Model free optimization of building cooling water systems with refined action space

作     者：Qiaofeng Xiong Zhengwei Li Wenxia Cai Zhechao Wang Qiaofeng Xiong;Zhengwei Li;Wenxia Cai;Zhechao Wang

作者机构：School of Mechanical Engineering Tongji UniversityShanghaiChina Key Laboratory of Performance Evolution and Control for Engineering Structures of Ministry of EducationTongji UniversityShanghaiChina 

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

年 卷 期：2023年第16卷第4期

页      面：615-627页

核心收录：

学科分类：083305[工学-城乡生态环境与基础设施规划] 08[工学] 081403[工学-市政工程] 0814[工学-土木工程] 0833[工学-城乡规划学] 

主　　题：building cooling water system cooling tower cooling water pump DQN controller convergence speed 

摘      要：Deep Q Network(DQN)is an efficient model-free optimization method,and has the potential to be used in building cooling water ***,due to the high dimension of actions,this method requires a complex neural ***,both the required number of training samples and the length of convergence period are barriers for real ***,penalty function based exploration may lead to unsafe actions,causing the application of this optimization method even more *** solve these problems,an approach to limit the action space within a safe area is proposed in this *** of all,the action space for cooling towers and pumps are separated into two ***,for each type of equipment,the action space is further divided into safe and unsafe *** a result,the convergence speed is significantly *** with the traditional DQN method in a simulation environment validated by real data,the proposed method is able to save the convergence time by 1 episode(one cooling season).The results in this paper suggest that,the proposed DQN method can achieve a much quicker learning speed without any undesired consequences,and therefore is more suitable to be used in projects without pre-learning stage.