摘要
负荷聚类不仅能为精细化负荷预测提供高质量数据,还能结合用电规律进行用户行为分析;为应对海量负荷数据挑战,提出一种基于日负荷指标的降维及分布式K-means聚类算法。通过建立日负荷指标,将原始高维负荷数据转化为低维负荷指标;基于负荷指标,利用熵权法改进的分布式K-means算法进行聚类,挖掘出隐藏的典型负荷类型;结合算例,根据得到的典型负荷类型进行用电规律分析,与实际用户类型匹配,实现四类典型用电规律的归纳。
Load clustering can not only provide high-quality data for fine load forecasting,but also help carry out user behavior analysis according to the law of electricity consumption.In order to meet the challenge of processing massive data,a dimension reduction and improved K-means clustering algorithm based on daily load indicators is proposed in this paper.Firstly,the original high-dimensional load data is converted into low-dimensional data by establishing a daily load indicator.Then,the distributed K-means algorithm improved by the entropy weight method is used to cluster the low-dimensional data in order to discover hidden typical load types.Finally,combing with the example,the electricity consumption law is analyzed according to the obtained typical load,and it is matched with the actual user type,and the four typical electricity consumption laws are summarized.
作者
李柏新
雷才嘉
方兵华
黄裕春
贾巍
马乙歌
Li Baixin;Lei Caijia;Fang Binghua;Huang Yuchun;Jia Wei;Ma Yige(Guangzhou Power Supply Bureau,Guangdong Power Grid Co.,Ltd.,Guangzhou 510620,China)
出处
《电测与仪表》
北大核心
2023年第10期104-111,共8页
Electrical Measurement & Instrumentation
基金
国家重点研发计划资助项目(2018YFB1503000)。
关键词
负荷指标
数据降维
分布计算
熵权法
K-MEANS
用电规律
load indicators
data dimension reduction
distributed calculation
entropy weight
K-means
electricity consumption law