Towards self-learning control of HVAC systems with the consideration of dynamic occupancy patterns: Application of model-free deep reinforcement learning

占用率 暖通空调 强化学习 计算机科学 钢筋 控制(管理) 工程类 人工智能 控制工程 建筑工程 空调 结构工程 机械工程
作者
Mohammad Esrafilian-Najafabadi,Fariborz Haghighat
出处
期刊:Building and Environment [Elsevier BV]
卷期号:226: 109747-109747 被引量:1
标识
DOI:10.1016/j.buildenv.2022.109747
摘要

This study proposes a self-learning control system that aims to learn occupancy profiles, building energy consumption patterns, and lag-time of the heating, ventilation, and air-conditioning (HVAC) systems. The control system learns by interacting with the environment with no need to develop building models and occupancy prediction models. The controller is developed based on a double deep Q-networks (DDQN) algorithm, as a model-free reinforcement learning method. The system's performance is evaluated and compared with that of a model predictive control (MPC) system under two scenarios of perfect and actual occupancy predictions based on occupancy data collected from 20 residential units. The MPC is assisted by a genetic algorithm and supervised learning models for predicting future occupancy patterns, indoor operative temperature, and building energy consumption. The results show that in the case of using perfect occupancy prediction, the self-learning controller operates almost as well as the MPC while not requiring any models. When occupancy prediction uncertainty is added to the problem, the proposed method outperforms the MPC in terms of thermal comfort by increasing the average temperature deviation and deviation period by 0.24 °C and 7.87%, respectively. However, the DDQN agent causes significant thermal comfort violations during the initial training period. The system causes up to a 2.8% longer deviation period and a 0.32 °C higher average temperature deviation, compared with the performance of the fully-trained system. • A self-learning occupancy-based predictive control system is developed. • Double deep Q-network is utilized as a model-free reinforcement learning technique. • The performance is compared with that of a model predictive control. • Thermal comfort is improved by 7.87% with no need for occupancy and building models. • Trial-and-error-based learning process causes almost 2.8% thermal discomfort.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
骨科AAA发布了新的文献求助10
刚刚
MYC007完成签到 ,获得积分10
刚刚
1秒前
xiaofeiyan发布了新的文献求助10
3秒前
兴奋雁蓉发布了新的文献求助10
4秒前
星辰大海应助太叔明辉采纳,获得10
6秒前
深情安青应助baibai采纳,获得10
6秒前
共享精神应助zxx采纳,获得10
7秒前
cgsatm完成签到,获得积分20
8秒前
追三发布了新的文献求助20
9秒前
bin完成签到,获得积分10
10秒前
10秒前
孤独的狼完成签到,获得积分10
11秒前
玉米烤肠完成签到 ,获得积分10
11秒前
13秒前
14秒前
量子星尘发布了新的文献求助10
15秒前
15秒前
Mason发布了新的文献求助10
16秒前
dreamy4869发布了新的文献求助10
17秒前
复杂焦完成签到 ,获得积分10
18秒前
18秒前
20秒前
WangXiaoze发布了新的文献求助10
21秒前
www应助害羞映容采纳,获得10
21秒前
21秒前
加速度完成签到,获得积分10
23秒前
23秒前
啥呀啥呀完成签到,获得积分10
23秒前
Coral.发布了新的文献求助10
23秒前
风里有声音完成签到 ,获得积分10
24秒前
25秒前
26秒前
LZY发布了新的文献求助10
26秒前
NexusExplorer应助完美蚂蚁采纳,获得10
27秒前
隐形曼青应助hyr采纳,获得10
30秒前
炼丹发布了新的文献求助10
30秒前
31秒前
小透明发布了新的文献求助10
31秒前
adong完成签到,获得积分10
32秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3976253
求助须知:如何正确求助?哪些是违规求助? 3520405
关于积分的说明 11203301
捐赠科研通 3257028
什么是DOI,文献DOI怎么找? 1798589
邀请新用户注册赠送积分活动 877755
科研通“疑难数据库(出版商)”最低求助积分说明 806521