Feature Extraction of Non-intrusive Load-Monitoring System Using Genetic Algorithm in Smart Meters
Feature Extraction of Non-intrusive Load-Monitoring System Using Genetic Algorithm in Smart Meters
复制标题
DOI：
10.1109/icebe.2011.48
复制
发表时间：
2011-10
期刊：
影响因子：
--
通讯作者：
Hsueh-Hsien Chang;Po-Ching Chien;Lung-Shu Lin;N. Chen
中科院分区：
文献类型：
--
作者：
Hsueh-Hsien Chang;Po-Ching Chien;Lung-Shu Lin;N. Chen
本文提出了非侵入式负荷监测（NILM）技术，利用人工神经网络（ANN）结合遗传算法（GA）识别负荷需求，提高非侵入式负荷监测结果的识别精度。遗传算法的特征提取方法可以提高载荷识别的效率和多次操作下的计算时间。在比较了人工神经网络的各种训练算法和分类器后，由于各种因素决定了网络是否用于模式识别，反向传播人工神经网络（BP-ANN）分类器被采用在负荷识别过程中。此外，结合电磁暂态程序（EMTP）模拟和现场测量，提取功率特征可以导致准确的负载识别，并且是智能电表的重要功能。
This paper proposes non-intrusive load-monitoring (NILM) techniques using artificial neural networks (ANN) in combination with genetic algorithm (GA) to identify load demands and improve recognition accuracy of non-intrusive load-monitoring results. The feature extraction method of genetic algorithm can improve the efficiency of load identification and computational time under multiple operations. After comparing various training algorithms and classifiers in terms of artificial neural networks due to various factors that determine whether a network is being used for pattern recognition, the back propagation artificial neural network (BP-ANN) classifier is adopted in the load identification process. Additionally, in combination with electromagnetic transients program (EMTP) simulations and measurements on site, extracting the features of power signatures can lead to accurate load identifications and is a significant feature in smart meters.