Optimal operation of energy storage system in photovoltaic-storage charging station based on intelligent reinforcement learning

Optimizing the energy storage charging and discharging strategy is conducive to improving the economy of the integrated operation of photovoltaic-storage charging. The existing model-driven stochastic optimization methods cannot fully consider the complex operating characteristics of the energy storage system and the uncertainty of photovoltaic power generation and electric vehicle charging load characteristics. Therefore, an optimal operation method for the entire life cycle of the energy storage system of the photovoltaic-storage charging station based on intelligent reinforcement learning is proposed. Firstly, the energy storage operation efficiency model and the capacity attenuation model are finely modeled. Then, the energy storage optimization operation strategy based on reinforcement learning was established with the goal of maximizing the revenue of photovoltaic charging stations, taking into account the uncertainty of electric vehicle charging demand, photovoltaic output, and electricity prices to satisfy the charging requirements and photovoltaic consumption of electric vehicles. A dual delay depth deterministic strategy gradient algorithm is used to solve the problem because of the continuity of decision-making actions for energy storage charging and discharging. The model is trained by the actual historical data, and the energy storage charging and discharging strategy is optimized in real time based on the current period status. Finally, the proposed method and model are tested, and the proposed method is compared with the traditional model-driven method. The results verify the effectiveness of the proposed method and model, and the revenue of optical storage charging stations throughout their energy storage life cycle is improved.