Data-Driven Optimal Bidding Strategy in Day-Ahead Electricity Markets Using Deep Reinforcement Learning

With growing renewable integration, optimizing bidding strategies is critical for efficient capacity allocation and generator revenue. However, using real operational data poses significant privacy risks. Thus, this article proposes a novel electricity market bidding strategy optimization framework based on reward learning and enhanced by conditional tabular generative adversarial networks (CTGAN). Initially, a CTGAN is employed to synthesize market data, effectively implementing data augmentation and mitigating privacy leakage risks. Subsequently, a reward learning algorithm grounded in the maximum entropy principle is developed to infer the implicit reward functions. Finally, leveraging the identified reward functions, a deep$Q$-network algorithm generates enhanced bidding strategies. Experimental results indicate that the CTGAN method more accurately replicates real-data distributions than conventional methods. In bidding simulations, the strategy derived from the identified reward function demonstrates enhanced flexibility and strategic behavior compared to predefined reward approaches, ultimately increasing generator profits and improving market efficiency.