A data‐driven scheduling approach for integrated electricity‐hydrogen system based on improved DDPG

The involvement of hydrogen energy systems has been recognised as a promising way to mitigate climate problems. As kind efficient multi-energy complementary system, the hydropower-photovoltaic-hydrogen (HPH) system could be an ideal approach combining with installed renewable improve flexibility management and reduce power curtailment. However, intra-day scheduling HPH brings challenges due time-related nonlinear hydropower generation process, complex conversion process uncertain natural resource supply. Faced these challenges, improved deep deterministic policy gradient (DDPG)-based data-driven algorithm is proposed. In contrast prevalent DDPG, two sets actor-critic networks are properly designed based on prior knowledge-based neural for considered search near-optimal policies approximate actor-value functions. addition, customized reward functions proposed consideration interactions among different supplies, which helps convergence speed stability. Finally, case study results demonstrate that model optimal strategy DDPG can guide electricity-hydrogen achieve rapid response more reasonable management.