As an effective way to promote the usage of electric vehicles (EVs) and facilitate the consumption of distributed energy, the optimal energy dispatch of photovoltaic (PV) and battery energy storage systems (BESS) integrated fast charging stations with vehicle‐to‐grid is of considerable value to the efficient use of renewable energy. Based on an examination of the electrical structure and operation modes of PV and BESS integrated fast charging stations, considering the randomness of EVs’ arrival and departure, a rolling optimization strategy is adopted. Combining the energy architecture characteristics of the charging stations, the economic dispatch model is established by scheduling the orderly charging and discharging of EVs and the BESS to minimize the expense of daily operations. In view of the shortcomings of the first‐stage economic dispatch, two further optimization strategies are proposed to level out the power fluctuation of the grid connection point (POC) of the charging station, and the effect of the two‐stage optimization model and the multi‐objective optimization model are studied in comparison. Finally, an intraday real‐time optimization algorithm is designed, and the similarities and differences of the economic index and power fluctuation index are comprehensively analysed by using an actual charging station as a case study.
15 December 2022 in International Transactions on Electrical Energy Systems
Maximizing the return on electric vehicle charging station (EVCS) operation helps to expand the EVCS, thus expanding the EV (electric vehicle) stock and better addressing climate change. However, in the face of dynamic regulation scenarios with large data, multiple variables, and low time scales, the existing regulation strategies aiming at maximizing EVCS returns many times fail to meet the demand. To handle increasingly complex regulation scenarios, a deep reinforcement learning algorithm (DRL) based on the improved twin delayed deep deterministic policy gradient (TD3) is used to construct basic energy management strategies in this paper. To enable the strategy to be more suitable for the goal of real-time energy regulation strategy, we used Thompson sampling strategy to improve TD3s exploration noise sampling strategy, which greatly accelerated the initial convergence of TD3 during training. Also, we use marginalised importance sampling to calculate the Q-return function for TD3, which ensures that the constructed strategies are more likely to learn high-value experiences while having higher robustness. It is shown in numerical experiments that the charging station management strategy (CSMS) based on the modified TD3 obtains the fastest convergence speed and the highest robustness and achieves the largest operational returns compared to the CSMS constructed using deep deterministic policy gradient (DDPG), actor-critic using Kronecker-factored trust region (ACKTR), trust region policy optimization (TRPO), proximal policy optimization (PPO), soft actor-critic (SAC), and the original TD3.