Data Driven Q-Learning for Commercial HVAC Control

被引:6
|
作者
Faddel, Samy [1 ]
Tian, Guanyu [1 ]
Zhou, Qun [1 ]
Aburub, Haneen [2 ]
机构
[1] Univ Cent Florida, Dept Elect & Comp Engn, Orlando, FL 32816 USA
[2] Florida Int Univ, Dept Elect & Comp Engn, Miami, FL 33199 USA
来源
关键词
HVAC; Demand Response. Comfort level; Data; Reinforcement Learning; REINFORCEMENT; COMFORT;
D O I
10.1109/southeastcon44009.2020.9249737
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Commercial HVAC systems play a key role in the consumption of commercial buildings. Therefore, there is a need for a safe and cost-effective HVAC control algorithm. An algorithm that can learn from the previous experience and reduce the associated energy cost is highly required. In this paper, a data driven-based reinforcement learning for the optimal control of HVAC system of a commercial building is proposed. Random forests technique is utilized to provide a data driven model for the HVAC system. A Q-learning algorithm is used as a type of reinforcement learning to minimize the building energy consumption cost while maintaining the comfort level. The results showed that the proposed algorithm is able to maintain the required building temperature and provide a lower energy cost compared to the base case schedule.
引用
收藏
页数:6
相关论文
共 50 条
  • [31] Double Deep Q-learning Based on Personalized Thermal Comfort Model for HVAC Optimization
    Zhou, Hanchen
    Wang, Di
    Xu, Zhanbo
    Jia, Qing-Shan
    2024 IEEE 20TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING, CASE 2024, 2024, : 3262 - 3267
  • [32] Data-driven model reference control of MIMO vertical tank systems with model-free VRFT and Q-Learning
    Radac, Mircea-Bogdan
    Precup, Radu-Emil
    Roman, Raul-Cristian
    ISA TRANSACTIONS, 2018, 73 : 227 - 238
  • [33] (Data-Driven) Development of dynamic scheduling in semiconductor manufacturing using a Q-learning approach
    Shiue, Yeou-Ren
    Lee, Ken-Chuan
    Su, Chao-Ton
    INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING, 2022, 35 (10-11) : 1188 - 1204
  • [34] Data-Driven Tracking Control for Multi-Agent Systems With Unknown Dynamics via Multithreading Iterative Q-Learning
    Dong, Tao
    Gong, Xiaomei
    Wang, Aijuan
    Li, Huaqing
    Huang, Tingwen
    IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2023, 53 (04): : 2533 - 2542
  • [35] Novel data-driven two-dimensional Q-learning for optimal tracking control of batch process with unknown dynamics
    Wen, Xin
    Shi, Huiyuan
    Su, Chengli
    Jiang, Xueying
    Li, Ping
    Yu, Jingxian
    ISA TRANSACTIONS, 2022, 125 : 10 - 21
  • [36] Real World Deployment of a Data Driven Cloud Based Cooling Solution for HVAC Control in Commercial Buildings
    Vishwanath, Arun
    Hong, Yu-Heng
    Blake, Charles
    E-ENERGY'18: PROCEEDINGS OF THE 9TH ACM INTERNATIONAL CONFERENCE ON FUTURE ENERGY SYSTEMS, 2018, : 417 - 419
  • [37] Data-driven evaluation of HVAC operation and savings in commercial buildings
    Khalilnejad, Arash
    French, Roger H.
    Abramson, Alexis R.
    APPLIED ENERGY, 2020, 278 (278)
  • [38] Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning
    Ohnishi, Shota
    Uchibe, Eiji
    Yamaguchi, Yotaro
    Nakanishi, Kosuke
    Yasui, Yuji
    Ishii, Shin
    FRONTIERS IN NEUROROBOTICS, 2019, 13
  • [39] Q-learning Approach in Ship Safety Inspection Data
    Huang, Tsan-Huang
    Huang, Yu-Chen
    Huang, Chao-Yi
    Fu, Shi-Yi
    BRIDGING THE EAST AND WEST: THEORIES AND PRACTICES OF TRANSPORTATION IN THE ASIA PACIFIC, 2016, : 229 - 235
  • [40] The impact of data distribution on Q-learning with function approximation
    Santos, Pedro P.
    Carvalho, Diogo S.
    Sardinha, Alberto
    Melo, Francisco S.
    MACHINE LEARNING, 2024, 113 (09) : 6141 - 6163