摘要
We propose DeepOPF-FT as an embedded training approach to design one deep neural network (DNN) for solving multiple AC-OPF problems with flexible topology and line admittances, addressing a critical limitation of learning-based OPF schemes. The idea is to embed the discrete topology representation into the continuous admittance space and train a DNN to learn the mapping from (load, admittance) to the corresponding OPF solution. We then employ the trained DNN to solve AC-OPF problems over any power network with the same bus, generation, and line capacity configurations but different topology and/or line admittances. Simulation results over IEEE 9-/57-bus and a synthetic 2000-bus test cases demonstrate the effectiveness of our design and highlight the training efficiency improvement of DeepOPF-FT over training one DNN for every combination of power network topology and line admittances.
学科与关键词
- DeepOPF-FT: One Deep Neural Network for Multiple AC-OPF Problems with Flexible TopologyZhou, Min*; Chen, Minghua; Low, Steven H.IEEE-Power-and-Energy-Society General Meeting (PESGM), Orlando, FL, 2023-07-16 To 2023-07-20.
- DeepOPF: A Feasibility-Optimized Deep Neural Network Approach for AC Optimal Power Flow ProblemsPan, Xiang; Chen, Minghua*; Zhao, Tianyu; Low, Steven H.IEEE Systems Journal, 2023, 17(1): 673-683.被引 9
- DeepOPF-V: Solving AC-OPF Problems EfficientlyHuang, Wanjun; Pan, Xiang; Chen, Minghua*; Low, Steven H.IEEE Transactions on Power Systems, 2022, 37(1): 800-803.被引 17
