微型电脑应用2025，Vol.41Issue(2)：269-272,4.
基于深度学习的供电决策图谱构建方法
A Method of Constructing Power Supply Decision Map Based on Deep Learning
杨玉强 1向新宇 2倪夏冰2
作者信息
- 1. 国网浙江省电力有限公司,浙江,杭州 310000
- 2. 国网浙江省电力有限公司杭州供电公司,浙江,杭州 310000
- 折叠
摘要
Abstract
In order to solve the problem of long time consuming and low accuracy of power supply decision in distribution net-works with distributed energy,a method of constructing power supply decision map based on deep learning is proposed.Through the application of the integration of operation,distribution and dispatching topology data can be of the power grid ac-quired in real time,as well as archive data and measurement data.The power grid knowledge is learned and extracted through convolutional nevral network(CNN),and the power supply decision method is established using knowledge map technology.On this basis,power supply decision suggestions are provided for power grid failures.Experiment is conducted in a power sup-ply company.The average decision running time is 3.2 s,and the accuracy of power supply decision is 98.5％.The experiment results show that the proposed method can reduce the time consumption of power supply decision and improve the accuracy of power supply decision judgment.关键词
深度学习/卷积网络/知识图谱/供电决策/故障告警Key words
deep learning/convolutional network/knowledge map/power supply decision/fault alarm分类
信息技术与安全科学引用本文复制引用
杨玉强,向新宇,倪夏冰..基于深度学习的供电决策图谱构建方法[J].微型电脑应用,2025,41(2):269-272,4.
