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

页码：291 / 310

页数：20

共 50 条

[21] Energy management based on multi-agent deep reinforcement learning for a multi-energy industrial park
Zhu, Dafeng
Yang, Bo
Liu, Yuxiang
Wang, Zhaojian
Ma, Kai
Guan, Xinping
[J]. APPLIED ENERGY, 2022, 311
[22] Multi-Agent Reinforcement Learning
Stankovic, Milos
[J]. 2016 13TH SYMPOSIUM ON NEURAL NETWORKS AND APPLICATIONS (NEUREL), 2016, : 43 - 43
[23] Intelligent Energy Management in Smart and Sustainable Buildings with Multi-agent Control System
Smitha, S. D.
Chacko, Fossy Mary
[J]. 2013 IEEE INTERNATIONAL MULTI CONFERENCE ON AUTOMATION, COMPUTING, COMMUNICATION, CONTROL AND COMPRESSED SENSING (IMAC4S), 2013, : 190 - 195
[24] A multi-agent based energy management solution for integrated buildings and microgrid system
Anvari-Moghaddam, Amjad
Rahimi-Kian, Ashkan
Mirian, Maryam S.
Guerrero, Josep M.
[J]. APPLIED ENERGY, 2017, 203 : 41 - 56
[25] Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings
Yu, Liang
Sun, Yi
Xu, Zhanbo
Shen, Chao
Yue, Dong
Jiang, Tao
Guan, Xiaohong
[J]. IEEE TRANSACTIONS ON SMART GRID, 2021, 12 (01) : 407 - 419
[26] MAPS: Multi-agent Reinforcement Learning-based Portfolio Management System
Lee, Jinho
Kim, Raehyun
Yi, Seok-Won
Kang, Jaewoo
[J]. PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 4520 - 4526
[27] Quantum Finance and Fuzzy Reinforcement Learning-Based Multi-agent Trading System
Cheng, Chi
Chen, Bingshen
Xiao, Ziting
Lee, Raymond S. T.
[J]. INTERNATIONAL JOURNAL OF FUZZY SYSTEMS, 2024, 26 (07) : 2224 - 2245
[28] Adaptive multi-agent reinforcement learning for flexible resource management in a virtual power plant with dynamic participating multi-energy buildings
Wu, Haochi
Qiu, Dawei
Zhang, Liyu
Sun, Mingyang
[J]. APPLIED ENERGY, 2024, 374
[29] Reinforcement learning for energy conservation and comfort in buildings
Dalamagkidis, K.
Kolokotsa, D.
Kalaitzakis, K.
Stavrakakis, G. S.
[J]. BUILDING AND ENVIRONMENT, 2007, 42 (07) : 2686 - 2698
[30] Cooperative Multi-Agent Reinforcement Learning in Express System
Li, Yexin
Zheng, Yu
Yang, Qiang
[J]. CIKM '20: PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, 2020, : 805 - 814

← 1 2 3 4 5 →