Renewable Energy Consumption Strategies for Electric Vehicle Aggregators Based on a Two-Layer Game

Rapid advances in renewable energy technologies offer significant opportunities for the global energy transition and environmental protection. However, due to the fluctuating and intermittent nature of their power generation, which leads to the phenomenon of power abandonment, it has become a key challenge to efficiently consume renewable energy sources and guarantee the reliable operation of the power system. In order to address the above problems, this paper proposes an electric vehicle aggregator (EVA) scheduling strategy based on a two-layer game by constructing a two-layer game model between renewable energy generators (REG) and EVA, where the REG formulates time-sharing tariff strategies in the upper layer to guide the charging and discharging behaviors of electric vehicles, and the EVA respond to the price signals in the lower layer to optimize the large-scale electric vehicle scheduling. For the complexity of large-scale scheduling, this paper introduces the A2C (Advantage Actor-Critic) reinforcement learning algorithm, which combines the value network and the strategy network synergistically to optimize the real-time scheduling process. Based on the case study of wind power, photovoltaic, and wind–solar complementary data in Jilin Province, the results show that the strategy significantly improves the rate of renewable energy consumption (up to 97.88%) and reduces the cost of power purchase by EVA (an average saving of RMB 0.04/kWh), realizing a win–win situation for all parties. The study provides theoretical support for the synergistic optimization of the power system and renewable energy and is of great practical significance for the large-scale application of electric vehicles and new energy consumption.