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. 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. ••Dual delay deterministic gradient algorithm is proposed for optimization of energy storage.••Uncertain factors are considered for optimization of intelligent reinforcement learning method.••Income of photovoltaic-storage charging station is up to 1759045.80 RMB in cycle of energy storage.Energy storage systemPhotovoltaic-storage charging stationUncertaintyIntelligent reinforcement learningAs a large-scale transportation hub complex, the high-speed railway station can help the development of clean energy and the ability to absorb green electricity. The popularization of electric vehicles (EV) is an important way to achieve carbon neutrality, and it is also a response to the effective solution to global energy problems and environmental crisis,. Using new energy as the main power source for electric vehicle charging stations can achieve “low carbon” in the true sense. Photovoltaic charging stations are new energy charging stations that use photovoltaics to charge electric vehicles. Since photovoltaic output is closely related to weather factors, electric vehicle charging demand is also subject to greater uncertainty. Photovoltaic charging stations are usually equipped with energy storage equipment to realize energy storage and regulation, improve photovoltaic consumption rate, and obtain economic profits through “low storage and high power generation”. There have been some research results in the scheduling strategy of the energy storage system of the photovoltaic charging station. It copes with the uncertainty of electric vehicle charging load by optimizing the active and reactive power of energy storage. The stochastic dynamic programming is used to solve the charging station scheduling problem for electric vehicle charging stations equipped with photovoltaics. The fuel cells and energy storage are aiming at reducing the operating cost of charging stations and thei. The photovoltaic-storage charging station consists of photovoltaic power generation, energy storage and electric vehicle charging piles, and the operation mode of which is shown in Fig. 1. The energy of the system is provided by photovoltaic power generation devices to meet the charging needs of electric vehicles. It stores excess electricity by th.
