z-logo
Premium
Low‐rate nonintrusive load disaggregation for resident load based on graph signal processing
Author(s) -
Qi Bing,
Liu Liya,
Wu Xin
Publication year - 2018
Publication title -
ieej transactions on electrical and electronic engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.254
H-Index - 30
eISSN - 1931-4981
pISSN - 1931-4973
DOI - 10.1002/tee.22746
Subject(s) - regularization (linguistics) , graph , computer science , simulated annealing , algorithm , minification , mathematical optimization , mathematics , artificial intelligence , theoretical computer science
A graph signal processing (GSP)‐based nonintrusive load monitoring (NILM) algorithm is proposed in this letter to disaggregate the low‐rate power data collected from electricity smart meters. We define load disaggregation as a minimization problem using the total graph variation based on the graph shift matrix as a new regularization term. First we minimize the regularization term to find the smoothest graph signal. Then, based on the smoothest signal, we use the simulated annealing algorithm to minimize the objective function and constraint iteratively. Simulation results using the REDD dataset demonstrate the effectiveness of the proposed algorithm and its superior performance compared with some state‐of‐the‐art low‐rate NILM algorithms. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here