Virtual Power Plant (VPP) technology enhances the accommodation potential of distributed energy resources and addresses blind spots in grid dispatch. To enable VPPs to guide large-scale integrated electric vehicle (EV) in orderly participation in distribution network optimization dispatch, this paper first establishes a control framework for VPPs in grid dispatch. Next, priority ranking indices for EV are selected, and the comprehensive weights of these indices are determined. Building on this, an improved TOPSIS model based on the Tanimoto coefficient is innovatively proposed to prioritize EV participation in dispatch. Finally, with the objective of maximizing VPP revenue, an optimized VPP dispatch strategy considering EV priority ranking is presented. Case study results demonstrate that the proposed strategy increases VPP profitability while effectively guiding EV in orderly participation in distribution network optimization dispatch.

As a flexible load, electric vehicles (EVs) play an important role in achieving load peak shaving and valley filling. However, current methods for calculating the schedulable potential of EVs are difficult to balance practicality and accuracy. Therefore, A model-data hybrid driven method for calculating the schedulable potential of EV clusters is proposed. Firstly, refined modeling of the boundary of a single EV. Aggregating EVs into a generalized energy storage (GES) model based on Minkowski summation theory. Then, the parameters of the GES model were accurately predicted based on Particle Swarm Optimization Long Short-Term Memory (PSO-LSTM) Network. Finally, the three-way Decisions (T-WD) model was established according to the user intentions to participate in different charging behaviors. The self-scheduling model of EVs was established considering the user intentions to quantify the schedulable potential of EVs. The example analysis results show that the proposed method can quantify the schedulable potential of EV clusters on the basis of accurately predicting the parameters of EVs and judging the intentions of users.

The increasing integration of distributed generation (DG) into the distribution network has led to greater complexity in power flow distribution and transient current characteristics during single-phase grounding faults. As a result, traditional fault location methods are no longer sufficient. Adapting existing fault location methods to accommodate changing permeability has become an urgent issue. In response, a fault location method utilizing a convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) network is proposed. The CNN is used to extract detailed longitudinal features from fault zero sequence current data at a specific time, compressing the data length to reduce subsequent network training parameters. Additionally, a cascade network with BiLSTM as its core is constructed to capture historical horizontal features of fault data during the fault evolution process. An Attention mechanism is integrated to ensure that the model focuses on changes in fault time and location data, thereby enhancing fault location accuracy. The simulation results demonstrate that the proposed method is capable of accurately identifying single-phase grounding faults, offering high precision and robustness in positioning, and exhibiting strong adaptability across various permeability fault scenarios.