Improving Domestic NILM Using An Attention-Enabled Seq2Point Learning Approach

Authors:

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.
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: