ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Multi-layer double deep Q network for active distribution network equivalent modeling with internal identification for EV loads

Zheng, J. H.; Wang, W. H.; Li, Zhigang*; Wu, Q. H.
APPLIED SOFT COMPUTING2023-11DOI: 10.1016/j.asoc.2023.110834
13阅读
引用收藏
分享

摘要

With more and more distributed renewable energy generations and diversified electric vehicle (EV) loads connected to active distribution networks (ADNs), the power interaction between the ADNs and backbone network becomes more complicated. Furthermore, it is difficult to exactly simulate the power flows in the ADN due to large amounts of branches without power measurement units. Consequently, this paper proposes an equivalent modeling for the ADN, consisting of a motor and a synthetic constant impedance (Z), constant current (I), constant power (P) load (ZIP) with an internal identification for EV loads. The equivalent modeling utilizes a multi-layer double deep Q network (MLDDQN) to track the dynamics of the original ADN using few power measurements in the boundary with high precision. In the MLDDQN, the types of the ZIP load and motor are selected from the load pool to obtain the dynamic equivalent modeling of the ADN in the first layer, and the weight of the model is determined to obtain the active power (P) and reactive power (Q) (PQ component) of motor and ZIP load in the second layer through the powerful feature extraction ability of deep learning and the optimization decision-making ability of reinforcement learning. Another layer is adopted to optimize the parameters of the equivalent EV to independently trace the characteristics of the original EV loads. The simulation results show that the proposed MLDDQN improves the sample selection and behavior value function evaluation in deep reinforcement learning through prior experience playback, huber loss function strategy and dueling network. Additionally, the precision and applicability of the equivalent modeling is tested with comparisons with traditional DDQN and DQN.

学科与关键词

关键词
Active distribution networkLoad modelingDynamic equivalenceDeep reinforcement learning
相关
加载中…
  • Hybrid Double Deep Q Network for Active Distribution Network Equivalent Modeling
    Qin, Yingjie; Wang, Wenhao; Zheng, Jiehui*; Li, Zhigang; Wu, Q. H.IEEE/IAS Industrial and Commercial Power System Asia (IEEE I and CPS Asia), Chongqing, PEOPLES R CHINA, 2023-07-07 To 2023-07-09.
  • Intelligent Voltage Control Method in Active Distribution Networks Based on Averaged Weighted Double Deep Q-network Algorithm
    Wang, Yangyang; Mao, Meiqin*; Chang, Liuchen; Hatziargyriou, Nikos D. D.Journal of Modern Power Systems and Clean Energy, 2023, 11(1): 132-143.被引 3
  • MADDPG-Based Active Distribution Network Dynamic Reconfiguration with Renewable Energy
    Jiang, Changxu; Lin, Zheng; Liu, Chenxi; Chen, Feixiong; Shao, Zhenguo*PROTECTION AND CONTROL OF MODERN POWER SYSTEMS, 2024, 9(6): 143-155.
查看全部 →

发表信息

论文状态
公开发表
期刊
APPLIED SOFT COMPUTING
发表日期
2023-11
卷期
第 147 卷
页码
110834
DOI
10.1016/j.asoc.2023.110834
语言
ENGLISH
成果收录
SCIE
资助标注
Natural Science Founda-tion of China [52007066]; Natural Science Foundation of Guangdong Province, China [2021A1515010584]; Young Elite Scientists Sponsorship Program By CSEE [CSEE-YESS-2021014]

作者

  • Z

    Zheng, J. H. (第一作者)

  • W

    Wang, W. H.

查看全部 4 位作者收起作者
  • L

    Li, Zhigang (通讯)

  • W

    Wu, Q. H.

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417