Combined Peak Reduction and Self-Consumption Using Proximal Policy Optimization

TL;DR

This paper enhances reinforcement learning for residential demand response by integrating domain knowledge into proximal policy optimization, achieving significant cost reductions in peak shaving and self-consumption tasks.

Contribution

It introduces a novel approach combining domain knowledge with PPO and transfer learning to improve data efficiency and performance in demand response applications.

Findings

Cost reduced by 14.51% compared to hysteresis controller

Cost reduced by 6.68% compared to standard PPO

Demonstrates improved data efficiency and effectiveness

Abstract

Residential demand response programs aim to activate demand flexibility at the household level. In recent years, reinforcement learning (RL) has gained significant attention for these type of applications. A major challenge of RL algorithms is data efficiency. New RL algorithms, such as proximal policy optimisation (PPO), have tried to increase data efficiency. Additionally, combining RL with transfer learning has been proposed in an effort to mitigate this challenge. In this work, we further improve upon state-of-the-art transfer learning performance by incorporating demand response domain knowledge into the learning pipeline. We evaluate our approach on a demand response use case where peak shaving and self-consumption is incentivised by means of a capacity tariff. We show our adapted version of PPO, combined with transfer learning, reduces cost by 14.51% compared to a regular hysteresis controller and by 6.68% compared to traditional PPO.