학술논문
SMELs: A Data-Driven Middleware for Smart Miscellaneous Electrical Load Management in Buildings
Document Type
Conference
Source
2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech) DASC-PICOM-DATACOM-CYBERSCITECH Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech), 2018 IEEE 16th Intl. :159-165 Aug, 2018
Subject
Language
Abstract
Growth in Information and Communication Technology (ICT) has trigged an unprecedented proliferation of appliances a.k.a. Miscellaneous Electrical Loads (MELs) in buildings. Till now, managing MELs energy consumption in an optimum, cost-effective and intelligent manner in buildings remain an open-challenge. This article introduces a new supervised, data-driven middleware towards Smart Miscellaneous Electrical Load management in buildings (SMELs). It can perform automatic extraction, modeling and classification of the semantics of office appliances by analyzing aggregated electrical load signatures from several electrical outlets in the workplace environment. The results of analyzing more than 2,000 electrical load signatures from office workstations present classification performance ranging from 79.4% upto 95.8%. The preliminary findings from the study demonstrate the potential of SMELs as a middleware technology in Internet-of-Things (IoT) enabled smart buildings. The novelty of the proposed approach lies in combining the use of optimum sensors and existing data-driven techniques to extract detailed insights about appliances operation in real buildings.