\Delta {u}_{q}= {R}_{\mathrm{v}}{i}_{\mathrm{o}q}+ {L}_{\mathrm{v}}\omega {i}_{\mathrm{o}d}\end{array}\right.$
图3为虚拟阻抗在${dq}$ 坐标系下的实现方法控制框图,其中参考电压幅值${u}_{\text{ref }d}$${u}_{\text{ref }q}$ 由下垂方程得到,分别为电压的$d$ 轴和$q$ 轴分量。
采用虚拟阻抗对系统阻抗进行补偿时需要满足以下 2 个要求。
(1)采用虚拟阻抗后使系统阻抗${G}_{\mathrm{z}}\left( s\right)$ 在基波频率${\omega }_{\mathrm{b}}$ 处近似为感性,并尽量使其在多次谐波频率处呈阻性, 这样不但可以满足功率近似解耦的要求, 而且能有效抑制逆变器输出电流的多次谐波。同时,功率近似解耦的阻感比应小于 0.83,即系统阻抗在基波频率处的相位角满足$\angle {G}_{\mathrm{z}}\left({\mathrm{j}{\omega }_{\mathrm{b}}}\right)> {50}^{\circ }{}^{\left\lbrack {24}\right\rbrack }$
(2)为了抑制逆变器间的无功环流, 改善逆变器间的无功功率分配精度, 需要使逆变器 1 和 2 的系统阻抗${G}_{{z}_{1}}\left( s\right)$${G}_{{z}_{2}}\left( s\right)$ 在基波频率${\omega }_{b}$ 处的幅值与设计容量呈反比例关系, 即逆变器系统阻抗在基波频率处的幅值与其对应的下垂系数${n}_{1}$${n}_{2}$ 呈正比例关系。
综上所述, 对于 2 台采用下垂控制的电压源型逆变器, 两者在基波频率处的系统阻抗幅值和相位角应满足
$\left\{\begin{array}{l}\frac{\left|{G}_{{z}_{1}}\left(\mathrm{j}{\omega }_{b}\right)> {50}^{\circ }\right|}{\left|{G}_{{z}_{2}}\left(\mathrm{j}{\omega }_{b}\right)> {50}^{\circ }\right|} \approx \frac{{n}_{1}}{{n}_{2}}\\\angle {G}_{{z}_{1}}\left({\mathrm{j}{\omega }_{b}}\right)\approx \angle {G}_{{z}_{2}}\left({\mathrm{j}{\omega }_{b}}\right)> {50}^{\circ }\end{array}\right.$
本文假设 2 台并联运行的逆变器具有相同容量和不同容量 2 种情形。在相同容量时, 逆变器 1 和逆变器 2 的容量比为$1 : 1$。为了使得采用虚拟阻抗补偿后的逆变器系统阻抗在基波频率处的幅值比接近$1 : 1$,需要使补偿后的等效阻抗${Z}_{\text{eql }}$${Z}_{\mathrm{{eq}}2}$ 的实部和虚部(对应电阻分量和电抗分量)满足$\operatorname{Re}\left({Z}_{\text{eql }}\right)\approx \operatorname{Re}\left({Z}_{\mathrm{{eq}}2}\right),\operatorname{Im}\left({Z}_{\mathrm{{eq}}1}\right)\approx \operatorname{Im}\left({Z}_{\mathrm{{eq}}2}\right)$,即${R}_{\mathrm{{eq}}1}\approx$ ${R}_{\mathrm{{eq}}2}$,${X}_{\mathrm{{eq}}1}\approx {X}_{\mathrm{{eq}}2}$。在不同容量时,逆变器 1 和逆变器 2 的容量比为$1 : 2$。为了使得采用虚拟阻抗补偿后的逆变器系统阻抗在基波频率处的幅值比接近$2 : 1$,需要使补偿后的等效阻抗${Z}_{\text{eql }}$${Z}_{\text{eq2 }}$ 的实部和虚部(对应电阻分量和电抗分量)满足$\operatorname{Re}\left({Z}_{\text{eql }}\right)\approx$ $2\operatorname{Re}\left({Z}_{\mathrm{{eq}}2}\right),\operatorname{Im}\left({Z}_{\mathrm{{eq}}1}\right)\approx 2\operatorname{Im}\left({Z}_{\mathrm{{eq}}2}\right)$,即${R}_{\mathrm{{eq}}1}\approx 2{R}_{\mathrm{{eq}}2},{X}_{\mathrm{{eq}}1}\approx$ $2{X}_{\mathrm{{eq}}2}$。本文所用样本数据和 PLSR 回归模型的建立、分析均以相同容量为例。
假设$p$ 个因变量$Y =\left\{{{y}_{1},{y}_{2},\cdots,{y}_{p}}\right\}$$m$ 个自变量$X =\left\{{{x}_{1},{x}_{2},\cdots,{x}_{m}}\right\}$ 的建模问题。偏最小二乘回归建模思路: 首先,在自变量集$X$ 中提取第 1 个成分${u}_{1}\left({u}_{1}\right.$$X$ 的线性组合,且尽可能多地提取$X$ 中的变异信息); 同时,在因变量集$Y$ 中也提取第 1 个成分${v}_{1}$,并且使成分对${u}_{1}$${v}_{1}$ 具有最大相关性。然后建立因变量$Y$${u}_{1}$ 的回归方程,此时如果回归方程已达到满意的精度, 则可以中止算法, 否则继续提取第 2 对成分${u}_{2}$${v}_{2}$,直至精度满足要求。满足精度要求后,假设已经对自变量集$X$ 提取了$r$ 个成分${u}_{1},{u}_{2},\cdots,{u}_{r}$。偏最小二乘回归将首先建立因变量集$Y$ 与提出成分${u}_{1},{u}_{2},\cdots,{u}_{r}$ 的回归方程,然后再表示为因变量集$Y$ 与原自变量集$X$ 的回归方程, 即偏最小二乘回归方程[13-14]。
假设自变量集$X$ 和因变量集$Y$$n$ 次标准化观测数据矩阵分别记为$\mathbf{A}$$\mathbf{B}$,即
$\mathbf{A}= \left\lbrack \begin{matrix}{a}_{11}& \cdots &{a}_{1m}\\\vdots && \vdots \\{a}_{n1}& \cdots &{a}_{nm}\end{matrix}\right\rbrack $
$\mathbf{B}= \left\lbrack \begin{matrix}{b}_{11}& \cdots &{b}_{1p}\\\vdots && \vdots \\{b}_{n1}& \cdots &{b}_{np}\end{matrix}\right\rbrack $
通常情况下, 为避免所选取参量的数值不在同一数量级或者为消除不同量纲带来的影响,首先需要对所选取参量的数据进行标准化处理。自变量的观测数据矩阵记为$\mathbf{A}= \left({a}_{ij}\right)$,因变量的观测数据矩阵记为$\mathbf{B}= \left({b}_{ij}\right)$。将自变量进行 z-score 标准化变换,即
$\left\{\begin{array}{l}{\widetilde{a}}_{ij}= \frac{{a}_{ij}- {\mu }_{j}}{{s}_{j}}\;i = 1,2,\cdots, n;j = 1,2,\cdots, m \\{\mu }_{j}= \frac{1}{n}\mathop{\sum }\limits_{{i = 1}}^{n}{a}_{ij}\\{s}_{j}= \sqrt{\frac{1}{n - 1}\mathop{\sum }\limits_{{i = 1}}^{n}{\left({a}_{ij}- {\mu }_{j}\right)}^{2}}\end{array}\right.$
式中:${a}_{ij}$${\widetilde{a}}_{ij}$ 分别为标准化前、后样本数据;${\mu }_{j}$${s}_{j}$ 分别为第$j$ 个自变量的样本均值和样本标准差。
同理,可以得到因变量标准化变换有${\widetilde{b}}_{ij}\text{、}{\mu }_{j}\text{、}{s}_{j \circ }$
分别提取 2 个变量集的第 1 对成分${u}_{1}\text{、}{v}_{1}$,并使之具有最大相关性。${u}_{1}$ 为自变量集$X$ 的线性组合,${v}_{1}$ 为因变量集$Y$ 的线性组合,即
$\left\{\begin{array}{l}{u}_{1}= {\alpha }_{11}{x}_{1}+ \cdots +{\alpha }_{1m}{x}_{m}= {\mathbf{\rho }}^{\left( 1\right)\mathrm{T}}X \\{v}_{1}= {\beta }_{11}{y}_{1}+ \cdots +{\beta }_{1p}{y}_{p}= {\mathbf{\gamma }}^{\left( 1\right)\mathrm{T}}Y \end{array}\right.$
式中:${\alpha }_{11}\sim {\alpha }_{1m}$ 为自变量${x}_{1}\sim {x}_{m}$ 对应的系数;${\beta }_{11}\sim$ ${\beta }_{1p}$ 为因变量${y}_{1}\sim {y}_{p}$ 对应的系数;${\rho }^{\left( 1\right)} \sim {\gamma }^{\left( 1\right)}$ 为系数的向量形式。
由 2 组变量集的标准化观测数据矩阵$\mathbf{A}$$\mathbf{B}$,可以计算第 1 对成分的得分向量,分别为${\widehat{\mathbf{u}}}_{1}$${\widehat{\mathbf{v}}}_{1}$,即
${\widehat{\mathbf{u}}}_{1}= \mathbf{A}{\mathbf{\rho }}^{\left( 1\right)} =\left\lbrack \begin{matrix}{a}_{11}& \cdots &{a}_{1m}\\\vdots && \vdots \\{a}_{n1}& \cdots &{a}_{nm}\end{matrix}\right\rbrack \left\lbrack \begin{matrix}{a}_{11}\\\vdots \\{a}_{1m}\end{matrix}\right\rbrack $
${\widehat{\mathbf{v}}}_{1}= \mathbf{B}{\mathbf{\gamma }}^{\left( 1\right)} =\left\lbrack \begin{matrix}{b}_{11}& \cdots &{b}_{1m}\\\vdots && \vdots \\{b}_{n1}& \cdots &{b}_{nm}\end{matrix}\right\rbrack \left\lbrack \begin{matrix}{b}_{11}\\\vdots \\{b}_{1m}\end{matrix}\right\rbrack $
式中:${\begin{Vmatrix}{\mathbf{\rho }}^{\left( 1\right)}\end{Vmatrix}}^{2}= 1;{\begin{Vmatrix}{\mathbf{\gamma }}^{\left( 1\right)}\end{Vmatrix}}^{2}= 1$
建立因变量集$Y$${u}_{1}$ 的回归及自变量集$X$${u}_{1}$ 的回归,即
$\left\{\begin{array}{l}\mathbf{A}= {\widehat{\mathbf{u}}}_{1}{\mathbf{\sigma }}^{\left( 1\right)\mathrm{T}}+ {\mathbf{A}}_{1}\\\mathbf{B}= {\widehat{\mathbf{u}}}_{1}{\mathbf{\tau }}^{\left( 1\right)\mathrm{T}}+ {\mathbf{B}}_{1}\end{array}\right.$
式中:${\mathbf{\sigma }}^{\left( 1\right)}$${\mathbf{\tau }}^{\left( 1\right)}$ 为回归系数;${\mathbf{A}}_{1}$${\mathbf{B}}_{1}$ 为残差阵。
回归系数和残差阵可分别表示为
$\left\{\begin{array}{l}{\mathbf{\sigma }}^{\left( 1\right)} ={\mathbf{A}}^{\mathrm{T}}{\widehat{\mathbf{u}}}_{1}/{\begin{Vmatrix}{\widehat{\mathbf{u}}}_{1}\end{Vmatrix}}^{2}\\{\mathbf{\tau }}^{\left( 1\right)} ={\mathbf{B}}^{\mathrm{T}}{\widehat{\mathbf{u}}}_{1}/{\begin{Vmatrix}{\widehat{\mathbf{u}}}_{1}\end{Vmatrix}}^{2}\end{array}\right.$
$\left\{\begin{array}{l}{\mathbf{A}}_{1}= \mathbf{A}- {\widehat{\mathbf{u}}}_{1}{\mathbf{\sigma }}^{\left( 1\right)\mathrm{T}}\\{\mathbf{B}}_{1}= \mathbf{B}- {\widehat{\mathbf{u}}}_{1}{\mathbf{\tau }}^{\left( 1\right)\mathrm{T}}\end{array}\right.$
如果残差阵${\mathbf{B}}_{1}$ 中元素的绝对值近似于 0,则认为用第 1 对成分建立的回归方程精度已经满足要求, 此时可以停止抽取其他成分。否则用残差阵${\mathbf{A}}_{1}$${\mathbf{B}}_{1}$ 代替$\mathbf{A}$$\mathbf{B}$,重复进行以上步骤,直至精度满足要求。
$n \times m$ 的数据阵$\mathbf{A}$ 的秩为$r \leq \min \left({n - 1, m}\right)$, 同时假设提取了$r$ 个成分${u}_{1},{u}_{2},\cdots,{u}_{r}$,则有
$\left\{\begin{array}{l}\mathbf{A}= {\widehat{\mathbf{u}}}_{1}{\mathbf{\sigma }}^{\left( 1\right)\mathrm{T}}+ \cdots +{\widehat{\mathbf{u}}}_{r}{\mathbf{\sigma }}^{\left( r\right)\mathrm{T}}+ {\mathbf{A}}_{r}\\\mathbf{B}= {\widehat{\mathbf{u}}}_{1}{\mathbf{\tau }}^{\left( 1\right)\mathrm{T}}+ \cdots +{\widehat{\mathbf{u}}}_{r}{\mathbf{\tau }}^{\left( r\right)\mathrm{T}}+ {\mathbf{B}}_{r}\end{array}\right.$
最后将所提取的成分${u}_{k}= {\alpha }_{k1}{x}_{1}+ \cdots +{\alpha }_{km}{x}_{m}(k = 1,2,\cdots$,$r)$ 代入$Y ={u}_{1}{\tau }^{\left( 1\right)} +\cdots +{u}_{\mathrm{r}}{\tau }^{\left( r\right)}$,即可得到$p$ 个因变量的偏最小二乘回归方程为
${y}_{j}= {c}_{j1}{x}_{1}+ \ldots +{c}_{jm}{x}_{m}\;j = 1,2,\cdots, p $
通常偏最小二乘回归并不需要选用所有的$r$ 个成分${u}_{1},{u}_{2},\cdots,{u}_{r}$ 来建立回归方程。与主成分分析类似,仅需选取前$k$ 个成分$\left({k \leq r}\right)$ 即可得到预测准确度较好的回归模型。$k$ 个成分的提取可以通过交叉有效性检验来确定。在建模过程中, 自变量集每次舍去第$i$ 个观测数据$\left({i = 1,2,\cdots, n}\right)$,对余下的$n - 1$ 个观测数据进行偏最小二乘回归建模, 并建立当提取$h\left({h \leq r}\right)$ 个成分时的回归方程; 然后将舍去的第$i$ 个观测数据代入回归方程,最终得到${y}_{j}(j = 1,2,\cdots$,$p)$ 在第$i$ 个观测点上的预测值${\widehat{b}}_{\left( i\right) j}\left( h\right)$。对自变量集重复验证完成后,得到提取$h$ 个成分时第$j$ 个因变量${y}_{j}\left({j = 1,2,\cdots, p}\right)$ 的预测误差平方和为
${\operatorname{PRESS}}_{j}\left( h\right)= \mathop{\sum }\limits_{{i = 1}}^{n}{\left\lbrack {b}_{ij}- {\widehat{b}}_{\left( i\right) j}\left( h\right)\right\rbrack }^{2}\;j = 1,2,\cdots, p $
因变量集$Y$ 的预测误差平方和为
$\operatorname{PRESS}\left( h\right)= \mathop{\sum }\limits_{{i = 1}}^{p}{\operatorname{PRESS}}_{j}\left( h\right)$
然后对所有的样本点拟合含有$h$ 个成分时的回归方程。记第$i$ 个样本点的预测值为${\widehat{\mathbf{b}}}_{ij}\left( h\right)$,则${y}_{j}\left({j = 1,2,\cdots, p}\right)$ 的误差平方和为
$ S{S}_{j}\left( h\right)= \mathop{\sum }\limits_{{i = 1}}^{n}{\left\lbrack {b}_{ij}- {\widehat{b}}_{\left( i\right) j}\left( h\right)\right\rbrack }^{2}$
因变量集$Y$ 的误差平方和为
${SS}\left( h\right)= \mathop{\sum }\limits_{{j = 1}}^{p}S{S}_{j}\left( h\right)$
由式(17)和式(19)可得交叉有效性为
${Q}_{h}^{2}= 1 -\frac{\operatorname{PRESS}\left( h\right)}{\operatorname{SS}\left({h - 1}\right)} $
如果提取$h$ 个成分${u}_{h}$ 时,有${Q}_{h}^{2}< 1 -{0.95}^{2}= {0.0975}$, 则模型精度达到要求, 继续提取下一个成分对改善模型的精度无意义,可停止提取; 若${Q}_{h}^{2}\geq {0.0975}$, 则表示抽取的$h$ 个成分的边际贡献率显著,应继续提取第$h + 1$ 个成分。
在 PLSR 分析中,为了量化自变量${x}_{j}$ 对因变量$y$ 的影响程度,常用变量投影重要性指标${V}_{j}$ 进行观测。设根据交叉有效性原则共提取了$h$ 个成分,则定义自变量${x}_{j}$ 的变量投影重要性指标为
${V}_{j}= {\left\lbrack \frac{m}{R\left({y;{t}_{1},{t}_{2},\cdots,{t}_{h}}\right)}\mathop{\sum }\limits_{{k = 1}}^{h}R\left( y;{t}_{k}\right){\omega }_{kj}^{2}\right\rbrack }^{1/2}$
式中:$m$ 为自变量个数;$R\left({y;{t}_{k}}\right)$$R\left({y;{t}_{1},{t}_{2},\cdots,{t}_{h}}\right)$ 分别为${t}_{k}$$y$ 的解释能力和${t}_{1},{t}_{2},\cdots,{t}_{h}$$y$ 的累积解释能力;${\omega }_{kj}$ 为转换系数。若某个自变量的${V}_{j}> 1$,则认为该自变量对因变量影响显著。
样本数据的选取存在随机性, 不一定所有数据均有效。为了对样本进行有效性验证, 需剔除样本中的特异点。特异点是对主成分有过大贡献率的样本点, 特异点的存在会影响回归拟合效果, 因此在回归分析中应予以剔除并重新建立模型进行拟合,一般采用二维${T}^{2}$ 椭圆图法对特异点进行检验。
参量的选取见表1。其中,因变量$Y =\left\{{{y}_{1},{y}_{2},{y}_{3}}\right.$,$\left.{y}_{4}\right\}$,分别为逆变器 1 虚拟电阻${y}_{1}$ 、逆变器 1 虚拟电抗${y}_{2}$ 、逆变器 2 虚拟电阻${y}_{3}$ 、逆变器 2 虚拟电抗${y}_{4}$; 自变量$X =\left\{{{x}_{1},{x}_{2},{x}_{3},{x}_{4},{x}_{5},{x}_{6},{x}_{7},{x}_{8}}\right\}$,分别为逆变器 1 线路电阻${x}_{1}$ 、逆变器 1 线路电抗${x}_{2}$ 、逆变器 2 线路电阻${x}_{3}$ 、逆变器 2 线路电抗${x}_{4}$ 、逆变器 1 系统阻抗在基波频率处的相位角${x}_{5}$ 、逆变器 2 系统阻抗在基波频率处的相位角${x}_{6}$ 、逆变器 1 系统阻抗在基波频率处的幅值${x}_{7}$ 、逆变器 2 系统阻抗在基波频率处的幅值${x}_{8}$。根据虚拟阻抗的设计原则并选取较小的虚拟电阻计算选取参量, 样本数据由 MATLAB 计算得到, 如表2所示。样本数据前 20 组用于建模, 后 10 组用于模型测试。低压微电网每千米线路阻抗${Z}_{\mathrm{l}}= {0.642}+ \mathrm{j}{0.083\Omega }$
主成分个数根据交叉有效性原则检验确定, 当选取 20 组样本数据进行建模时, 检验结果如表3所示, 可知: 前 3 个主成分的交叉有效性均大于 0.0975 ; 第 4 个主成分的交叉有效性为 -0.111784, 小于 0.0975,不满足交叉有效性提取条件。这表明该成分不能明显改善模型的拟合能力。因此, 模型仅提取前 3 个主成分, 此时模型对因变量的累积解释能力将高达 99.9999%,累积交叉有效性为 99.9998%。
不同样本长度交叉有效性检验结果如表4所示, 可知: 当选取 15 组样本时需要提取第 8 个成分才能满足交叉有效性检验条件, 主成分过多会大大增加计算量, 影响运算速度; 采用 20 组、25 组和 30 组样本数据, 仅需提取第 4 个主成分即可满足交叉有效性检验条件, 兼顾了运算速度和预测精度。检验结果证明了样本数据长度对模型预测精度的影响, 在运算速度和预测精度相同的条件下应尽可能少的使用样本数据, 因此使用 20 组样本数据建模最佳。
运用 SIMCA-P 软件绘制出本文所提模型的二维${T}^{2}$ 椭圆,如图4所示。可见,所有样本点均落在椭圆平面内, 证明样本数据中不存在特异点, 是合理的, 无需调整。
为了分析各自变量对因变量的影响程度, 绘制自变量 VIP 直方图,如图5所示。可见, 自变量${V}_{j}$ 顺序为${x}_{3}> {x}_{4}> {x}_{8}> {x}_{6}> {x}_{1}> {x}_{2}> {x}_{5}> {x}_{7}$。其中,${x}_{3}$${x}_{4}\text{、}{x}_{6}\text{、}{x}_{8}$ 的 VIP 值均超过 1,说明${x}_{3}\text{、}{x}_{4}\text{、}{x}_{6}\text{、}{x}_{8}$ 是影响因变量的重要因素。
经过主成分提取和特异点剔除, 最终得到标准化偏最小二乘回归方程为
${y}_{1}= {0.3558}- {0.2519}{x}_{1}- {1.9484}{x}_{2}+ \\{0.1729}{x}_{3}+ {1.3371}{x}_{4}+ {0.0081}{x}_{5}- \\{0.005}6{x}_{6}- {0.4163}{x}_{7}+ {0.2889}{x}_{8}\\{y}_{2}= -{0.1427}- {0.0327}{x}_{1}- {0.2527}{x}_{2}+ \\{0.287}9{x}_{3}+ {2.2269}{x}_{4}+ {0.0011}{x}_{5}- \\{0.009}2{x}_{6}- {0.049}7{x}_{7}+ {0.4863}{x}_{8}\\{y}_{3}= {0.3672}+ {3.0552}\times {10}^{-5}{x}_{1}+ \\{2.3632}\times {10}^{-4}{x}_{2}- {0.0782}{x}_{3}- \\{0.6046}{x}_{4}- {1.9650}\times {10}^{-5}{x}_{5}+ \\{0.0025}{x}_{6}- {0.0012}{x}_{7}- {0.1321}{x}_{8}\\{y}_{4}= -{0.1413}- {9.8519}\times {10}^{-5}{x}_{1}- \\{76204}\times {10}^{-4}{x}_{2}+ {0.2554}{x}_{3}+ \\{1.9759}{x}_{4}+ {6.438}\times {10}^{-5}{x}_{5}- \\{0.008}{2}_{{x}_{6}}+ {0.0040}{x}_{7}+ {0.4319}{x}_{8}$
对比式 (23)$\sim$ 式 (26) 中各系数可以看出,偏最小二乘回归方程中每个自变量对应的系数接近, 不会出现因为某个自变量数据突然增大或减小而影响整个模型预测值的情况, 且方程中包含所有自变量, 充分使用了所有自变量。
使用后 10 组样本数据对模型进行验证。为了观察 4 个回归方程的模型预测精度, 设所有样本数据的虚拟阻抗实际值为$y$,利用偏最小二乘回归方程得到的预测数据为$\widehat{y}$,以$\left({\widehat{y}, y}\right)$ 为坐标值,对 10 个测试样本点绘制预测图。PLSR 虚拟阻抗预测如图6所示。定义绝对误差$\varepsilon = y -\widehat{y}$ 和相对误差$r =\left({y -\widehat{y}}\right)/y$, 如图7所示。
为了验证 PLSR 虚拟阻抗预测模型的预测准确度, 分别建立 BP 和 RBF 神经网络预测模型进行对比。BP 神经网络主要训练参数: 隐含层神经元个数为 10、训练目标最小误差为${10}^{-3}$ 、学习速率为 0.01、 训练次数为 300 ; RBF 神经网络主要训练参数: 训练目标最小误差为${10}^{-3}$ 、径向基函数分布系数为 3 、 隐含层最大神经元个数为 10、每次显示添加的神经元个数为 1。BP 神经网络虚拟阻抗预测如图8所示, 绝对误差和相对误差如图9所示。RBF 神经网络虚拟阻抗预测如图10所示, 绝对误差和相对误差如图11所示。
根据 3 种模型的虚拟阻抗预测图可见: PLSR 模型的所有测试点均在$\widehat{y}= y$ 线上均匀分布,斜率约为 1, 不存在偏离对角线的点; 而 RBF 神经网络模型有个别点偏离对角线, BP 神经网络模型几乎所有点均有偏离。从预测效果看, PLSR 模型的预测线性度优于其他 2 种神经网络模型。为进一步分析 3 种模型的预测准确度, 从预测误差中分别提取绝对误差和相对误差的最大偏差值(精确到小数点后 4 位), 如表5表6所示, 可见, PLSR 模型的预测准确度比其他 2 种神经网络模型高 10 倍以上, 优势明显。
在MATLAB/Simulink上搭建由 2 台相同容量逆变器组成的微电网仿真系统,仿真参数如表7所示。 为了验证自适应虚拟阻抗的效果, 对 3 种预测模型分别进行仿真。设置仿真时长为$2\mathrm{\;s}$。在$1\mathrm{\;s}$ 时,逆变器 1 的线路长度由${0.9}\mathrm{\;{km}}$ 切换为${0.8}\mathrm{\;{km}}$;逆变器 2 的线路长度由${1.5}\mathrm{\;{km}}$ 切换为${1.2}\mathrm{\;{km}}$,线路切换前后均采用虚拟阻抗预测值。仿真功率如图12所示。
图12可见, 线路切换前后, 3 种模型的自适应虚拟阻抗对有功功率分配无影响, 2 台逆变器的有功功率始终能够合理分配,均约为${9.2}\mathrm{\;{kW}}$。 从无功功率分配效果来看: PLSR 模型的分配效果最佳, 2 台逆变器的无功功率始终能够合理分配, 均约为 2.3 kvar,且线路切换后无功功率调节到稳定值所用时间为${0.15}\mathrm{\;s}$,调节时间最短;$\mathrm{{RBF}}$ 模型的分配效果欠佳,线路切换前${Q}_{1}> {Q}_{2}$,切换后${Q}_{1}< {Q}_{2},2$ 台逆变器的无功功率始终无法合理分配, 差值均在${0.3}\mathrm{{kvar}}$ 以上,且线路切换后无功功率调节到稳定值所用时间为${0.3}\mathrm{\;s}$,调节时间较长;$\mathrm{{BP}}$ 模型的分配效果最差,始终${Q}_{1}< {Q}_{2}$,最大差值达${0.9}\mathrm{{kvar}}$,最小差值也为${0.4}\mathrm{{kvar}},2$ 台逆变器的无功功率始终无法合理分配, 且线路切换后无功功率调节到稳定值所用时间为${0.5}\mathrm{\;s}$,调节时间最长。
无功环流如图13所示。由图13可见: PLSR 模型由于无功分配效果最为合理, 整体无功环流值最小,无功环流值大多集中在$-{0.2}\sim {0.2}\mathrm{\;A}$,且由于调节时间最短,线路切换后无功环流值最为平稳;RBF 模型由于无功分配效果欠佳, 整体无功环流值较大,无功环流值大多超过$\pm {0.2}\mathrm{\;A}$,且由于调节时间较长, 线路切换后无功环流值存在一段不稳定时间;BP 模型由于无功分配效果最差, 整体无功环流值最大,无功环流值大多超过$\pm {0.4}\mathrm{\;A}$,且由于调节时间最长,线路切换后无功环流值最不稳定。
综上所述, 从仿真效果看, PLSR 模型的无功分配效果和无功环流抑制均优于对比模型, 说明
PLSR 模型的自适应虚拟阻抗表现优越。
本文针对采用固定值虚拟阻抗的改进下垂控制策略, 当线路阻抗变化时仍存在无功功率分配不平衡和无功环流的问题, 结合机器学习算法提出 1 种基于偏最小二乘回归的虚拟阻抗预测模型。该模型利用线路阻抗值和补偿前系统阻抗值实现自适应虚拟阻抗, 解决了上述问题。通过与对照模型的预测结果对比, 以及与 MATLAB/Simulink 仿真波形对比,验证了该模型的优越性。
(1)PLSR 模型的预测线性度、准确度均优于对照模型。
(2)PLSR 模型能够拟合出虚拟阻抗的线性回归方程, 简化了虚拟阻抗的计算过程。
(3)PLSR 模型的无功分配效果和无功环流抑制均优于对照模型, 表明该模型对虚拟阻抗的自适应性表现优越, 比对照模型更适合应用于微电网虚拟阻抗预测。
另外, 该模型具有无需实时采集环流值和功率值、无需通信链路、不影响系统稳定性等优点。
参考文献 引证文献
排序方式:
[1]
Le Minh P, Duc D H V, Xuan H P T, et al. A new control strategy of power sharing in islanded microgrids[C]// 2017 International Conference on System Science and Engineering(ICSSE). Ho Chi Minh City, Vietnam, 2017: 175-179.
[2]
Guan Yajuan, Guerrero J M, Zhao Xin, et al. Comparison of a synchronous reference frame virtual impedance-based autonomous current sharing control with conventional droop control for parallel-connected inverters[C]// 2016 IEEE 8th International Power Electronics and Motion Control Conference(IPEMC-ECCE Asia). Hefei, China, 2016: 3419-3426.
[3]
Minh P L, Xuan H P T, Duc D H V, et al. Control of power sharing in an island microgrid using virtual impedance[C]// 2017 International Conference on System Science and Engineering(ICSSE). Ho Chi Minh City, Vietnam, 2017: 154-159.
[4]
Zhang Jiyuan, Shu Jie, Ning Jia, et al. Enhanced proportional power sharing strategy based on adaptive virtual impedance in low-voltage networked microgrid[J]. IET Generation, Transmission & Distribution, 2018. 12(11): 2566-2576.
[5]
Dou Chunxia, Zhang Zhanqiang, Yue Dong, et al. Improved droop control based on virtual impedance and virtual power source in low-voltage microgrid[J]. IET Generation, Transmission & Distribution, 2017. 11(4): 1046-1054.
[6]
潘健, 陈凤娇, 张琦, 等. 基于抑制环流的自适应下垂控制改进策略[J]. 电源学报, 2023. 21(5): 101-109.
Pan Jian, Chen Fengjiao, Zhang Qi, et al. Improved strategy for adaptive droop control based on suppressing circulating current[J]. Journal of Power Supply, 2023. 21(5): 101-109 (in Chinese).
[7]
李红萍, 杨洪耕, 曾巧燕, 等. 孤岛型微电网中改进下垂控制策略[J]. 电力系统及其自动化学报, 2017. 29(4): 49-54.
Li Hongping, Yang Honggeng, Zeng Qiaoyan, et al. Improved droop control strategy for islanded microgrid[J]. Proceedings of the CSU-EPSA, 2017. 29(4): 49-54 (in Chinese).
[8]
郭通, 李燕青, 仝年, 等. 基于自调节下垂系数的微电网控制策略[J]. 电力科学与技术学报, 2017. 32(2): 77-82, 91.
Guo Tong, Li Yanqing, Tong Nian, et al. Control strategy of micro-grid based on self-adjustable droop coefficient[J]. Journal of Electric Power Science and Technology, 2017. 32(2): 77-82, 91 (in Chinese).
[9]
王二永, 王帅. 自适应下垂系数的低压微电网功率控制策略[J]. 电力系统保护与控制, 2019. 47(23): 52-56.
Wang Eryong, Wang Shuai. Power control strategy of low voltage microgrid based on adaptive droop coefficient[J]. Power System Protection and Control, 2019. 47(23): 52-56 (in Chinese).
[10]
史卫卫, 寻鲁宁, 曹亚景, 等. 河北省居民 2015—2018 年脑梗死流行特征分析及时间序列预测[J]. 中国公共卫生, 2021. 37(12): 1800-1804.
Shi Weiwei, Xun Luning, Cao Yajing, et al. Prevalence characteristics of cerebral infarction among residents in Hebei province, 2015—2018: A time series analysis[J]. Chinese Journal of Public Health, 2021. 37(12): 1800-1804 (in Chinese).
[11]
周生辉, 刘廷玺, 段利民, 等. 基于时间序列的海流兔河流域降水量模拟预测分析[J]. 水土保持研究, 2021. 28(5): 88-94.
Zhou Shenghui, Liu Tingxi, Duan Limin, et al. Simulation and prediction of precipitation in Hailiutu river basin based on time series[J]. Research of Soil and Water Conservation, 2021. 28(5): 88-94 (in Chinese).
[12]
苏卫星, 任欢. 基于改进偏最小二乘回归的矿浆元素含量预测[J]. 计算机工程与设计, 2019. 40(9): 2594-2600.
Su Weixing, Ren Huan. Prediction of slurry element content based on improved partial least squares regression[J]. Computer Engineering and Design, 2019. 40(9): 2594-2600 (in Chinese).
[13]
王雁凌, 吴梦凯. 经济新常态下基于偏最小二乘回归的中长期负荷预测模型[J]. 电力自动化设备, 2018. 38(3): 133-139.
Wang Yanling, Wu Mengkai. Medium and long term load forecasting model based on partial least-square regression under new normal economy[J]. Electric Power Automation Equipment, 2018. 38(3): 133-139 (in Chinese).
[14]
高腾, 许焕敏. 基于偏最小二乘回归的疏浚产量预测方法[J]. 水运工程, 2020. 4): 175-179.
Gao Teng, Xu Huanmin. Prediction method for dredging production based on partial least squares regression[J]. Port & Waterway Engineering, 2020. 4): 175-179 (in Chinese).
[15]
李泽文, 邹彬, 赵廷, 等. 基于偏最小二乘回归的高精度同步时钟[J]. 电力系统及其自动化学报, 2019. 31(1): 1-6.
Li Zewen, Zou Bin, Zhao Ting, et al. High-precision synchronous clock based on partial least squares regression[J]. Proceedings of the CSU-EPSA, 2019. 31(1): 1-6 (in Chinese).
[16]
张志勇, 张飞, 刘志强, 等. 无刷直流电机输出转矩的非线性偏最小二乘回归估计[J]. 电工技术学报, 2017. 32(5): 62-69.
Zhang Zhiyong, Zhang Fei, Liu Zhiqiang, et al. Brushless DC motor torque estimation based on nonlinear partial least square method[J]. Transactions of China Electrotechnical Society, 2017. 32(5): 62-69 (in Chinese).
[17]
王胜, 冯兴明, 周宇, 等. 基于BP神经网络预测的微网系统 dq 轴谐波阻抗的主动测量策略[J]. 电测与仪表, 2021. 58(3): 118-125.
Wang Sheng, Feng Xingming, Zhou Yu, et al. An active measurement strategy of dq-axis harmonic impedance in micro-gridsystem based on BP neural network prediction[J]. Electrical Measurement & Instrumentation, 2021. 58(3): 118-125 (in Chinese).
[18]
邱勇, 杨泽文, 周鑫宇, 等. 基于BP神经网络的直角折线堰过流能力预测[J]. 水电能源科学, 2021. 39(3): 74-77.
Qiu Yong, Yang Zewen, Zhou Xinyu, et al. Prediction of overflow capability of right-angle polyline weir based on BP neural network[J]. Water Resources and Power, 2021. 39(3): 74-77 (in Chinese).
[19]
王晓辉, 刘静蕾, 边会娟, 等. 基于改进BP神经网络的室内环境热舒适度预测与分析[J]. 控制工程, 2021. 28(7): 1437-1445.
Wang Xiaohui, Liu Jinglei, Bian Huijuan, et al. Prediction and analysis of indoor environmental thermal comfort based on improved BP neural network[J]. Control Engineering of China, 2021. 28(7): 1437-1445 (in Chinese).
[20]
关鹏, 焦玉勇, 段新胜. 基于 RBF 神经网络的土体导热系数非线性预测[J]. 太阳能学报, 2021. 42(3): 171-178.
Guan Peng, Jiao YuYong, Duan Xinsheng. Non-liner prediction of soil thermal conductivity based on RBF neural network[J]. Acta Energiae Solaris Sinica, 2021. 42(3): 171-178 (in Chinese).
[21]
叶佳卓, 杨力, 伍诗雨, 等. 孤岛微电网自适应虚拟阻抗控制策略[J]. 电工电能新技术, 2019. 38(12): 1-9.
Ye Jiazhuo, Yang Li, Wu Shiyu, et al. Adaptive virtual impedance control strategy for island microgrid[J]. Advanced Technology of Electrical Engineering and Energy, 2019. 38(12): 1-9 (in Chinese).
[22]
An improved droop control strategy for parallel inverters in microgrid[C]// 2017 IEEE Conference on Energy Internet and Energy System Integration(EI2), 2017: 1-5.
[23]
Huang Jing, Liu Xiaohua, Li Hongping. Control method of islanded microgrid to improve reactive power sharing and power quality[C]// 2016 China International Conference on Electricity Distribution(CICED). Xi’an, China, 2016: 1-5.
[24]
何瑞. 基于虚拟阻抗的并网变流器并联控制策略的研究[D]. 西安: 西安理工大学, 2019.
He Rui. Research on parallel control strategy of grid-connected converter based on virtual impedance[D]. Xi'an: Xi'an University of Technology, 2019. (in Chinese).
2024年第22卷第6期
PDF下载
414
176
引用本文
BibTeX
文章信息
doi: 10.13234/j.issn.2095-2805.2024.6.139
  • 接收时间:2021-08-04
  • 首发时间:2025-07-19
  • 出版时间:2024-11-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2021-08-04
  • 修回日期:2021-10-27
  • 录用日期:2021-10-31
基金
作者信息
    安徽理工大学 电气与信息工程学院 淮南 232001
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2024.6.139
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏