Evaluation of Look-ahead Economic Dispatch Using Reinforcement Learning

TL;DR

This paper presents a comprehensive evaluation framework for reinforcement learning-based look-ahead economic dispatch in power systems, emphasizing scenario generation, performance metrics, and case studies on a modified IEEE 30-bus system.

Contribution

It introduces a novel evaluation approach for RL agents in economic dispatch, including scenario generation, network aggregation, and performance metrics, with practical case studies.

Findings

RL agents adapt quickly to different scenarios

Evaluation metrics effectively assess economic and security performance

Comparison guides better RL strategy design

Abstract

Modern power systems are experiencing a variety of challenges driven by renewable energy, which calls for developing novel dispatch methods such as reinforcement learning (RL). Evaluation of these methods as well as the RL agents are largely under explored. In this paper, we propose an evaluation approach to analyze the performance of RL agents in a look-ahead economic dispatch scheme. This approach is conducted by scanning multiple operational scenarios. In particular, a scenario generation method is developed to generate the network scenarios and demand scenarios for evaluation, and network structures are aggregated according to the change rates of power flow. Then several metrics are defined to evaluate the agents' performance from the perspective of economy and security. In the case study, we use a modified IEEE 30-bus system to illustrate the effectiveness of the proposed evaluation approach, and the simulation results reveal good and rapid adaptation to different scenarios. The comparison between different RL agents is also informative to offer advice for a better design of the learning strategies.