To comprehensively consider the benefits of both the supply and demand sides in the scheduling process of a microgrid, an island microgrid dual-layer optimal scheduling model considering demand response is established. The upper level optimizes the output of each unit with the goal of maximizing the net revenue of the microgrid. The lower level optimizes the load curve with the goal of maximizing residents' overall comfort. An improved dung beetle optimizer is used to solve the dual-layer optimization model. The population is initialized using a sinusoidal mapping and optimized with quasi-oppositional learning to increase population diversity. During the update phase, the Harris hawks' besiege strategy and adaptive t-distribution perturbation are introduced to enhance the optimization capability and improve the solution quality. The superiority of the improved algorithm is verified by comparing its convergence on test functions with other algorithms. The case study results show that the improved algorithm not only improves the system's economic benefits but also enhances the users' electricity and energy comfort. Comparing the results with those obtained by the original dung beetle optimizer confirms the effectiveness of the im-proved method.

The image acquisition of substations in low light environments can lead to problems such as low visual quality, loss of details, and low contrast, which in turn affect the subsequent detection and monitoring of equipment. A fusion method based on low light image enhancement and nonsubsampling contourlet transform (NSCT) and discrete cosine transform (DCT) technology is proposed in this paper. Firstly, adaptive image adjustment is performed on visible light images based on gamma parameters to enhance visibility. Then NSCT decomposes the image into high and low frequency coefficients. For high-frequency coefficients, edge information extraction based on Sobel operator is used, and for low-frequency coefficients, improved DCT-DFT is used for decomposition and integration. The decomposed amplitude spectrum and the phase spectrum are fused using contrast enhancement weighting and local energy optimization rule based on singular value decomposition (SVD), respectively. Finally, the fused image is obtained by NSCT inverse transformation. Three sets of images of common equipment in substations are used to compare the proposed method with other algorithms. The results show that this proposed method performs better in indicators such as average gradient, information entropy and mutual information.

Against the backdrop of the continuous development of new power system, various regions across the country are actively carrying out new energy storage construction to enhance the regulation capacity of the power system and meet the peak shaving and demand of the power grid. With the characteristics of bidirectional transmission and fast response speed, it is a key issue that should be considered in the site selection stage of energy storage planning, which involves how to effectively improve the security of the power grid and enhance the ability to resist the impact of faults after the new energy storage is access to the power system. A multi-objective decision-making model for energy storage site selection is constructed to address the impact of new energy storage access on the vulnerability of partitioned power grids. Faced with the shortcomings of traditional power grid vulnerability analysis methods, a new vulnerability assessment method based on k-core decomposition is proposed. The system vulnerability indicators under different typical operation scenarios after energy storage access to the power grid are taken as decision-making sub-targets, and the technique for order preference by similarity to an ideal solution (TOPSIS) decision method is used to comprehensively evaluate the optimal solution of energy storage target access point. The rationality and effectiveness of the proposed vulnerability assessment method and the energy storage site selection method are verified through the analysis of the IEEE 39-node system.

In response to the problem of the conventional cooling early warning of wind turbine generator, this paper puts forward the cooling early warning method of wind turbine generator based on multiple linear regression, which makes effective use of the existing new energy centralized control system environment, adopts Pearson coefficient analysis and establishes the early warning framework, and forms the early warning model by multiple linear regression calculation. At the same time, according to different models and different working conditions, different evaluation indexes of generator cooling warning threshold are established, which makes the warning model more flexible and more accurate. The verification results of the example show that this method can correctly achieve the cooling early warning for wind turbine generators.

Aiming at the disadvantages that numerous insulated gate bipolar transistor (IGBT) switching loss are difficult to accurately measure online in the cascaded energy storage application area, switching loss prediction model is established based on the error back propagation neural network. Firstly, dynamic test system of switching loss is built with cascaded H bridge power module, the massive switching loss data is obtained with changing the direct current bus voltage, alternating current and coolant temperature of power module. 3 main factors including collector-emitter voltage, collector current and device junction temperature are taken as the input of IGBT switching loss prediction model. The particle swarm optimization is used to optimize the initial weight and threshold of prediction model, improving prediction accuracy and accelerating the convergence of learning laws. The optimized performance of this model is compared and analyzed with the prediction model that the initial weight and threshold are given randomly. The results show that the prediction accuracy of the model proposed in this paper is higher. The maximum percentage error for 50 sets of random validation data is 3.3%.

A short term electricity price prediction method based on variational mode decomposition and hybrid deep neural network is proposed to address the characteristics of nonlinearity, volatility, and timeliness in electricity price data in the electricity market. Firstly, the original electricity price sequence is decomposed into multiple stationary subsequences using variational mode decomposition (VMD). Secondly, a hybrid deep neural network prediction model is used to predict and superimpose each subsequence separately, obtaining the final electricity price prediction result. This model combines convolutional neural network (CNN) and bidirectional long short term memory (BiLSTM) network to effectively extract spatial and temporal features of the original electricity price data, and combines attention mechanism to effectively distinguish the importance of electricity price data at different times in the original electricity price sequence. Finally, simulation analysis is conducted using actual electricity price data from the PJM electricity market in the United States, and the effectiveness of the proposed method is verified by comparing multiple electricity price prediction models.

A small-signal stability preventive control method based on convolutional neural network (CNN) sensitivity analysis is presented in the paper, to improve the developing speed of small- signal stability preventive control measures. For poor or negative damping low frequency oscillation modes (i.e., the damping ratios are smaller than a threshold), first, an optimization model with small- signal stability constraints is established; second, the sensitivities of the damping ratios with respect to control variables (the active power of adjustable generators) based on CNN model of damping ratio prediction are calculated and then the optimization model is transformed into a quadratic programming model by linearizing small-signal stability constraints through sensitivities; finally, the adjustment amounts of generator active power are obtained. Several iterations are needed to make the damping ratios meet specific requirements. Analysis results of WEPRI 36-node case show that the effective control measures can be obtained by the presented method, which is more precise than that of the support vector machine method. The computing speed of the presented method is faster than that of the traditional eigenvalue analysis method. The ideas presented in this paper can also be applied to transient stability preventive control.

Electric heavy truck charging and swapping stations are developing rapidly, and battery charging strategies have an important impact on station-side operating costs and user battery swapping experience. How to meet the daily battery swapping needs of electric heavy trucks while minimizing station-side operating costs and shortening user battery swapping waiting time is a key research direction. First, a certain electric heavy truck charging and swapping station is taken as the experimental object, and statistical analysis methods are used to obtain user battery swapping needs at different times of the day. Secondly, a charging strategy optimization control model is proposed with the goal of reducing station-side battery charging costs and life loss costs. Combined with battery swapping demand and time-of-use electricity prices, a genetic algorithm is used to solve the charging rate matrix and charging cut-off voltage of the battery charging compartment at different times of the day. Finally, the effectiveness of the model is verified through experimental examples, which also provides reference for its wide application in actual charging and swapping stations.

The article introduces a case of analyzing and processing abnormal ultrasonic signals in the busbar air chamber of a 330kV gas insulated switchgear (GIS). By locating the amplitude and changing the operating status of the equipment, it is determined that the defect comes from the busbar chamber on the main transformer side. By analyzing the scatter plot and phase amplitude plot of the partial discharge ultrasonic signal, it is believed that the discharge of metal foreign objects at the bottom of the gas chamber is the main cause of the abnormal ultrasonic signal. After inspection of the manhole, it is found that there is a silver white metal sharp substance at the measuring point on the bottom of the tank body, which is generated during the production. This GIS busbar air chamber discharge is a typical case of metal tip discharge treatment, providing reference for the treatment of similar abnormal defects in the future.

Modern power systems may experience untypical forced wideband oscillations, and traditional methods are difficult to identify the source of such forced oscillations. This paper proposes a universal identification method for forced oscillation sources based on voltage oscillation ratio (VOR), using wide-frequency measurement data provided by the broadband measurement system. The VOR is the ratio of the oscillation voltage amplitude relative to the steady-state voltage amplitude, which can effectively reflect the physical characteristics that the forced oscillation source has the maximum relative amplitude of oscillation voltage. This method is suitable for identification of low-frequency oscillation and sub/super-synchronous oscillation. This method is applicable in different voltage levels and can reduce the impact of measurement errors of transformers and broadband measurement devices. The effectiveness of this proposed method is verified through simulation cases and on-site cases.