电源学报

基于KKT条件的微网负荷波动抑制双层优化算法

PDF下载

刘进 ¹ , 郝文波 ¹ , 李童 ² , 宋智 ¹ , 张笑宇 ³ , 张纯江中国电源学会高级会员 ³

电源学报 | 新能源系统 2025,23(4): 220-232

收起

电源学报 |新能源系统 2025 , 23 (4) : 220 -232

基于KKT条件的微网负荷波动抑制双层优化算法

全屏

刘进¹, 郝文波¹, 李童², 宋智¹, 张笑宇³, 张纯江中国电源学会高级会员³

作者信息

^1.国网黑龙江省电力有限公司电力科学研究院，哈尔滨　150030

^2.国网黑龙江省电力有限公司，哈尔滨　150090

^3.燕山大学电气工程学院，秦皇岛　066004

通讯作者:

张笑宇（1999—　），男，通信作者，硕士研究生。研究方向：微电网优化控制。E-mail：abrahamz99@163.com。

作者简介:

刘进（1982—　），女，硕士，高级工程师。研究方向：电力系统及其自动化，新能源电网稳定性。E-mail：15515120559@163.com。

郝文波（1976—　），男，博士，正高级工程师。研究方向：电力系统及其自动化。E-mail：176991383@qq.com。

李童（1984—　），男，硕士，高级工程师。研究方向：电能质量控制。E-mail：ljm121618233462319@126.com。

宋智（1995—　），男，硕士，助理工程师。研究方向：电能质量控制和新能源发电技术。E-mail：302623537@qq.com。

张纯江（1961—　），男，中国电源学会高级会员，博士，教授。研究方向：可再生能源分布式发电及控制，储能变流器，微电网功率流控制。E-mail：zhangcj@ysu.edu.cn。

Two-layer Optimization Algorithm for Load Fluctuation Suppression in Microgrid Based on KKT Condition

Jin LIU¹, Wenbo HAO¹, Tong LI², Zhi SONG¹, Xiaoyu ZHANG³, Chunjiang ZHANG Senior Member, CPSS³

Affiliations

^1.Electric Power Research Institute, State Grid Heilongjiang Electric Power Co., Ltd., Harbin 150030, China

^2.State Grid Heilongjiang Electric Power Co., Ltd., Harbin 150090, China

^3.School of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China

出版时间: 2025-07-30 doi: 10.13234/j.issn.2095-2805.2025.4.220

文章导航

摘要

收起

针对微电网中可再生能源发电出力的不确定性及负荷随机波动问题，提出1种基于微网负荷波动抑制策略的双层优化算法。对微网发电设备运行状态和功率分配方式进行建模，上层模型主要考虑微源输出功率约束及微网运行相关约束，以保证各发电设备调度优先级和降低微网运行成本为目标函数；下层模型以最小化微网等效负荷波动为目标函数，同时采用长短期记忆与注意力机制LSTM-Attention（long short-term memory-attention）神经网络的预测值，对微网发电设备输出功率进一步约束。优化模型根据KKT条件将双层模型转换为单层模型进行求解，降低模型的求解难度。设计2种负荷场景，采用双层优化算法分别对2种负荷场景进行仿真计算。仿真结果显示，所提双层优化算法能够动态调整微网各发电设备输出功率，提高可再生能源的消纳比例，并针对不同负荷场景改变微网的运行状态，降低负荷波动对微网运行造成的影响。

关键词

微电网 / 双层优化算法 / 长短期记忆与注意力机制 / KKT条件 / 负荷波动

Abstract

收起

A two-layer optimization algorithm based on a microgrid load fluctuation suppression strategy is proposed, aiming to address the uncertainties in renewable energy generation and random load fluctuations. Through the modeling of operating states of generation devices and power allocation modes, the upper-layer model mainly considers the micro-resource output power constraints and related constraints on microgrid operations, so as to ensure the scheduling priorities of generation devices while reducing the operating cost of microgrid. The lower-layer model minimizes the equivalent load fluctuations in microgrid while using the values predicted by LSTM-Attention neural network to further constrain the output power of generation devices. The two-layer model is transformed into a single-layer model by applying the KKT condition, thus reducing the complexity in solving the model. Two different load scenarios are designed, and the two-layer optimization algorithm is used to perform simulations under the two scenarios, respectively. Simulation results show that the proposed algorithm can dynamically adjust the output power of generation devices and improve the consumption proportion of renewable energy. In addition, it can change the microgrid’s operating state according to different load scenarios and thus mitigate the impact of load fluctuations on microgrid operations.

Key words

Microgrid / two-layer optimization algorithm / LSTM-Attention / KKT condition / load fluctuation

引用本文

刘进, 郝文波, 李童, 宋智, 张笑宇, 张纯江中国电源学会高级会员. 基于KKT条件的微网负荷波动抑制双层优化算法. 电源学报, 2025 , 23 (4) : 220 -232 . DOI: 10.13234/j.issn.2095-2805.2025.4.220

Jin LIU, Wenbo HAO, Tong LI, Zhi SONG, Xiaoyu ZHANG, Chunjiang ZHANG. Two-layer Optimization Algorithm for Load Fluctuation Suppression in Microgrid Based on KKT Condition[J]. Journal of Power Supply, 2025 , 23 (4) : 220 -232 . DOI: 10.13234/j.issn.2095-2805.2025.4.220

基金

收起

国网黑龙江省电力有限公司科技资助项目(522437230003)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

陈冲, 贾利民, 赵天宇, 等. 去碳化导向的轨道交通与新能源融合发展: 形态模式、解决方案和使/赋能技术[J]. 电工技术学报, 2023, 38(12): 3321-3337. Chen Chong, Jia Limin, Zhao Tianyu, et al. Decarbonization-oriented rail transportation and renewable energy integration development: Configurations, solutions, and enabling/empowering technologies[J]. Transactions of China Electrotechnical Society, 2023, 38(12): 3321-3337. (in Chinese)

[2]

杨珺, 侯俊浩, 刘亚威, 等. 分布式协同控制方法及在电力系统中的应用综述[J]. 电工技术学报, 2021, 36(19): 4035-4049. Yang Jun, Hou Junhao, Liu Yawei, et al. Distributed cooperative control method and application in power system[J]. Transaction of China Electrotechnical Society, 2021, 36(19): 4035-4049. (in Chinese)

[3]

Hossain M S, Mahmood H. Short-term photovoltaic power forecasting using an LSTM neural network and synthetic weather forecast[J]. IEEE Access, 2020, 8: 172524-172533.

[4]

Xia Min, Shao Haidong, Ma Xiandong, et al. A stacked GRU-RNN-based approach for predicting renewable energy and electricity load for smart grid operation[J]. IEEE Transactions on Industrial Informatics, 2021, 17(10): 7050-7059.

[5]

Li Jian, Deng Daiyu, Zhao Junbo, et al. A novel hybrid short-term load forecasting method of smart grid using MLR and LSTM neural network[J]. IEEE Transactions on Industrial Informatics, 2021, 17(4): 2443-2452.

[6]

Rotering N, Kellermann J, Moser A. Algorithm for simultaneous medium voltage grid planning and electric vehicle scheduling[J]. IEEE Transactions on Smart Grid, 2021, 12(4): 3305-3313.

[7]

Chen Ziyu, Zhu Jizhong, Dong Hanjiang, et al. Optimal dispatch of WT/PV/ES combined generation system based on cyber-physical-social integration[J]. IEEE Transactions on Smart Grid, 2022, 13(1): 342-354.

[8]

Palma-Behnke R, Benavides C, Lanas F, et al. A microgrid energy management system based on the rolling horizon strategy[J]. IEEE Transactions on Smart Grid, 2013, 4(2): 996-1006.

[9]

Bertsimas D, Litvinov E, Sun X A, et al. Adaptive robust optimization for the security constrained unit commitment problem[J]. IEEE Transactions on Power Systems, 2013, 28(1): 52-63.

[10]

Rezaei N, Ahmadi A, Khazali A H, et al. Energy and frequency hierarchical management system using information gap decision theory for islanded microgrids[J]. IEEE Transactions on Industrial Electronics, 2018, 65(10): 7921-7932.

[11]

张帅涛, 蒋品群, 宋树祥, 等. 基于注意力机制和CNN-LSTM融合模型的锂电池SOC预测[J]. 电源学报, 2024, 22(5): 269-277. Zhang Shuaitao, Jiang Pinqun, Song Shuxiang, et al. SOC prediction for lithium battery based on fusion model of attention mechanism and CNN-LSTM[J]. Journal of Power Supply, 2024, 22(5): 269-277. (in Chinese).

[12]

Yang Tongguang, Li Bin, Xun Qian. LSTM-attention-embedding model-based day-ahead prediction of photovoltaic power output using Bayesian optimization[J]. IEEE Access, 2019, 7: 171471-171484.

[13]

舒征宇, 翟二杰, 李镇翰, 等. 基于Dropout优化算法和LSTM的铅酸蓄电池容量预测[J]. 电源学报, 2023, 21(5): 173-181. Shu Zhengyu, Zhai erjie, Li Zhenhan, et al. Prediction of lead-acid battery capacity based on dropout optimization algorithm and LSTM[J]. Journal of Power Supply, 2023, 21(5): 173-181. (in Chinese)

[14]

陈晨, 王小杨, 梁建盈, 等. 基于新型注意力机制的LSTM光伏发电预测方法[J]. 现代计算机, 2021, 27(11): 28-32, 38. Chen Chen, Wang Xiaoyang, Liang Jianying, et al. LSTM photovoltaic power generation forecasting method based on attention mechanism[J]. Modern Computer, 2021, 27(11): 28-32, 38. (in Chinese)

[15]

马磊, 黄伟, 李克成, 等. 基于Attention-LSTM的光伏超短期功率预测模型[J]. 电测与仪表, 2021, 58(2): 146-152. Ma Lei, Huang Wei, Li Kecheng, et al. Photovoltaic ultra-short-term power prediction model based on Attention-LSTM[J]. Electrical Measurement & Instrumentation, 2021, 58(2): 146-152. (in Chinese)

[16]

张迪, 苗世洪, 赵健, 等. 分布式发电市场化环境下扶贫光伏布点定容双层优化模型研究[J]. 电工技术学报, 2019, 34(10): 1999-2010. Zhang Di, Miao Shihong, Zhao Jian, et al. A Bi-level locating and sizing optimal model for poverty alleviation PVS considering the marketization environment of distributed generation[J]. Transaction of China Electrotechnical Society, 2019, 34(10): 1999-2010. (in Chinese)

2025年第23卷第4期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.13234/j.issn.2095-2805.2025.4.220

接收时间：2023-07-04
首发时间：2026-10-26
出版时间：2025-07-30

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2023-07-04
修回日期：2023-10-23
录用日期：2023-10-27

基金

Technology Project Funding from State Grid Heilongjiang Electric Power Co., Ltd.(522437230003)

国网黑龙江省电力有限公司科技资助项目(522437230003)

作者信息

^1.国网黑龙江省电力有限公司电力科学研究院，哈尔滨　150030

^2.国网黑龙江省电力有限公司，哈尔滨　150090

^3.燕山大学电气工程学院，秦皇岛　066004

通讯作者:

张笑宇（1999—　），男，通信作者，硕士研究生。研究方向：微电网优化控制。E-mail：abrahamz99@163.com。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2025.4.220

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

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

BibTeX
EndNote
RefWorks
TxT