Constraint-guided Deep Neural Network for solving Optimal Power Flow

Abstract

Due to the nonlinear and non-convex attributes of the optimization problems in power systems such as Optimal Power Flow (OPF), traditional iterative optimization algorithms require significant amount of time to converge for large electric networks. Therefore, power system operators seek other methods such as DC Optimal Power Flow (DC-OPF) to obtain faster results, to obtain the state of the system. However, DC-OPF provides approximated results, neglecting important features of the system such as voltages and reactive power. Fortunately, recent developments in machine learning have led to new approaches for solving such problems faster, more flexible, and more accurate. In this paper, a Deep Neural Network-based Optimal Power Flow (DNN-OPF) algorithm is implemented on small to large case studies to show the accuracy and efficiency of the ML-based algorithms. The paper provides a novel approach to classify the feasible and infeasible AC-OPF problems, and suggests a constraint-guided method, based on normalizing outputs and using particular activation functions to respect the limits of generators. Furthermore, the proposed post-processing approach guarantees the feasibility of the solutions. The suggested method is applied on IEEE24-bus, IEEE 300 bus, and PEGASE 1354 bus systems and the results show significant improvement on accuracy of the results and execution time, comparing to traditional gradient-based methods, such as Newton–Raphson and Gauss–Seidel methods.