Research on Integrated Energy System Economic Dispatch Method Based on Proximal Policy Optimization

Abstract

Purposes The economic dispatch of Integrated Energy Systems (IES) is a key research topic of energy technology reform, inherently a complex Mixed-Integer Nonlinear Programming problem. Traditional optimization methods have high computational complexity and struggle to adapt to the source-load uncertainty in IES coupled with renewable energy systems. Utilizing Deep Reinforcement Learning to decompose and accelerate the original problem enhances the efficiency of the IES economic dispatch model. Methods To address these issues, in this paper, an IES optimization dispatch framework based on an improved Proximal Policy Optimization (PPO) algorithm is proposed. The PPO algorithm is used to approximate some variables of the nonlinear constraints in the original model, converting them into linear constraints to speed up the solution. Findings The effectiveness and efficiency of this method over others are validated through case studies, predicting significant computational advantages in large-scale IES optimization problems.

Keywords

• integrated energy system
• economic dispatch
• reinforcement learning
• proximal policy optimization