Improving Domestic NILM Using An Attention-Enabled Seq2Point Learning Approach
Authors:
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 434-439
Abstract
The past decade have seen a growth in Internet technology, the overlap of cyberspace and social space provides great convenience for people's life. The in-depth study of non-intrusive load management (NILM) promotes the development of multi-integration and refinement in the future power industry, and makes it possible for customer demand side management. This paper proposes an improved sequence to point load disaggregation algorithm, which combines seq2point learning neural networks with attention mechanism to improve the performance of the algorithm.Keywords
Funding Information
- National Natural Science Foundation of China (41911530242,41975142)
- Royal Society of Edinburgh, UK
- (Natural Science Foundation) of Jiangsu Province (BK20191398,BK20180794)
This publication has 24 references indexed in Scilit:
- Transfer Learning for Non-Intrusive Load MonitoringIEEE Transactions on Smart Grid, 2019
- Dilated residual attention network for load disaggregationNeural Computing and Applications, 2019
- Residential Load Disaggregation Considering State TransitionsIEEE Transactions on Industrial Informatics, 2019
- NILM Techniques for Intelligent Home Energy Management and Ambient Assisted Living: A ReviewEnergies, 2019
- Low-Complexity Non-Intrusive Load Monitoring Using Unsupervised Learning and Generalized Appliance ModelsIEEE Transactions on Consumer Electronics, 2019
- A Cloud-Based On-Line Disaggregation Algorithm for Home Appliance LoadsIEEE Transactions on Smart Grid, 2018
- Review of Smart Meter Data Analytics: Applications, Methodologies, and ChallengesIEEE Transactions on Smart Grid, 2018
- A Hierarchical Hidden Markov Model Framework for Home Appliance ModelingIEEE Transactions on Smart Grid, 2016
- Interactive Energy-Saving Dispatch Considering Generation and Demand Side Uncertainties: A Chinese StudyIEEE Transactions on Smart Grid, 2016
- Neural NILM2015