다중 분류 시스템을 이용한 가전기기 식별 알고리즘
Appliance identification algorithm using multiple classifier system
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Real-time energy monitoring systems is a demand-response system which is reported to be effective in saving energy up to 12%. Real-time energy monitoring system is commonly composed of smart-plugs which sense how much electrical power is consumed and IHD(In-Home Display device) which displays power consumption patterns. Even though the monitoring system is effective, users should themselves match which smart plus is connected to which appliance. In order to make the matching work to be automatic, the monitoring system need to have appliance identification algorithm, and some works have made under the name of NILM(Non-Intrusive Load Monitoring). This paper proposed an algorithm which utilizes multiple classifiers to improve accuracy of appliance identification. The algorithm proposes to understand each classifiers performance, that is, when a classifier make a result how much the result is reliable, and utilize it in choosing the final result among result candidates from many classifiers. By using the proposed algorithm this paper make 4.5% of improved accuracy with respect to using single best classifier, and 2.9% of improved accuracy with respect to other method using multiple classifiers, so called CDM(Commitee Decision Mechanism) method.
Abstract
Real-time energy monitoring systems is a demand-response system which is reported to be effective in saving energy up to 12%. Real-time energy monitoring system is commonly composed of smart-plugs which sense how much electrical power is consumed and IHD(In-Home Display device) which displays power consumption patterns. Even though the monitoring system is effective, users should themselves match which smart plus is connected to which appliance. In order to make the matching work to be automatic, the monitoring system need to have appliance identification algorithm, and some works have made under the name of NILM(Non-Intrusive Load Monitoring). This paper proposed an algorithm which utilizes multiple classifiers to improve accuracy of appliance identification. The algorithm proposes to understand each classifiers performance, that is, when a classifier make a result how much the result is reliable, and utilize it in choosing the final result among result candidates from many classifiers. By using the proposed algorithm this paper make 4.5% of improved accuracy with respect to using single best classifier, and 2.9% of improved accuracy with respect to other method using multiple classifiers, so called CDM(Commitee Decision Mechanism) method.
참고문헌 (12)
- Advanced Metering Initiatives and Residential Feedback Programs: a Meta-Review for Household Electricity-Saving Opportunities, "K. Ehrhardt-Martinez", ACEEE, ~, pp.Report E105 (2010)
- Residential electricity use feedback: A research synthesis and economic framework, "B. Neenan", Electric Power Research Institute, ~ (2009)
- 박성욱, "기기별 전력 모니터링 시스템 개발에 관한 연구", 한국지능시스템학회 논문지, 20(5), pp.638~644 (2010), 한국지능시스템학회
- G. W. Hart, "Nonintrusive appliance load monitoring", Proceedings of IEEE, 80(12), pp.1870~1891 (1992)
- C. Laughman, "Power signature analysis", IEEE Power and Energy Magazine, 1(2), pp.56~63 (2003)
- M. Berges, "Learning systems for electric consumption of buildings", Proceedings of the 2009 ASCE International Workshop on Computing in Civil Engineering (2009)
- S. N. Patel, "At the flick of a switch : Detecting and classifying unique electrical events on the residential power line", Proceedings of 9th International Conference on Ubiquitous Computing, pp.271~288 (2007)
- M. Zeifman, "Nonintrusive appliance load monitoring : Review and outlook", IEEE Transactions on Consumer Electronics, 57(1), pp.76~84 (2011)
- J. Liang, "Load signature study-Part I : Basic concept, structure, and methodology", IEEE Transactions on Power Delivery, 25(2), pp.551~560 (2010)
- J. Liang, "Load signature study-Part II : Disaggregation framework, simulation, and applications", IEEE Transactions on Power Delivery, 25(2), pp.561~569 (2010)
- R. O. Duda, "Pattern Classification, 2nd edition" (2012), WILEY
- A. Zoha, "Non-instrusive load monitoring approaches for disaggregated energy sensing : A survey", Sensors, 12(12), pp.16838~16866 (2012)