期刊
CONTROL ENGINEERING PRACTICE
卷 18, 期 5, 页码 532-539出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.conengprac.2010.01.018
关键词
Online tuning; Fuzzy; Reinforcement learning; Supervisory control; Building energy system
This paper proposes a model-free method using reinforcement learning scheme to tune a supervisory controller for a low-energy building system online. The training time and computational demands are reduced by basing the supervisor on sets of fuzzy rules generated by off-line optimisation and by learning the optimal values of only one parameter, which selects the most appropriate set of rules. By carefully choosing the tuning targets, discretizing the state space, parameterizing the fuzzy rule base, using fuzzy trace-back, the proposed method can complete the training process in one season. (C) 2010 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据