DeepOPF: Deep Neural Networks for Optimal Power Flow

We develop a Deep Neural Network (DNN) approach, namely Deep-OPF, for solving optimal power flow (OPF) problems that are critical for daily power system operation. DeepOPF leverages a DNN model to depict the high-dimensional load-to-solution mapping and can directly solve the OPF problem upon given load, excelling in fast computation process and desirable scalability. Simulation results for IEEE test cases show that DeepOPF generates feasible solutions with negligible (<0.2%) optimality loss and accelerates the computation time by up to two orders of magnitude as compared to a state-of-the-art solver.