Bidding Strategy of Two-Layer Optimization Model for Electricity Market Considering Renewable Energy Based on Deep Reinforcement Learning

Abstract

In the future, the large-scale participation of renewable energy in electricity market bidding is an inevitable trend. In order to describe the Nash equilibrium effect and market power between renewable energy and traditional power generators in the tacit competition in the electricity market, a bidding strategy based on deep reinforcement learning is proposed. The strategy is divided into two layers; the inner layer is the electricity market clearing model, and the outer layer is the deep reinforcement learning optimization algorithm. Taking the equilibrium supply function as the clearing model of the electricity market, considering the green certificate trading mechanism and the carbon emission mechanism, and taking the maximization of social welfare as the objective function, the optimal bidding on the best electricity price is solved. Finally, the calculation examples of the 3-node system and the 30-node system show that compared with other algorithms, more stable convergence results can be obtained, the Nash equilibrium in game theory can be reached, social welfare can be maximized, renewable energy has more market power in the market. The market efficiency evaluation index is introduced to analyze the market efficiency of the two case systems. The final result is one of great significance and value to the reasonable electricity price declaration, the optimization of market resources, and the policy orientation of the electricity market with renewable energy.