Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Spectogram analysis of active power of appliances and LSTM-based Energy Disaggregation

다수 가전기기 유효전력의 스팩토그램 분석 및 LSTM기반의 전력 분해 알고리즘

  • Received : 2020.12.24
  • Accepted : 2021.02.20
  • Published : 2021.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we propose a deep learning-based NILM technique using actual measured power data for 5 kinds of home appliances and verify its effectiveness. For about 3 weeks, the active power of the central power measuring device and five kinds of home appliances (refrigerator, induction, TV, washing machine, air cleaner) was individually measured. The preprocessing method of the measured data was introduced, and characteristics of each household appliance were analyzed through spectogram analysis. The characteristics of each household appliance are organized into a learning data set. All the power data measured by the central power measuring device and 5 kinds of home appliances were time-series mapping, and training was performed using a LSTM neural network, which is excellent for time series data prediction. An algorithm that can disaggregate five types of energies using only the power data of the main central power measuring device is proposed.

본 연구에서는 가전기기 5종에 대해 실제 측정 전력 데이터를 이용하여 딥러닝 기반의 NILM 기법을 제안하고 그 효용성을 검증 하고자 한다. 약 3주간 중앙 전력 측정 장치 및 5종 가전기기(냉장고, 인덕션, TV, 세탁기, 공기청정기)의 유효전력을 개별 측정하였다. 실측 데이터의 전처리 방법을 소개하고 Spectogram 분석을 통해 가전 기기별 특징을 분석하였다. 가전기기별 특징을 학습 데이터셋으로 구성하였다. 중앙 전력 측정 기기와 가전기기 5종에서 측정된 모든 전력 데이터를 시계열 매핑하여 시계열 데이터 분석에 우수한 RNN 계열의 LSTM 신경망을 이용해 학습을 수행하였다. 메인 중앙 전력 측정 장치의 전력 데이터만으로도 5종 전력 신호를 분해해낼 수 있는 알고리즘을 제안하였다.

Keywords

References

  1. Eurostat. (27 March 2018). Energy Statistics-An Overview. Available online. https://ec.europa.eu
  2. O. Elma & U. S. Selamogullar. (2017). A survey of a residential load profile for demand side management systems. IEEE Internatdional Conference on Smart Energy Grid Engineering (SEGE). DOI : 10.1109/SEGE.2017.8052781
  3. S. Mostafavi & R. W. Cox. (2017). An unsupervised approach in learning load patterns for non-intrusive load monitoring. IEEE 14th International Conference on Networking. Sensing and Control (ICNSC). DOI : 10.1109/icnsc.2017.8000164
  4. L. Perez-Lombard, J. Ortiz & C. Pout. (2008). A review on buildings energy consumption information. Energy and Build. 40(3), 394-398. DOI : 10.1016/j.enbuild.2007.03.007
  5. D. Lee & C-C. Cheng. (2016). Energy savings by energy management systems: A review. Renewable and Sustainable Energy Reviews. 56, 760-777. DOI :10.1016/j.rser.2015.11.067
  6. S. Katipamula & M. Brambley. (2005). Review Article: Methods for Fault Detection, Diagnostics, and Prognostics for Building Systems-A Review, Part II. HVAC&R Reserach. 11(2), 169-187. DOI :10.1080/10789669.2005.10391133
  7. M. Zeifman & K. Roth. (2011). Viterbi algorithm with sparse transitions (VAST) for nonintrusive load monitoring. IEEE Symposium on Computational Intelligence Applications In Smart Grid (CIASG). 1-8. DOI : 10.1109/CIASG.2011.5953328
  8. C. Ogwumike, M. Short & M. Denai. (2015). Near-optimal scheduling of residential smart home appliances using heuristic approach. IEEE International Conference on Industrial Technology (ICIT). 3128-3133. DOI : 10.1109/ICIT.2015.7125560
  9. V. Indragandhi, R. Logesh, V. Subramaniyaswamy, V. Varadarajan, P. Siarry & L. Uden. (2018). Multi-objective optimization and energy management in renewable based AC/DC microgrid. Computers & Electrical Engineering. 70, 179-198. DOI : 10.1016/j.compeleceng.2018.01.023
  10. K. Buchanan, N. Banks, I. Preston & R. Russo, (2016). The British public's perception of the UK smart metering initiative: Threats and opportunities. Energy Policy. 91. 87-97. DOI : 10.1016/j.enpol.2016.01.003
  11. G. C. Koutitas & L. Tassiulas. (2016). Low cost disaggregation of smart meter sensor data. IEEE Sensors. J. 16(6), 1665-1673. DOI : 10.1109/JSEN.2015.2501422
  12. G. W. Hart. (1992). Nonintrusive appliance load monitoring. Proceedings of the IEEE. 80(12), 1870-1891. DOI : 10.1109/5.192069
  13. R. Arghandeh & Y. Zhou. (2018). Big Data Application in Power Systems, Amsterdam : Elsevier Science. DOI : 10.1016/c2016-0-00194-8
  14. D. Egarter, V. P. Bhuvana & W. Elmenreich. (2015). PALDi: Online Load Disaggregation via Particle Filtering. IEEE Transactions on Instrumentation and Measurement. 64(2), 467-477. DOI : 10.1109/tim.2014.2344373
  15. A. Cominola, M. Giuliani, D. Piga, A. Castelletti & A. E. Rizzoli. (2017). A Hybrid Signature-based Iterative Disaggregation algorithm for Non-Intrusive Load Monitoring. Applied Energy 185, 331-344. DOI : 10.1016/j.apenergy.2016.10.040
  16. C. Gisler, A. Ridi, D. Zuerey, O. A. Khaled & J. Hennebert. (2013). Appliance consumption signature database and recognition test protocols. 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA), 336-341. DOI : 10.1109/wosspa.2013.6602387
  17. A. S. Bouhouras, P. A. Gkaidatzis, E. Panagiotou, N. Poulakis & G. C. Christoforidis. A NILM algorithm with enhanced disaggregation scheme under harmonic current vectors. Energy and Buildings, 183(15), 392-407 DOI : 10.1016/j.enbuild.2018.11.013
  18. T. Hassan, F. Javed & N. Arshad. (2014). An empirical investigation of V-I trajectory based load signatures for non-intrusive load monitoring. IEEE Transactions on Smart Grid, 5(2), 870-878. DOI : 10.1109/TSG.2013.2271282
  19. Y. H. Lin & M-S. Tsai. (2015). An advanced home energy management system facilitated by nonintrusive load monitoring with automated multiobjective power scheduling. Transactions on Smart Grid, 6(4), 1839-1851. DOI : 10.1109/TSG.2015.2388492
  20. P. Bilski & W. Winiecki. Generalized algorithm for the non-intrusive identification of electrical appliances in the household. IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), 730-735. DOI : 10.1109/IDAACS.2017.8095186
  21. Y. Kim, S. Kong, R. Ko & S. -K. Joo. (2014). Electrical event identification technique for monitoring home appliance load using load signatures. IEEE International Conference on Consumer Electronics (ICCE), 296-297. DOI : 10.1109/ICCE.2014.6776012
  22. D. Murray, L. Stankovic, V. Stankovic, S. Lulic, S. Sladojevic, (2019). Transferability of neural network approaches for low-rate energy disaggregation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 8330-8334. DOI : 10.1109/ICASSP.2019.8682486
  23. K. S. Barsim & B. Yang. (5 Feb 2018). On the Feasibility of Generic Deep Disaggregation for Single-Load Extraction. New york : Cornell University https://arxiv.org/abs/1802.02139v1
  24. X. Wu, X. Han & K. X. Liang. (2019). Event-based non-intrusive load identification algorithm for residential loads combined with underdetermined decomposition and characteristic filtering. IET Generation, Transmission & Distribution, 13(1), 99-107. DOI : 10.1049/iet-gtd.2018.6125
  25. I. Cavdar & V. Faryad. (2019). New Design of a Supervised Energy Disaggregation Model Based on the Deep Neural Network for a Smart Grid Energies, 12(7), 1217. DOI : 10.3390/en12071217
  26. W. He & Y. Chai. (2016). An empirical study on energy disaggregation via deep learning. Proceedings of the 2016 2nd International Conference on Artificial Intelligence and Industrial Engineering (AIIE 2016). DOI : 10.2991/aiie-16.2016.77
  27. L. Mauch & B. Yang. (2015). A new approach for supervised power disaggregation by using a deep recurrent LSTM network. IEEE Global Conference on Signal and Information Processing (GlobalSIP), 63-67. DOI : 10.1109/GlobalSIP.2015.7418157
  28. F. C. C. Garcia, C. M. C. Creayla & E. Q. B. Macabebe. (2017). Development of an intelligent system for smart home energy disaggregation using stacked denoising autoencoders. Procedia Computer Science, 105, 248-255. DOI : 10.1016/j.procs.2017.01.218
  29. S. J. Cho & T. Y. Yoon. (2016). Seasonal pattern analysis and implications for residential electricity demand. Ulsan : KEEI. https://www.nkis.re.kr:4445/subject_view1.do?otpId=KEEI00047525&otpSeq=0&eoSeq=0