Title: Nonintrusive power load feature recognition based on internet of things technology

Authors: Jing Liu; Di Zhao

Addresses: Department of Information Engineering, Hunan Vocational College of Engineering, Changsha, 410151, China ' School of Information Science and Engineering, Hunan First Normal University, Changsha, 410205, China

Abstract: In order to overcome the problems of low recognition efficiency, low information credibility and low recognition accuracy existing in the existing nonintrusive power load feature recognition methods, a nonintrusive power load feature recognition method based on internet of things technology is proposed. With the support of internet of things technology, the feature parameters of power consumption information are obtained by the Fourier transform method, and the feature parameters are fused according to the correct time sequence to realise the recognition of power consumption equipment. Based on the detection results, a nonintrusive power load feature recognition model is constructed by the C4.5 decision tree algorithm, and the nonintrusive power load feature recognition model is realised by using the nonintrusive power load feature recognition model. The experimental results show that the proposed method has high recognition efficiency, high information reliability and high recognition accuracy.

Keywords: internet of things technology; Fourier transform; parameter feature; C4.5 decision tree algorithm; load feature recognition; feature parameters; nonintrusive power.

DOI: 10.1504/IJAACS.2023.131632

International Journal of Autonomous and Adaptive Communications Systems, 2023 Vol.16 No.3, pp.296 - 312

Received: 21 May 2020
Accepted: 22 Oct 2020
Published online: 21 Jun 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article