• HOME
  • About Journal
    • Historical evolution
    • Journal Honors
  • Editorial Board
    • Members of Committee
    • Director of the Committee
    • President and Editor in chief
  • Submission Guide
    • Instructions for Authors
    • Manuscript Processing Flow
    • Model Text
    • Procedures for Submission
  • Academic Influence
  • Open Access
  • Ethics&Policies
    • Publication Ethics Statement
    • Peer Review Process
    • Academic Misconduct Identification and Treatment
    • Advertising and Marketing
    • Correction and Retraction
    • Conflict of Interest
    • Authorship & Copyright
  • Contact Us
  • Chinese
Site search        
文章摘要
深度学习驱动的电网无功-电压优化控制策略模型
Optimal control strategy model of reactive power-voltage in power grid driven by deep learning
Received:July 02, 2020  Revised:July 02, 2020
DOI:10.19753/j.issn1001-1390.2023.11.023
中文关键词: 电力系统  无功优化  深度神经网络  遗传算法  网损
英文关键词: power system, reactive power optimization, deep neural network, genetic algorithm, network loss
基金项目:国家自然科学基金项目(51977133)
Author NameAffiliationE-mail
LI Yanjun School of Electrical Engineering, Sichuan University 837289390@qq.com 
LIU Youbo* School of Electrical Engineering, Sichuan University liuyoubo@scu.edu.cn 
RAN Jinzhou School of Electrical Engineering, Sichuan University 9702006@qq.com 
LIU Junyong School of Electrical Engineering, Sichuan University liujy@scu.edu.cn 
Hits: 1301
Download times: 341
中文摘要:
      文章在应用深度神经网络的基础之上,提出一种可对电网网络损耗进行有效评估与优化的方法。该方法通过神经网络寻求电网中无功补偿设备、变压器运行状态与系统网络中网络损耗的内在联系,结合改进遗传算法对无功补偿设备、变压器变比进行优化求解实现快速调节控制。该方法解决了电网使用传统最优潮流计算求解非线性混合变量规划时存在的收敛性问题,文中放弃了使用潮流分布数据进行训练而是采用节点电压数据替代,实现降维的同时保证了电力系统全局响应信息;通过佳点集抽样样本优化神经网络训练的效果,并改进传统遗传算法提升搜索的全局性或收敛的速度;文中以IEEE 30节点系统对本套方案进行仿真验证,证明了改进方法的有效性。
英文摘要:
      On the basis of applying deep neural network, this paper proposes a methodology to estimate and optimize the network losses for a designated power grid. This method seeks the internal relationship between the operation state of the reactive power compensation equipments and transformers and the network losses in the system network, with the deep neural network, combining with the improved genetic algorithm, the reactive power compensation equipments and transformer ratio are optimized and solved to realize rapid regulation and control. The method solves the convergence problem when the traditional power flow calculation is used to solving the nonlinear mixed variable programming. In this paper, instead of using power flow distribution data for training, the node voltages data is used to achieve dimension reduction while ensuring global response information in power system. The training effect of deep neural network is optimized with good point set samples, and the traditional genetic algorithms is improved to enhance the global and convergence speed of search. Finally, the proposed scheme is tested on the IEEE30-node system and the effectiveness of the methodology is proved to be effective.
View Full Text   View/Add Comment  Download reader
Close
  • Home
  • About Journal
    • Historical evolution
    • Journal Honors
  • Editorial Board
    • Members of Committee
    • Director of the Committee
    • President and Editor in chief
  • Submission Guide
    • Instructions for Authors
    • Manuscript Processing Flow
    • Model Text
    • Procedures for Submission
  • Academic Influence
  • Open Access
  • Ethics&Policies
    • Publication Ethics Statement
    • Peer Review Process
    • Academic Misconduct Identification and Treatment
    • Advertising and Marketing
    • Correction and Retraction
    • Conflict of Interest
    • Authorship & Copyright
  • Contact Us
  • 中文页面
Address: No.2000, Chuangxin Road, Songbei District, Harbin, China    Zip code: 150028
E-mail: dcyb@vip.163.com    Telephone: 0451-86611021
© 2012 Electrical Measurement & Instrumentation
黑ICP备11006624号-1
Support:Beijing Qinyun Technology Development Co., Ltd