GoogLeResNet3 network for detecting the abnormal electricity consumption behavior of users. (February 2023)

• Record Type: Journal Article
• Authors: Yin, Linfei; Zhong, Qiuyue
• Is Part Of: International journal of electrical power & energy systems. Volume 145(2023)
• Publication Date: 2023-02
• Subjects: GoogLeNet -- ResNet-18 -- User abnormal electricity consumption behavior detection -- Deep learning; Electrical engineering -- Periodicals; Electric power systems -- Periodicals; Électrotechnique -- Périodiques; Réseaux électriques (Énergie) -- Périodiques; Electric power systems; Electrical engineering; Periodicals; 621.3
• DOI: 10.1016/j.ijepes.2022.108733
• Languages: English
• ISSNs: 0142-0615

Abstract

Highlights: Users' abnormal electricity consumption behaviors (AECB) are predicted. Load curve plots abnormal electricity consumption images for AECB prediction. Inception and residual modules are improved for higher prediction accuracy. Deep fully-connected layers combine inception and residual for AECB classification. The proposed network obtains higher prediction accuracy with a short training time. Abstract: With users' increasing knowledge and intellectualization, users' abnormal electricity consumption behaviors (AECB) are becoming more prevalent. Since access to renewable energy sources leads to a volatile and intermittent electricity load, the existing artificial intelligence methods are challenging to detect the AECB of users. To quickly and accurately identify the AECB of a massive number of users, this work proposes the GoogLeResNet3 network module, which contains fully connected layers, the Inception module, and a residual module. The GoogLeResNet3 network is compared with the GoogLeNet module, ResNet-50, ResNet-101, and 11 other neural networks. The results of the comparison experiments indicate that: the GoogLeResNet3 network with the highest accuracy is 335 s quicker than the second-fast network, and the accuracy is 10.57 % higher than the second-best network at least.