Title: Multi-scale residual network for energy disaggregation

Authors: Wan'an Liu; Liguo Weng; Min Xia; Yiqing Xu; Ke Wang; Zhuhan Qiao

Addresses: Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing, 210044, China ' Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing, 210044, China ' Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing, 210044, China ' College of Information Science and Technology, Nanjing Forestry University, Nanjing, 210037, China ' China Electric Power Research Institute, Nanjing, 210003, China ' Department of Mechanical Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, 15213, USA

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.

Keywords: energy disaggregation; deep learning; residual learning; multi-scale convolution; NILM; non-intrusive load monitoring.

DOI: 10.1504/IJSNET.2019.100220

International Journal of Sensor Networks, 2019 Vol.30 No.3, pp.172 - 183

Received: 22 Feb 2019
Accepted: 09 Mar 2019
Published online: 18 Jun 2019 *

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