Non-intrusive load disaggregation based on composite deep long short-term memory network

作者：

Highlights：

• A composite deep LSTM network is proposed for non-intrusive load disaggregation.

• Repetitive training is avoided in the proposed algorithm.

• Cross-layer connection is introduced to solve vanishing gradient of deep network.

• The proposed algorithm reduces the disaggregation error.

摘要

•A composite deep LSTM network is proposed for non-intrusive load disaggregation.•Repetitive training is avoided in the proposed algorithm.•Cross-layer connection is introduced to solve vanishing gradient of deep network.•The proposed algorithm reduces the disaggregation error.

论文关键词：Non-intrusive load disaggregation,Long short-term memory network,Cross-layer connection,Time series

论文评审过程：Received 3 June 2019, Revised 18 May 2020, Accepted 14 June 2020, Available online 24 June 2020, Version of Record 3 July 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113669