大用户多维度可中断特性精细化分析

doi:10.19595/j.cnki.1000-6753.tces.L80290

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (31553 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The study of large-consumers’ interruptible features is the basis to schedule interruptible loads. This paper chose the Ward system clustering method combined with improved fuzzy C-means clustering method (FCM) which takes into consideration the proximity correlation of each sample to deal with the consumers’ daily load data. The number of clusters was optimized by the validity function. Then the twice classification model was proposed to analyze large users’ interruptible characteristics. The refined load data classification was obtained by two-level clustering and the cluster centers were extracted as typical power consumption patterns. By comparing the several typical load curves, the interruptible characteristics of large users were analyzed from four dimensions: interruptible schedule mode, interruptible capacity, interruptible span and interruptible time. Finally, based on the actual historical data, the multi-dimensional interruptible characteristics of a user in the cotton textile printing and dyeing industry were successfully excavated, which verifies the effectiveness of the proposed method and model.

Key words： Improved fuzzy C-means clustering method validity function twice classification multi-dimension interruptible characteristics

Received: 29 June 2018 Published: 05 March 2020

PACS:

TM73

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors

Cite this article:

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.L80290 OR https://dgjsxb.ces-transaction.com/EN/Y2020/V35/Izk1/284