###

计算机系统应用英文版:2019,28(1):156-162

View/Add Comment 过刊浏览高级检索 HTML

←前一篇 | 后一篇→

码上扫一扫！

下载全文

基于Q-Learning算法的建筑能耗预测

陈建平^1,2,3, 陈其强^1,2,3, 胡文^1,2,3, 陆悠^1,2,3, 吴宏杰^1,2,3, 傅启明^1,2,3

(1.苏州科技大学电子与信息工程学院, 苏州 215009;2.
江苏省建筑智慧节能重点实验室, 苏州 215009;3.
苏州市移动网络技术与应用重点实验室, 苏州 215009)

Prediction of Building Energy Consumption Based on Q-Learning

CHEN Jian-Ping^1,2,3, CHEN Qi-Qiang^1,2,3, HU Wen^1,2,3, LU You^1,2,3, WU Hong-Jie^1,2,3, FU Qi-Ming^1,2,3

(1.College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China;2.
Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China;3.
Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China)

摘要

图/表

参考文献

相似文献

本文已被：浏览 1682次下载 1774次
Received:July 31, 2018 Revised:August 27, 2018

中文摘要: 提出一种基于Q-learning算法的建筑能耗预测方法.通过将建筑能耗预测问题建模为一个标准的马尔科夫决策过程，利用深度置信网对建筑能耗进行状态建模，结合Q-learning算法，实现对建筑能耗的实时预测.通过美国巴尔的摩燃气和电力公司公开的建筑能耗数据进行测试实验，结果表明，基于本文所提出的模型，利用Q-learning算法可以实现对建筑能耗的有效预测，并在此基础上，基于深度置信网的Q-learning算法具有更高的预测精度.此外，实验部分还进一步验证了算法中相关参数对实验性能的影响.

中文关键词: 强化学习建筑能耗预测 Q-learning 深度置信网

Abstract:This study proposed a building energy consumption prediction method based on Q-learning algorithm. By modeling the building energy consumption prediction problem as a standard Markov decision process, combining with the deep belief network to model the state, we use Q-learning algorithm to achieve the real-time prediction of the building energy consumption. Based on the building energy consumption data published by Baltimore Gas and Electric Power Company of the United States, the proposed model were tested and the results show that the Q-learning algorithm can be used to predict the building energy consumption successfully. Moreover, deep belief network can improve the prediction accuracy effectively. In addition, some experimental results further verify the influence of related parameters on experimental performance.

keywords: reinforcement learning building energy consumption prediction Q-learning deep belief network

文章编号： 中图分类号： 文献标志码：

基金项目:国家自然科学基金（61502329，61876121，61772357，61750110519，61672371，61602334，61472267）；江苏省重点研发计划（BE2017663）；江苏省高校自然科学研究项目（18KJB520045）；江苏省建设系统科技指导项目（2017ZD005）

Author Name	Affiliation	E-mail
CHEN Jian-Ping	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China
CHEN Qi-Qiang	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China
HU Wen	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China
LU You	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China
WU Hong-Jie	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China
FU Qi-Ming	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China	fqm_1@126.com

Author Name	Affiliation	E-mail
CHEN Jian-Ping	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China
CHEN Qi-Qiang	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China
HU Wen	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China
LU You	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China
WU Hong-Jie	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China
FU Qi-Ming	College of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, China Jiangsu Key Laboratory of Building Intelligent Energy Saving, Suzhou 215009, China Suzhou Key Laboratory of Mobile Network Technology and Application, Suzhou 215009, China	fqm_1@126.com

引用文本：
陈建平,陈其强,胡文,陆悠,吴宏杰,傅启明.基于Q-Learning算法的建筑能耗预测.计算机系统应用,2019,28(1):156-162
CHEN Jian-Ping,CHEN Qi-Qiang,HU Wen,LU You,WU Hong-Jie,FU Qi-Ming.Prediction of Building Energy Consumption Based on Q-Learning.COMPUTER SYSTEMS APPLICATIONS,2019,28(1):156-162