Transmission Network Expansion Planning Considering Wind Power and Load Uncertainties Based on Multi-Agent DDQN

This paper presents a multi-agent Double Deep Q Network (DDQN) based on deep reinforcement learning for solving the transmission network expansion planning (TNEP) of high-penetration renewable energy source (RES) system considering uncertainty. First, K-means algorithm that enhances extraction quality variable wind and load power uncertain characteristics is proposed. Its clustering objective function considers cumulation change rate operation data. Then, typical scenarios, we build bi-level TNEP model includes comprehensive cost, electrical betweenness, curtailment shedding to evaluate stability economy network. Finally, propose DDQN predicts construction value each line through interaction with model, then optimizes sequence. training mechanism more traceable interpretable than heuristic-based methods. Simultaneously, experience reuse characteristic can be implemented in multi-scenario tasks without repeated training. Simulation results obtained modified IEEE 24-bus New England 39-bus verify effectiveness proposed method.