Published October 14, 2022 | public
Journal Article

DeepOPF: A Feasibility-Optimized Deep Neural Network Approach for AC Optimal Power Flow Problems

An error occurred while generating the citation.

Abstract

To cope with increasing uncertainty from renewable generation and flexible load, grid operators need to solve alternative current optimal power flow (AC-OPF) problems more frequently for efficient and reliable operation. In this article, we develop a deep neural network (DNN) approach, called DeepOPF, for solving AC-OPF problems in a fraction of the time used by conventional iterative solvers. A key difficulty for applying machine learning techniques for solving AC-OPF problems lies in ensuring that the obtained solutions respect the equality and inequality physical and operational constraints. Generalized a prediction-and-reconstruction procedure in our previous studies, DeepOPF first trains a DNN model to predict a set of independent operating variables and then directly compute the remaining ones by solving the power flow equations. Such an approach not only preserves the power-flow balance equality constraints but also reduces the number of variables to be predicted by the DNN, cutting down the number of neurons and training data needed. DeepOPF then employs a penalty approach with a zero-order gradient estimation technique in the training process toward guaranteeing the inequality constraints. We also drive a condition for tuning the DNN size according to the desired approximation accuracy, which measures its generalization capability. It provides theoretical justification for using DNN to solve AC-OPF problems. Simulation results for IEEE 30/118/300-bus and a synthetic 2000-bus test cases demonstrate the effectiveness of the penalty approach. They also show that DeepOPF speeds up the computing time by up to two orders of magnitude as compared to a state-of-the-art iterative solver, at the expense of < 0.2% cost difference.

Additional Information

This work was supported in part by the General Research Fund from Research Grants Council, Hong Kong under Grant 11203122, in part by the InnoHK initiative, The Government of the HKSAR, and Laboratory for AI-Powered Financial Technologies, and in part by the NSF through grants ECCS under Grant 1931662, Caltech Resnick, S2I funds, and C3.ai/UC Berkeley. The authors would like to thank T. Cui, W. Huang, Q. Lin, and A. Venzke for the discussions related to this study, and Y. Guo and the National Supercomputer Center in Jinan for providing GPU/CPU computing resources. They also would like to thank the anonymous reviewers for careful reading and the helpful comments.

Additional details

Created:
August 22, 2023
Modified:
October 23, 2023