Optimal Economic Gas Turbine Dispatch with Deep Reinforcement Learning

TL;DR

This paper demonstrates how deep reinforcement learning can optimize gas turbine dispatch in modern electricity grids, effectively handling uncertainties and incorporating operational costs for more realistic and economical operation.

Contribution

It introduces a DRL-based approach for gas turbine dispatch that accounts for operational costs and uncertainties, improving upon existing methods.

Findings

DQN achieved the highest rewards among tested algorithms.

PPO was the most sample-efficient algorithm.

The proposed cost model better reflects true operational costs.

Abstract

Dispatching strategies for gas turbines (GTs) are changing in modern electricity grids. A growing incorporation of intermittent renewable energy requires GTs to operate more but shorter cycles and more frequently on partial loads. Deep reinforcement learning (DRL) has recently emerged as a tool that can cope with this development and dispatch GTs economically. The key advantages of DRL are a model-free optimization and the ability to handle uncertainties, such as those introduced by varying loads or renewable energy production. In this study, three popular DRL algorithms are implemented for an economic GT dispatch problem on a case study in Alberta, Canada. We highlight the benefits of DRL by incorporating an existing thermodynamic software provided by Siemens Energy into the environment model and by simulating uncertainty via varying electricity prices, loads, and ambient conditions. Among the tested algorithms and baseline methods, Deep Q-Networks (DQN) obtained the highest rewards while Proximal Policy Optimization (PPO) was the most sample efficient. We further propose and implement a method to assign GT operation and maintenance cost dynamically based on operating hours and cycles. Compared to existing methods, our approach better approximates the true cost of modern GT dispatch and hence leads to more realistic policies.