Data-Driven Bidding Strategy for DER Aggregator Based on Gated Recurrent Unit–Enhanced Learning Particle Swarm Optimization

Distributed energy resources (DERs) such as wind turbines (WTs), photovoltaics (PVs), storage systems (ESSs), local loads, and demand response (DR) are highly valued for environmental protection. However, their volatility poses several risks to the DER aggregator while formulating a profitable strategy bidding in day-ahead power market. This study proposes data-driven framework confronted with various uncertainties. First, forecasting model involving gated recurrent unit–enhanced learning particle swarm optimization (GRU-ELPSO) improved mutual information (IMI) is employed renewables loads. It critical accurately estimate these components before aids reducing penalty costs of errors. Second, an optimal that based on gap decision theory (IGDT) formulated address market price uncertainty. The assumed be risk-averse (RA) or risk-seeker (RS), corresponding strategies according risk preferences thereof. Then, hourly profile created bid successfully proposed evaluated using illustrative system wherein dataset obtained from PJM results reveal effectiveness handling uncertainty by providing accurate results. In addition, can effectively its preference robustness high profit, suitable profile.