DeepOPF-V: Solving AC-OPF Problems Efficiently

AC optimal power flow (AC-OPF) problems need to be solved more frequently in the future maintain stable and economic system operation. To tackle this challenge, a deep neural network-based voltage-constrained approach (DeepOPF-V) is proposed solve AC-OPF with high computational efficiency. Its unique design predicts voltages of all buses then uses them reconstruct remaining variables without solving non-linear equations. A fast post-processing process also developed enforce box constraints. The effectiveness DeepOPF-V validated by simulations on IEEE 118/300-bus systems 2000-bus test system. Compared existing studies, achieves decent computation speedup up four orders magnitude comparable performance optimality gap, while preserving feasibility solution.