基于DQN算法的泵站供水系统节能控制优化

TU991; 针对手动调节泵站中水泵运行的转速和启停会造成严重的能量浪费问题,引入基于深度Q网络(deep Q-learning network,DQN)的强化学习算法,通过获取当前泵组运行的状态,自动优化水泵组工作时各个水泵的运行参数,在各个水泵均处于高效区的前提下,提高水泵组的整体效率.对水泵组状态优化问题分别进行了数学描述和马尔可夫决策过程描述.同时定义了水泵组运行时的状态空间、动作空间和即时奖励值,构建DQN网络,并以深圳市M水厂为算例,在由Gym构建的自定义仿真环境中进行验证.相较于人工调控,DQN算法调控降低了 8.84%的损失能耗,一年可节省吨水电耗达 1.27×10-2 kW·...

Full description

Saved in:
Bibliographic Details
Published in净水技术 Vol. 43; no. 4; pp. 60 - 127
Main Authors 陈财会, 张天宇, 黄健康, 金典, 王卓悦, 张小磊
Format Journal Article
LanguageChinese
Published 哈尔滨工业大学<深圳>土木与环境工程学院,深圳 518055 2024
Subjects
DQN algorithm
pumping station water supply
泵站供水
optimal controling
Markov decision process
energy saving and emission reduction
优化调度
DQN算法
马尔可夫决策过程
节能减排
Online AccessGet full text
ISSN1009-0177
DOI10.15890/j.cnki.jsjs.2024.04.008

Cover

Abstract TU991; 针对手动调节泵站中水泵运行的转速和启停会造成严重的能量浪费问题,引入基于深度Q网络(deep Q-learning network,DQN)的强化学习算法,通过获取当前泵组运行的状态,自动优化水泵组工作时各个水泵的运行参数,在各个水泵均处于高效区的前提下,提高水泵组的整体效率.对水泵组状态优化问题分别进行了数学描述和马尔可夫决策过程描述.同时定义了水泵组运行时的状态空间、动作空间和即时奖励值,构建DQN网络,并以深圳市M水厂为算例,在由Gym构建的自定义仿真环境中进行验证.相较于人工调控,DQN算法调控降低了 8.84%的损失能耗,一年可节省吨水电耗达 1.27×10-2 kW·h/t,实现了节能减排,具有良好的经济效能.同时,DQN算法可通过在线学习的方式适应供水环境的变化,具有自主性、实时性、可推广性等优点.
AbstractList TU991; 针对手动调节泵站中水泵运行的转速和启停会造成严重的能量浪费问题,引入基于深度Q网络(deep Q-learning network,DQN)的强化学习算法,通过获取当前泵组运行的状态,自动优化水泵组工作时各个水泵的运行参数,在各个水泵均处于高效区的前提下,提高水泵组的整体效率.对水泵组状态优化问题分别进行了数学描述和马尔可夫决策过程描述.同时定义了水泵组运行时的状态空间、动作空间和即时奖励值,构建DQN网络,并以深圳市M水厂为算例,在由Gym构建的自定义仿真环境中进行验证.相较于人工调控,DQN算法调控降低了 8.84%的损失能耗,一年可节省吨水电耗达 1.27×10-2 kW·h/t,实现了节能减排,具有良好的经济效能.同时,DQN算法可通过在线学习的方式适应供水环境的变化,具有自主性、实时性、可推广性等优点.
Abstract_FL To address the issue of significant energy waste caused by manually adjusting the running speed and start-stop of the pumps in the pump station,the deep Q-learning network(DQN)algorithm was introduced to automatically optimize the operation of each pump during the operation of the pump unit by obtaining the current operating status.Operating parameters,on the premise that each pump was in the high-efficiency area,improved the overall efficiency of the pump unit.The state optimization problem of the pump unit was described mathematically and using the Markov decision process.At the same time,the state,action and reward value of the pump unit were defined,and a DQN network was established.As an example,Shenzhen M WTP was validated verified in a custom simulation environment built by Gym.Compared to manual regulation,DQN algorithm regulation reduced the loss of energy consumption by 8.84%,and could save electricity consumption per tons of water by 1.27×10-2 kW·h/t a year,which contributing to energy saving,emission reduction,and good economic.At the same time,the DQN algorithm,which had the advantages of autonomy,real-time,and generalizability,could adapt to changes in the water supply conditions through online learning.
Author 王卓悦
陈财会
金典
黄健康
张小磊
张天宇
AuthorAffiliation 哈尔滨工业大学<深圳>土木与环境工程学院,深圳 518055
AuthorAffiliation_xml – name: 哈尔滨工业大学<深圳>土木与环境工程学院,深圳 518055
Author_FL CHEN Caihui
JIN Dian
ZHANG Xiaolei
WANG Zhuoyue
HUANG Jiankang
ZHANG Tianyu
Author_FL_xml – sequence: 1
  fullname: CHEN Caihui
– sequence: 2
  fullname: ZHANG Tianyu
– sequence: 3
  fullname: HUANG Jiankang
– sequence: 4
  fullname: JIN Dian
– sequence: 5
  fullname: WANG Zhuoyue
– sequence: 6
  fullname: ZHANG Xiaolei
Author_xml – sequence: 1
  fullname: 陈财会
– sequence: 2
  fullname: 张天宇
– sequence: 3
  fullname: 黄健康
– sequence: 4
  fullname: 金典
– sequence: 5
  fullname: 王卓悦
– sequence: 6
  fullname: 张小磊
BookMark eNrjYmDJy89LZWBQMDTQMzS1sDTQz9JLzsvO1MsqzirWMzIwMtEzACIDCxYGTkMDA0tdA0Nzcw4G3uLiLAMDAyNLS0NzU1NOBrOn83c92dXnEuj3fN30Z5unPp_V8mzz1uerZz7ZN_vZhi3PN-9-vnv-i66mF817n_Utf9qx7cmeGU97pvEwsKYl5hSn8kJpbgZVN9cQZw_d8sS8tMS89Pis_NKiPKBMPMg5INcYmAAdYUysOgAZr1K2
ClassificationCodes TU991
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.15890/j.cnki.jsjs.2024.04.008
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
DocumentTitle_FL Optimization of Energy-Saving Control for Pumping Station Water Supply System Based on DQN Algorithm
EndPage 127
ExternalDocumentID jsjs202404009
GrantInformation_xml – fundername: (深圳市可持续发展科技专项); (哈尔滨工业大学
  funderid: (深圳市可持续发展科技专项); (深圳)课程教学项目)
GroupedDBID -03
2B.
4A8
92I
93N
ALMA_UNASSIGNED_HOLDINGS
CCEZO
CEKLB
GROUPED_DOAJ
PSX
TCJ
ID FETCH-wanfang_journals_jsjs2024040093
ISSN 1009-0177
IngestDate Thu May 29 03:55:33 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords DQN algorithm
pumping station water supply
泵站供水
optimal controling
Markov decision process
energy saving and emission reduction
优化调度
DQN算法
马尔可夫决策过程
节能减排
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-wanfang_journals_jsjs2024040093
ParticipantIDs wanfang_journals_jsjs202404009
PublicationCentury 2000
PublicationDate 2024
PublicationDateYYYYMMDD 2024-01-01
PublicationDate_xml – year: 2024
  text: 2024
PublicationDecade 2020
PublicationTitle 净水技术
PublicationTitle_FL Water Purification Technology
PublicationYear 2024
Publisher 哈尔滨工业大学<深圳>土木与环境工程学院,深圳 518055
Publisher_xml – name: 哈尔滨工业大学<深圳>土木与环境工程学院,深圳 518055
SSID ssj0002991755
ssib036434735
ssib051370136
ssib000269207
ssib018829930
ssib001129148
ssib009282338
Score 4.679865
Snippet TU991; 针对手动调节泵站中水泵运行的转速和启停会造成严重的能量浪费问题,引入基于深度Q网络(deep Q-learning...
SourceID wanfang
SourceType Aggregation Database
StartPage 60
Title 基于DQN算法的泵站供水系统节能控制优化
URI https://d.wanfangdata.com.cn/periodical/jsjs202404009
Volume 43
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07b9RAELaS0NAgECCeUQqmQhf8Wnu33L3bU0QRCSlI6aLYvgOCdEjk0qQECoRQKt4UKSmQEFKAIgF-zT3yM5gZb86OCM_GGs9-np39VvbOrNdrz7sictqEKxKNUArRiAO_21DdWDZkkWVC-lmSlKt8F5OFm_H1ZbE8Nf2stmppo5_N55tHflfyP72KOuxX-kr2H3p2YhQVKGP_4hF7GI9_1cdgBag2GA02pqO0rRuLYFPQFlQKNgETgRKkUVgaO41hjTagFF-IYMNFPpiYighjWDBk30qQeHnIAha1CCwt6JQckBJMwnaaoCRrUEjqUS8rU1pUUdWSsE3WqCboyQJjsIr8QqtYGwJ1eGBbVxBBCu2ToBGiWLBQDapkBZ2nJmPVAWjBF2kwhyDolAoYgoWyPgMSVnOfzHLEHgnyXpU8GtClJmXr6KMklp1LTI1ugU4gajIe2eSqsLXIb2SdTPyWFEhnBJlF6onfNhsJifSqopSQ0lT2S8IQFh5R0VURSL_cotiNPfyeKnB_tXGDU7mHlbsJ49pIU_6FwcUsQbm_wk_DoZDK5_Ew7929M7-2vkYb1Icxb-7ryyoEmCzMJAgh6NGupr1jYZoGojZRUb6bTlRYmzSgiL2eVCvM4qPqqR5gDqdUlaRGGAMf_O-azkUQpbRx4GRmFNEY0wpepuAYcUvwqDnXftEY_uiu113t3arFh0snvRMusZvT5V16ypvavH3aS4bbu4PdLbwrxx9ejnaej988Gu18Hr9_Pfj-dvTx03hnb7y3vf_kwf7Db6Otd8PHXwZfXw2fvjjjQdsuNRcarq4V9zRYXznEXHTWm-nd63XOeXOYcGRFB9ubF1FcZPmq38FgseiEQhWYHeXnvdnf27rwJ8BF7zjJ5bzgJW-mf3-jcxkj5X42yx33A8P2iVc
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8EDQN%E7%AE%97%E6%B3%95%E7%9A%84%E6%B3%B5%E7%AB%99%E4%BE%9B%E6%B0%B4%E7%B3%BB%E7%BB%9F%E8%8A%82%E8%83%BD%E6%8E%A7%E5%88%B6%E4%BC%98%E5%8C%96&rft.jtitle=%E5%87%80%E6%B0%B4%E6%8A%80%E6%9C%AF&rft.au=%E9%99%88%E8%B4%A2%E4%BC%9A&rft.au=%E5%BC%A0%E5%A4%A9%E5%AE%87&rft.au=%E9%BB%84%E5%81%A5%E5%BA%B7&rft.au=%E9%87%91%E5%85%B8&rft.date=2024&rft.pub=%E5%93%88%E5%B0%94%E6%BB%A8%E5%B7%A5%E4%B8%9A%E5%A4%A7%E5%AD%A6%3C%E6%B7%B1%E5%9C%B3%3E%E5%9C%9F%E6%9C%A8%E4%B8%8E%E7%8E%AF%E5%A2%83%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E6%B7%B1%E5%9C%B3+518055&rft.issn=1009-0177&rft.volume=43&rft.issue=4&rft.spage=60&rft.epage=127&rft_id=info:doi/10.15890%2Fj.cnki.jsjs.2024.04.008&rft.externalDocID=jsjs202404009
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fjsjs%2Fjsjs.jpg