AUTHOR=Liu Yu , Wang Jiarui , Deng Jiewen , Sheng Wenquan , Tan Pengxiang 

TITLE=Non-Intrusive Load Monitoring Based on Unsupervised Optimization Enhanced Neural Network Deep Learning

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2021.718916

DOI=10.3389/fenrg.2021.718916

ISSN=2296-598X

ABSTRACT=Non-intrusive load monitoring has broad application prospects because of its low implementation cost and little interference to users, which has emerged as research hotspot due to the development of learning algorithms. After reviewing the advantages and disadvantages of existing deep learning based disaggregation algorithms, a non-intrusive load disaggregation approach based on enhanced neural network learning algorithm is proposed. The presented appliance monitoring approach establishes the neural network model following the supervised learning at first, and then utilizes the unsupervised learning based optimization to enhance the scalability and adaptation for diverse scenarios, leading to the disaggregation performance improvement. By verifications on the REDD public dataset, the proposed approach is demonstrated to be with good performance in non-intrusive load monitoring. In addition to the high accuracy, the proposed approach is also with good scalability, which is efficient in recognizing the newly added appliance.