A non-intrusive approach to classify electrical appliances based on higher-order statistics and genetic algorithm: a smart grid perspective
详细信息 查看全文
- 作者：Juan D.S. Guedes juandiegoguedes@yahoo.com.br" class="auth_mail" title="E-mail the corresponding author ; Danton D. Ferreira ; danton@deg.ufla.br" class="auth_mail" title="E-mail the corresponding author ; Bruno H.G. Barbosa brunohb@deg.ufla.br" class="auth_mail" title="E-mail the corresponding author
- 关键词：Electrical appliances ; Higher-order statistics ; Genetic algorithms
- 刊名：Electric Power Systems Research
- 出版年：2016
- 出版时间：November 2016
- 年：2016
- 卷：140
- 期：Complete
- 页码：65-69
- 全文大小：541 K
文摘
- •
A new method for non-invasive classification of electrical appliances was presented.
- •
Higher-order statistics features were extracted to construct compact load signatures.
- •
Fisher's discriminant ratio and genetic algorithms were used for feature selection.
- •
The feature selection led to a considerable dimension reduction, from 2048 to 6.
- •
Overall validation efficiencies over 99.5% were achieved with simple classifiers.