A review disaggregation method in Non-intrusive Appliance Load Monitoring. (December 2016)

• Record Type: Journal Article
• Authors: Esa, Nur Farahin; Abdullah, Md Pauzi; Hassan, Mohammad Yusri
• Is Part Of: Renewable & sustainable energy reviews. Volume 66(2017)
• Page Start: 163
• Page End: 173
• Publication Date: 2016-12
• Subjects: NIALM Non-Intrusive Appliance Load Monitoring -- IALM Intrusive Load Monitoring -- EPU Economic Planning Unit -- MIT Massachusetts Institute of Technology -- FSM Finite State Machines -- US United State -- HMM Hidden Markov Model -- FHMM Factorial Hidden Markov Model -- LCD Liquid-Crystal Display -- PF Power Factor -- HELP Heuristic End-Use Load Profiler -- UEC unit energy consumption -- CU Concordia University -- FFT Fast Fourier Transform -- NN Neural-Network -- CPU Central Processor Unit -- RBF radial basis function -- MLP multilayer perceptron -- SVM support vector machines -- EMI electromagnetic interference -- SMPS switch mode power supplies -- DSP Digital Signal Processing -- RECAP Recognition of electrical Appliances and Profiling in real-time -- ANNOT Automated Electricity Data Annotation Using Wireless Sensor Networks -- ROC Receiver Operating Characteristic; Non-intrusive Appliance Load Monitoring -- Disaggregation method -- Demand side management -- Energy saving; Renewable energy sources -- Periodicals; Power resources -- Periodicals; Énergies renouvelables -- Périodiques; Ressources énergétiques -- Périodiques; 333.794
• DOI: 10.1016/j.rser.2016.07.009
• Languages: English
• ISSNs: 1364-0321

Abstract

Abstract: The development of home energy management have increased due to energy saving. Instead of Intrusive Load Monitoring (IALM) which requires individual sensor for each appliance, Non-Intrusive Appliance Load Monitoring (NIALM) is an advanced low-cost system that requires fewer sensors and disaggregates load data in a different way. NIALM is a study to determine energy consumption of individual appliances measured at a single power source point. This system disaggregates data from a total power load and analyses power consumption of an appliance so that consumer can monitor the total power usage of a building. This paper reviews several feature extractions, state-of-the-art load signatures and disaggregation algorithms used for appliance recognition in NIALM method. Highlights: We present the main outcomes of the Landslide Thematic services of the EU-funded project SAFER. The work deals with landslide inventory mapping and monitoring using radar and optical data. EO satellite data are exploited in different environments and emergency management phases. Example applications in Italy, Austria, Slovakia and Taiwan are shown.