ED-DQN: An event-driven deep reinforcement learning control method for multi-zone residential buildings

Residential Heating, Ventilation, and Air conditioning (HVAC) systems are responsible for a significant amount of energy consumption, but their management is challenging due to the complexities of building thermodynamics and human activities. Reinforcement learning (RL) has been adopted to tackle th...

Full description

Saved in:
Bibliographic Details
Published in:Building and environment Vol. 242; p. 110546
Main Authors: Fu, Qiming, Li, Zhu, Ding, Zhengkai, Chen, Jianping, Luo, Jun, Wang, Yunzhe, Lu, You
Format: Journal Article
Language:English
Published: Elsevier Ltd 15.08.2023
Subjects:
Deep reinforcement learning
Event-driven
HVAC systems
Multi-zone residential buildings
Thermal comfort control
Deep reinforcement learning
Multi-zone residential buildings
HVAC systems
Event-driven
Thermal comfort control
ISSN:0360-1323
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Residential Heating, Ventilation, and Air conditioning (HVAC) systems are responsible for a significant amount of energy consumption, but their management is challenging due to the complexities of building thermodynamics and human activities. Reinforcement learning (RL) has been adopted to tackle this issue, but traditional RL methods require massive training data, long learning periods, and frequent equipment adjustments. To address these issues, we construct a new event-driven Markov decision process (ED-MDP) framework, which enables adjustments of control policies triggered by events, reducing unnecessary operations. Moreover, we propose an event-driven deep Q network (ED-DQN) method, which optimizes the action selection based on the triggered events. In the HVAC control problem, the proposed ED-DQN can effectively capture dynamic non-linear features of thermal comfort, and reduce the equipment damage caused by frequent adjustments. Our experimental results show that compared to three benchmark methods and three RL methods, our ED-DQN achieved state-of-the-art performance in both energy saving and thermal comfort violations. Moreover, our method demonstrates promising performance when applied to new test thermal environments, indicating its robustness and adaptability for optimizing residential HVAC controls. •An event-driven Markov decision processes framework for optimal HVAC control.•Two types of events capture factors impacting performance.•Event-driven Deep Q network improves learning speed and minimizes decisions.•Comprehensive experiments show the superiority of the proposed method.
ISSN:0360-1323
DOI:10.1016/j.buildenv.2023.110546