Deep Reinforcement Learning for Optimal Control of Space Heating

TL;DR

This paper introduces a deep reinforcement learning algorithm for space heating control that outperforms traditional rule-based methods in simulations, offering faster computation and greater robustness.

Contribution

The paper presents a novel deep reinforcement learning approach for building heating control that is computationally efficient and benchmarks it against existing techniques.

Findings

Outperforms rule-based control by 5-10% in simulations

Offers faster computation times

Provides increased robustness to non-stationarities

Abstract

Classical methods to control heating systems are often marred by suboptimal performance, inability to adapt to dynamic conditions and unreasonable assumptions e.g. existence of building models. This paper presents a novel deep reinforcement learning algorithm which can control space heating in buildings in a computationally efficient manner, and benchmarks it against other known techniques. The proposed algorithm outperforms rule based control by between 5-10% in a simulation environment for a number of price signals. We conclude that, while not optimal, the proposed algorithm offers additional practical advantages such as faster computation times and increased robustness to non-stationarities in building dynamics.