Proximal Policy Optimization with Graph Neural Networks for Optimal Power Flow

TL;DR

This paper introduces a novel approach combining Proximal Policy Optimization and Graph Neural Networks to efficiently solve the complex, non-linear AC Optimal Power Flow problem, demonstrating improved generalization and performance on power grid scenarios.

Contribution

It presents a new architecture integrating GNNs with DRL for ACOPF, enabling better generalization to unseen power system configurations.

Findings

Outperforms traditional DCOPF in cost efficiency.

Successfully generalizes to topology changes in power networks.

Demonstrates effectiveness on IEEE 30 bus system.

Abstract

Optimal Power Flow (OPF) is a very traditional research area within the power systems field that seeks for the optimal operation point of electric power plants, and which needs to be solved every few minutes in real-world scenarios. However, due to the nonconvexities that arise in power generation systems, there is not yet a fast, robust solution technique for the full Alternating Current Optimal Power Flow (ACOPF). In the last decades, power grids have evolved into a typical dynamic, non-linear and large-scale control system, known as the power system, so searching for better and faster ACOPF solutions is becoming crucial. Appearance of Graph Neural Networks (GNN) has allowed the natural use of Machine Learning (ML) algorithms on graph data, such as power networks. On the other hand, Deep Reinforcement Learning (DRL) is known for its powerful capability to solve complex decision-making problems. Although solutions that use these two methods separately are beginning to appear in the literature, none has yet combined the advantages of both. We propose a novel architecture based on the Proximal Policy Optimization algorithm with Graph Neural Networks to solve the Optimal Power Flow. The objective is to design an architecture that learns how to solve the optimization problem and that is at the same time able to generalize to unseen scenarios. We compare our solution with the DCOPF in terms of cost after having trained our DRL agent on IEEE 30 bus system and then computing the OPF on that base network with topology changes