Energy-efficient control of thermal comfort in multi-zone residential HVAC via reinforcement learning

Energy efficient control of thermal comfort has been already an important part of residential heating, ventilation, and air conditioning (HVAC) systems. However, the optimisation of energy saving control for thermal comfort is not an easy task due to the complex dynamics of HVAC systems, the dynamic...

Full description

Saved in:
Bibliographic Details
Main Authors: Zheng-Kai Ding, Qi-Ming Fu, Jian-Ping Chen, Hong-Jie Wu, You Lu, Fu-Yuan Hu
Format: Article
Language:English
Published: Taylor & Francis Group 2022-12-01
Series:Connection Science
Subjects:
Online Access:http://dx.doi.org/10.1080/09540091.2022.2120598
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850255344833396736
author Zheng-Kai Ding
Qi-Ming Fu
Jian-Ping Chen
Hong-Jie Wu
You Lu
Fu-Yuan Hu
author_facet Zheng-Kai Ding
Qi-Ming Fu
Jian-Ping Chen
Hong-Jie Wu
You Lu
Fu-Yuan Hu
author_sort Zheng-Kai Ding
collection DOAJ
description Energy efficient control of thermal comfort has been already an important part of residential heating, ventilation, and air conditioning (HVAC) systems. However, the optimisation of energy saving control for thermal comfort is not an easy task due to the complex dynamics of HVAC systems, the dynamics of thermal comfort and the trade-off between energy saving and thermal comfort. To solve the above problem, we propose a deep reinforcement learning-based thermal comfort control method in multi-zone residential HVAC. In this paper, firstly we design a SVR-DNN model, consisting of Support Vector Regression and a Deep Neural Network to predict thermal comfort value. Then, we apply Deep Deterministic Policy Gradient (DDPG) based on the output of the SVR-DNN model to achieve an optimal HVAC thermal comfort control strategy. This method can minimise energy consumption while satisfying occupants' thermal comfort. The experimental results show that our method can improve thermal comfort prediction performance by 20.5% compared with DNN; compared with deep Q-network (DQN), energy consumption and thermal comfort violation can be reduced by 3.52% and 64.37% respectively.
format Article
id doaj-art-37ea10ca5cd845f78370d6eb74f69878
institution OA Journals
issn 0954-0091
1360-0494
language English
publishDate 2022-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-37ea10ca5cd845f78370d6eb74f698782025-08-20T01:56:53ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-013412364239410.1080/09540091.2022.21205982120598Energy-efficient control of thermal comfort in multi-zone residential HVAC via reinforcement learningZheng-Kai Ding0Qi-Ming Fu1Jian-Ping Chen2Hong-Jie Wu3You Lu4Fu-Yuan Hu5SuZhou University of Science and TechnologySuZhou University of Science and TechnologySuzhou University of Science and TechnologySuZhou University of Science and TechnologySuZhou University of Science and TechnologySuZhou University of Science and TechnologyEnergy efficient control of thermal comfort has been already an important part of residential heating, ventilation, and air conditioning (HVAC) systems. However, the optimisation of energy saving control for thermal comfort is not an easy task due to the complex dynamics of HVAC systems, the dynamics of thermal comfort and the trade-off between energy saving and thermal comfort. To solve the above problem, we propose a deep reinforcement learning-based thermal comfort control method in multi-zone residential HVAC. In this paper, firstly we design a SVR-DNN model, consisting of Support Vector Regression and a Deep Neural Network to predict thermal comfort value. Then, we apply Deep Deterministic Policy Gradient (DDPG) based on the output of the SVR-DNN model to achieve an optimal HVAC thermal comfort control strategy. This method can minimise energy consumption while satisfying occupants' thermal comfort. The experimental results show that our method can improve thermal comfort prediction performance by 20.5% compared with DNN; compared with deep Q-network (DQN), energy consumption and thermal comfort violation can be reduced by 3.52% and 64.37% respectively.http://dx.doi.org/10.1080/09540091.2022.2120598reinforcement learningdeep reinforcement learningmulti-zone residential hvacenergy consumptionthermal comfort
spellingShingle Zheng-Kai Ding
Qi-Ming Fu
Jian-Ping Chen
Hong-Jie Wu
You Lu
Fu-Yuan Hu
Energy-efficient control of thermal comfort in multi-zone residential HVAC via reinforcement learning
Connection Science
reinforcement learning
deep reinforcement learning
multi-zone residential hvac
energy consumption
thermal comfort
title Energy-efficient control of thermal comfort in multi-zone residential HVAC via reinforcement learning
title_full Energy-efficient control of thermal comfort in multi-zone residential HVAC via reinforcement learning
title_fullStr Energy-efficient control of thermal comfort in multi-zone residential HVAC via reinforcement learning
title_full_unstemmed Energy-efficient control of thermal comfort in multi-zone residential HVAC via reinforcement learning
title_short Energy-efficient control of thermal comfort in multi-zone residential HVAC via reinforcement learning
title_sort energy efficient control of thermal comfort in multi zone residential hvac via reinforcement learning
topic reinforcement learning
deep reinforcement learning
multi-zone residential hvac
energy consumption
thermal comfort
url http://dx.doi.org/10.1080/09540091.2022.2120598
work_keys_str_mv AT zhengkaiding energyefficientcontrolofthermalcomfortinmultizoneresidentialhvacviareinforcementlearning
AT qimingfu energyefficientcontrolofthermalcomfortinmultizoneresidentialhvacviareinforcementlearning
AT jianpingchen energyefficientcontrolofthermalcomfortinmultizoneresidentialhvacviareinforcementlearning
AT hongjiewu energyefficientcontrolofthermalcomfortinmultizoneresidentialhvacviareinforcementlearning
AT youlu energyefficientcontrolofthermalcomfortinmultizoneresidentialhvacviareinforcementlearning
AT fuyuanhu energyefficientcontrolofthermalcomfortinmultizoneresidentialhvacviareinforcementlearning