Day-Ahead Scheduling Strategy for Distribution Networks Considering the Coordination of Flexible Heterogeneous Resources

Addressing the challenges of insufficient exploration and efficient utilization of flexible regulation resources caused by the high penetration of renewable energy sources in the context of the dual-carbon goals, this paper proposes an optimal day-ahead scheduling strategy for distribution networks considering the coordination of flexible heterogeneous resources. Initially, an improved generative adversarial neural network (GAN) approach is employed to generate scenarios for wind and solar power output, characterizing the uncertainty of RES output. With the objectives of minimizing electricity purchases and voltage fluctuations, a multi-scenario, multi-objective optimization model is established and solved using the weighting method. This determines the actions for on-load tap-changing transformers (OLTC) and capacitor banks, as well as the reconfiguration plan for the distribution network. The effectiveness and feasibility of the proposed method are demonstrated through validation using an improved IEEE-33-bus test system.