Yang, Jiajia, Zhao, Junhua, Wen, Fuhsuan, Dong, Zhaoyang, and Xue, Yusheng (2016) Residential Appliance Identification and Load Modeling Based on Big Data Mining in Smart Grid Environment. Electric Power Construction, 37 (12). pp. 11-23.

PDF (Published Version) - Published Version Restricted to Repository staff only

Abstract

Through big data mining of residential load data, it can not only analyze the electricity consumption behaviour of residents by the identification of electrical load equipment, but also establish the load precise modeling, which can realize targeted demand-side management as well as develop customized electricity retailing strategies. Given this background, based on the dynamic time warping (DTW) time series matching method, this paper proposes a novel appliance identification algorithm for low frequency sampling load data. Firstly, the residential load sequence is segmented into subsequences composed of the single appliance load profile and multi-appliance load profile. Then, according to the time length of subsequences to be identified and measured electrical equipment power consumption data, reference load sequences of all given appliances are generated which have the same length of each query subsequence, including power change from the moment before equipment start to that after equipment shutdown. Finally, the DTW distance is taken as the similarity metric to determine recognition results. For a subsequence composed of multiple appliances, the best matched reference sequence is reduced after each DTW is matched, and then segmentation and DTW matching are carried on until all appliances are extracted. Given the status of all identified appliances, a statistical residential load model is developed. The proposed algorithm is coded in the R programming language and tested through a load dataset containing 500 households profiles. The simulation results show that the proposed algorithm could identify the single appliance load subsuquence at an accuracy above 93%, under the condition that the load data is sampled once every minute; while for the more difficult multi-appliance subsequence identification, the achieved accuracy is around 83%.

Item ID:	82458
Item Type:	Article (Research - C1)
ISSN:	1000-7229
Keywords:	smart grid, data mining, R programming language, dynamic time warping (DTW), appliance identification, load modeling
Date Deposited:	19 Dec 2024 06:43
FoR Codes:	40 ENGINEERING > 4008 Electrical engineering > 400805 Electrical energy transmission, networks and systems @ 100%
SEO Codes:	17 ENERGY > 1703 Energy storage, distribution and supply > 170309 Smart grids @ 100%
Downloads:	Total: 1 Last 12 Months: 1
	More Statistics