Comparative Evaluation of Machine Learning Models and Input Feature Space for Non-intrusive Load Monitoring

作     者：Attique Ur Rehman Tek Tjing Lie Brice Valles Shafiqur Rahman Tito Attique Ur Rehman;Tek Tjing Lie;Brice Vallès;Shafiqur Rahman Tito

作者机构：Department of Electrical and Electronic EngineeringAuckland University of TechnologyAucklandNew Zealand Brice Valles ConsultingAucklandNew Zealand School of Engineering and TradesManukau Institute of TechnologyAucklandNew Zealand 

出 版 物：《Journal of Modern Power Systems and Clean Energy》 (现代电力系统与清洁能源学报（英文）)

年 卷 期：2021年第9卷第5期

页      面：1161-1171页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 080802[工学-电力系统及其自动化] 0808[工学-电气工程] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Machine learning model load feature non-intrusive load monitoring(NILM) comparative evaluation 

摘      要：Recent advancement in computational capabilities has accelerated the research and development of non-intrusive load ***-intrusive load monitoring(NILM)offers many promising applications in the context of energy efficiency and *** classification is a key component of NILM that relies on different artificial intelligence techniques,e.g.,machine *** study employs different machine learning models for load classification and presents a comprehensive performance evaluation of the employed models along with their comparative ***,this study also analyzes the role of input feature space dimensionality in the context of classification *** the above purposes,an event-based NILM methodology is presented and comprehensive digital simulation studies are carried out on a low sampling real-world electricity load acquired from four different *** on the presented analysis,it is concluded that the presented methodology yields promising results and the employed machine learning models generalize well for the invisible diverse testing *** multi-layer perceptron learning model based on the neural network approach emerges as the most promising ***,it is also noted that it significantly facilitates the classification performance by reducing the input feature space dimensionality.