Multi-scale residual network for energy disaggregation. (15th June 2019)

• Record Type: Journal Article
• Authors: Liu, Wan'an; Weng, Liguo; Xia, Min; Xu, Yiqing; Wang, Ke; Qiao, Zhuhan
• Is Part Of: International journal of sensor networks. Volume 30:Number 3(2019)
• Page Start: 172
• Page End: 183
• Publication Date: 2019-06-15
• Subjects: energy disaggregation -- deep learning -- residual learning -- multi-scale convolution -- NILM -- non-intrusive load monitoring; Sensor networks -- Periodicals; 681.2
• Languages: English
• ISSNs: 1748-1279

Abstract

Energy disaggregation technology is a key technology to realise real-time non-intrusive load monitoring (NILM). Current energy disaggregation methods use the same scale to extract features from the sequence, which makes part of the local features lost, resulting in low recognition accuracy of electrical appliances. Aiming at the low accuracy of non-intrusive energy disaggregation with low-frequency sampling, a sequential multi-scale residual network is proposed. Multi-scale residual network extracts multi-scale feature information through multi-scale convolution, and uses residual learning to deepen the network structure to further improve the performance of the algorithm. Different scales features are captured by multi-scale convolution to improve the recognition accuracy of electrical appliances with low using frequency. Sequence-to-sequence energy disaggregation mechanism can improve the disaggregation efficiency of the algorithm. The experimental comparison results show that the model can get better disaggregation effect, and can effectively identify the start-stop state of electrical appliances.