摘要
针对现有配电网运行风险评估存在计算繁杂、误差较大和不确定因考虑不全面等问题,提出了计及配电终端可靠性的配电网运行风险分析方法。首先根据配电终端设备历史运维数据利用数据驱动与机器学习的方法对配电终端可靠性与运行状态进行评估,然后分析配电终端状态对配电网运行风险的影响,基于多目标卷积神经网络评估配电网综合运行风险,并以IEEE33节点配电网验证了所设计方法的有效性。
For the problems of complex calculations,large errors and incomplete consideration of uncertain factors in the existing distribution network operation risk assessment,a distribution network operation risk analysis method in consideration of the reliability of distribution terminals is proposed.Firstly,according to the historical operation and maintenance data of power distribution terminals,the reliability and operation status of power distribution terminals are evaluated by data-driven and machine learning methods,then the influence of the power distribution terminal state on distribution network operation risks is analyzed,the integrated operation risk of distribution network is evaluated based on multi-objective convolution neural network,and the effectiveness of the designed method is verified by IEEE33 node distribution network.
作者
陈洪涛
郭艳春
杨泽栋
CHEN Hongtao;GUO Yanchun;YANG Zedong(Songyuan Power Supply Company,State Grid Jilingsheng Electric Power Suply Company,Songyuan,Jilin Province,138000 China;School of Electrical Engineering,Northeast Electric Power University,Jilin City,Jilin Province,132012 China)
出处
《科技资讯》
2023年第10期38-42,共5页
Science & Technology Information
基金
国网吉林省电力有限公司科技项目“基于电力物联网的配电网运维智能化决策方法和管理系统开发”。
关键词
配电终端
可靠性
配电网运行风险
多目标卷积神经网络
Distribution terminal
Reliability
Distribution network operation risk
Multi-objective convolutional neural network
