Embedded NILM as Home Energy Management System
A Heterogeneous Computing Approach
Keywords:
Cognitive meter, energy management, energy meter, NILM, smart meteringAbstract
This paper presents an embedded NILM engine to enable load disaggregation intelligence and to explore its potential application as an energy management system. In this sense, the power meter is upgraded to a novel category called cognitive power meter. Therefore, this paper discloses a heterogeneous multiprocessing approach to attend NILM prerequisites and increase household interactivity. The NILM is performed attempting microscopic analysis supported by the Conservative Power Theory (CPT) for the feature extraction; K-Nearest Neighbors (KNN) for the appliance classification; and the Power Signature Blob (PSB) for the energy disaggregation. Results show that NILM can be performed onsite, embedded into modern cognitive power meters, and it may support households on providing important information about appliances' usage for energy management systems.