Deep Reinforcement Learning for Optimal Control of Space Heating

2018/05/10 by Ádám Nagy, Nagy, Adam, Hussain Kazmi +5 · 2 citations
Engineering · #Applications (stat.AP) #Building Energy and Comfort Optimization #Energy Load and Power Forecasting #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (stat.ML) #Radiative Heat Transfer Studies #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1805.03777

openalex publication_date 2018/05/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

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.

Citations

• Playing Atari with Deep Reinforcement Learning

Cited by

• Reinforced model predictive control (RL-MPC) for building energy management
• Integration of Multi-Mode Preference into Home Energy Management System Using Deep Reinforcement Learning

Related

• Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control
• Deep Reinforcement Learning for Heat Pump Control
• Exploring Deep Reinforcement Learning for Holistic Smart Building Control
• Experimental analysis of data-driven control for a building heating\n system
• Towards Optimal District Heating Temperature Control in China with Deep Reinforcement Learning