A Model-Data Hybrid Driven Method for Calculating the Schedulable Potential of EV Clusters

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.