Constrained Reinforcement Learning for Safe Heat Pump Control

TL;DR

This paper introduces a new building simulator and a constrained RL algorithm to optimize heat pump control, improving energy efficiency and comfort while ensuring safety constraints are met.

Contribution

The paper presents I4B, a versatile building simulator, and CSAC-LB, a novel constrained RL algorithm, for safe and efficient heat pump control in buildings.

Findings

CSAC-LB outperforms baseline algorithms in data efficiency.

CSAC-LB effectively satisfies safety constraints.

The new simulator I4B supports diverse control scenarios.

Abstract

Constrained Reinforcement Learning (RL) has emerged as a significant research area within RL, where integrating constraints with rewards is crucial for enhancing safety and performance across diverse control tasks. In the context of heating systems in the buildings, optimizing the energy efficiency while maintaining the residents' thermal comfort can be intuitively formulated as a constrained optimization problem. However, to solve it with RL may require large amount of data. Therefore, an accurate and versatile simulator is favored. In this paper, we propose a novel building simulator I4B which provides interfaces for different usages and apply a model-free constrained RL algorithm named constrained Soft Actor-Critic with Linear Smoothed Log Barrier function (CSAC-LB) to the heating optimization problem. Benchmarking against baseline algorithms demonstrates CSAC-LB's efficiency in data exploration, constraint satisfaction and performance.