Fuzzy Reinforcement Learning Multi-agent System for Comfort and Energy Management in Buildings

被引：0
|
作者：
Kofinas, Panagiotis [1 ]
Dounis, Anastasios [1 ]
Korkidis, Panagiotis [1 ]
机构：
[1] Univ West Attica, Dept Biomed Engn, Athens, Greece
来源：
PROCEEDINGS OF SIXTH INTERNATIONAL CONGRESS ON INFORMATION AND COMMUNICATION TECHNOLOGY (ICICT 2021), VOL 2 | 2022年 / 236卷
关键词：
Multi-agent system; Building; Fuzzy reinforcement learning; Q-learning; Energy management; Comfort management; EFFICIENT BUILDINGS; NONLINEAR CONTROL; LOAD; CONTROLLER;
D O I：
10.1007/978-981-16-2380-6_26
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper, a Multi-agent System (MAS) is proposed to maintain the comfort of a building in high levels and simultaneously reduce the overall energy consumption. The multi-agent system consists of three independent agents each one dedicated to one comfort factor. These factors are the thermal comfort, the visual comfort and the air quality. Fuzzy Q-learning algorithm is utilised in all the agents in order to deal with the continuous state-action space. Simulation results highlight the superiority of the system compared to a simple on-off algorithm, as a reduction of 3% is observed and the comfort index remains high throughout the entire simulation.
引用
收藏
页码：291 / 310
页数：20
相关论文
共 50 条
  • [1] Multi-agent hierarchical reinforcement learning for energy management
    Jendoubi, Imen
    Bouffard, Francois
    [J]. APPLIED ENERGY, 2023, 332
  • [2] Energy management based on safe multi-agent reinforcement learning for smart buildings in distribution networks
    Sun, Yiyun
    Zhang, Senlin
    Liu, Meiqin
    Zheng, Ronghao
    Dong, Shanling
    [J]. ENERGY AND BUILDINGS, 2024, 318
  • [3] Energy-efficient personalized thermal comfort control in office buildings based on multi-agent deep reinforcement learning
    Yu, Liang
    Xu, Zhanbo
    Zhang, Tengfei
    Guan, Xiaohong
    Yue, Dong
    [J]. BUILDING AND ENVIRONMENT, 2022, 223
  • [4] A coordination model using fuzzy reinforcement learning for multi-agent system
    Peng, Jun
    Liu, Miao
    Liu, Jianfeng
    Lin, Kuo-Chi
    Wu, Min
    [J]. CTS 2007: PROCEEDINGS OF THE 2007 INTERNATIONAL SYMPOSIUM ON COLLABORATIVE TECHNOLOGIES AND SYSTEMS, 2007, : 129 - +
  • [5] Multi-agent Reinforcement Learning in Network Management
    Bagnasco, Ricardo
    Serrat, Joan
    [J]. SCALABILITY OF NETWORKS AND SERVICES, PROCEEDINGS, 2009, 5637 : 199 - 202
  • [6] An Information Fusion Based Multi-Agent Control System for Indoor Energy and Comfort Management in Smart and Green Buildings
    Wang, Zhu
    Dounis, Anastasios I.
    Wang, Lingfeng
    Yang, Rui
    [J]. 2011 IEEE POWER AND ENERGY SOCIETY GENERAL MEETING, 2011,
  • [7] Distributed energy management of multi-area integrated energy system based on multi-agent deep reinforcement learning
    Ding, Lifu
    Cui, Youkai
    Yan, Gangfeng
    Huang, Yaojia
    Fan, Zhen
    [J]. INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2024, 157
  • [8] Deep clustering of cooperative multi-agent reinforcement learning to optimize multi chiller HVAC systems for smart buildings energy management
    Homod, Raad Z.
    Yaseen, Zaher Mundher
    Hussein, Ahmed Kadhim
    Almusaed, Amjad
    Alawi, Omer A.
    Falah, Mayadah W.
    Abdelrazek, Ali H.
    Ahmed, Waqar
    Eltaweel, Mahmoud
    [J]. JOURNAL OF BUILDING ENGINEERING, 2023, 65
  • [9] Scalable energy management approach of residential hybrid energy system using multi-agent deep reinforcement learning
    Wang, Zixuan
    Xiao, Fu
    Ran, Yi
    Li, Yanxue
    Xu, Yang
    [J]. APPLIED ENERGY, 2024, 367
  • [10] Multi-energy Management of Interconnected Multi-microgrid System Using Multi-agent Deep Reinforcement Learning
    Li, Sichen
    Cao, Di
    Hu, Weihao
    Huang, Qi
    Chen, Zhe
    Blaabjerg, Frede
    [J]. JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY, 2023, 11 (05) : 1606 - 1617
12345