Challenges and opportunities of machine learning control in building operations

作     者：Liang Zhang Zhelun Chen Xiangyu Zhang Amanda Pertzborn Xin Jin Liang Zhang;Zhelun Chen;Xiangyu Zhang;Amanda Pertzborn;Xin Jin

作者机构：The University of Arizona1209 E 2nd StTucsonAZUSA Drexel University3141 Chestnut StPhiladelphiaPAUSA National Renewable Energy Laboratory15013 Denver W PkwyGoldenCOUSA National Institute of Standards and Technology100 Bureau DrGaithersburgMDUSA 

出 版 物：《Building Simulation》 (建筑模拟（英文）)

年 卷 期：2023年第16卷第6期

页      面：831-852页

核心收录：

学科分类：08[工学] 081104[工学-模式识别与智能系统] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the National Renewable Energy Laboratory, operated by Alliance for Sustainable Energy, LLC, for the U.S. Department of Energy (DOE) Funding provided by the U.S. Department of Energy Office of Energy Efficiency and Renewable Energy Building Technologies Office 

主　　题：machine learning building operation control building energy system reinforcement learning 

摘      要：Machine learning control(MLC)is a highly flexible and adaptable method that enables the design,modeling,tuning,and maintenance of building controllers to be more accurate,automated,flexible,and adaptable.The research topic of MLC in building energy systems is developing rapidly,but to our knowledge,no review has been published that specifically and systematically focuses on MLC for building energy systems.This paper provides a systematic review of MLC in building energy systems.We review technical papers in two major categories of applications of machine learning in building control:(1)building system and component modeling for control,and(2)control process learning.We identify MLC topics that have been well-studied and those that need further research in the field of building operation control.We also identify the gaps between the present and future application of MLC and predict future trends and opportunities.