Paper Conference

Proceedings of BSO Conference 2018: Fourth Conference of IBPSA-England


Deep Reinforcement Learning for Building Optimization

Adam Nagy, Hussain Kazmi, Cheaib Farah, Johan Driesen

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.
Pages: 96 - 103