###
DOI:
电力大数据:2018,21(2):-
←前一篇   |   后一篇→
本文二维码信息
配电网中大数据的挖掘应用
张嵩,刘洋,许芳,侯喆瑞
(国网冀北电力有限公司经济技术研究院,国网冀北电力有限公司经济技术研究院,国网冀北电力有限公司经济技术研究院,国网冀北电力有限公司经济技术研究院)
Application of big data mining in power distribution network
Zhang Song,Liu Yang,Xu Fang and Hou Zherui
(state grid jibei electric economic research institute,state grid jibei electric economic research institute,state grid jibei electric economic research institute,state grid jibei electric economic research institute)
摘要
图/表
参考文献
相似文献
本文已被:浏览 748次   下载 1066
投稿时间:2018-02-07    修订日期:2018-02-22
中文摘要: 为了适应日益增长的电力需求,解决配电网点多面广、设备多、管理难度大、配电网信息实时性低等问题,本文系统梳理了国际、国内配电网发展现状,以及数据挖掘与分析处理技术在配电网的应用研究情况,将大数据挖掘应用引入配电网日常管理,利用大数据分析,针对电网运行和设备检测或监测数据、电力企业营销数据、交易电价、售电量、用电客户等方面的数据,结合地域配电网网架结构,对配电网存在的薄弱点,尤其在迎峰度夏和春节保供电等用电高峰期,通过事前提前研判、事中实时指挥、事后深入分析,提前发现未来病态设备,推进配电网设备在线化、透明化、智能化,将配电网由“修得快”向“不停电”转变,提升优质服务水平,并希望能对今后相关研究时间工作提供一定的参考价值。
Abstract:The past decade has seen the burgeoning research in the application of big data mining in power distribution network which covers various fields of power system. According to the characteristic of power industry, data mining can be implemented in the following field, including equipment status control, defect control, outstate state, load sate, voltage quality, three-phase unbalance, distribution line load risk assessment, line loss, grounding analysis, health evaluation of equipment, current status evaluation, risk warning, overload warning, thunder disaster warning and the seasonal characteristics of voltage distribution network to predict the risk of distribution network and seasonal characteristics to predict the risk of mining overload. For us, concerns about how to improve the technical efficiency, economical efficiency, comprehensiveness and systematically development of smart distribution network keep growing. This paper focuses on current research in distribution network and big data mining technology in both international and domestic papers which is instructive for future study.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本: