基于数据驱动的配用电系统的智慧感知分析研究
Intelligent Perception Analysis of Distribution Systems Based on Data-driven
赵辉程 1王宇之 2曹刚1
作者信息
- 1. 南京苏逸实业有限公司科技信息网络分公司,江苏南京 210008
- 2. 南京华群能源集团有限公司,江苏南京 210019
- 折叠
摘要
为提高低压台区的负荷预测精度,首先根据台区负荷特点基于K-means++对台区负荷进行聚类分析,然后提出一种基于最小冗余最大相关法和长短期记忆网络的负荷预测模型.研究了基于数据挖掘的线变关系辨识和台户关系纠查,实现了配电系统实时拓扑获取.在此基础上提出一种基于分解-协调框架的配电网系统状态感知方法,有效解决了当前配电网难以实现全网可观性的问题.
Abstract
In order to improve the accuracy of load forecasting for low voltage areas,cluster analysis of the station load based on K-Means++is firstly carried out.Then,a load forecasting model based on minimum redundancy maximum rel-evance method and long short-term memory network is proposed.Based on data mining,the identification of feeder trans-former connectivity and the correction of the station and users relationship are further studied,and the real-time topology acquisition of distribution system is realized.Based on the above,a data sensing method of distribution network state based on decomposition-coordination framework is proposed,which effectively solves the problem that the distribution network is difficult to achieve the observability of the whole network.
关键词
智能配电网/负荷预测/线变关系/台户关系/状态估计Key words
intelligent distribution network/load forecasting/feeder transformer connectivity/station and users relation-ship/state estimation引用本文复制引用
出版年
2024
NETL
NSTL
万方数据