Learning-Based Non-Intrusive Electric Load Monitoring for Smart Energy Management

• DOI: 10.20944/preprints202404.0356.v1
• Publication Date: 2024-04-05T06:00:03Z
• Authors: Nian He; Dengfeng Liu; Zhichen Zhang; Zhiquan Lin; Tiesong Zhao; Yiwen Xu
• Keywords: smart city; Chemical technology; electric load monitoring; smart electric energy management; TP1-1185; load recognition algorithm; 01 natural sciences; computer vision; Article; 0104 chemical sciences

The state-of-the-art smart city has been calling for an economic but efficient energy management over large-scale network, especially the electric power system. It is a critical issue to monitor, analyze and control loads of all users in In this paper, we employ popular computer vision techniques AI design non-intrusive load monitoring method management. First all, utilize both signal transforms (including wavelet transform discrete Fourier transform) Gramian Angular Field (GAF) methods map one-dimensional current signals onto two-dimensional color feature images. Second, propose recognize from images using deep neural network with multi-scale extraction attention mechanism. Third, our as cloud-based, users, thereby saving cost during system control. Experimental results on public private datasets have demonstrated achieves superior performances than its peers, thus supports Internet Things.