한국수자원학회논문집 (Journal of Korea Water Resources Association)

  • 제54권10호
  • /
  • Pages.759-768
  • /
  • 2021
  • /
  • 2799-8746(pISSN)
  • /
  • 2799-8754(eISSN)
한국수자원학회 (Korea Water Resources Association)
권호 표지
DOI QR코드

DOI QR Code

스마트미터 데이터 활용 방법에 대한 연구

A study on the practical use of smart meter end-user demand data

  • 박근영 (고려대학교 건축사회환경공학부) ;
  • 정동휘 (고려대학교 건축사회환경공학부) ;
  • 전상훈 (애리조나 주립대학교 토목공학과)
  • Park, Geunyeong (School of Civil, Environmental and Architectural Engineering, Korea University) ;
  • Jung, Donghwi (School of Civil, Environmental and Architectural Engineering, Korea University) ;
  • Jun, Sanghoon (Department of Civil and Architectural Engineering and Mechanics, The University of Arizona)
  • 투고 : 2021.06.30
  • 심사 : 2021.07.23
  • 발행 : 2021.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

이 연구는 스마트 미터 최종 사용자 수요 데이터의 특성을 조사하여 개별 가정용 물 사용량을 분류하는 새로운 접근방식을 도입한다. 여기서는 잘 알려진 비지도 기계학습법 중 하나인 K-means 알고리즘을 적용하여 각 가구별 물 사용 분류를 수행한다. 최종 사용자 수요의 물 사용강도와 지속 시간은 물 수요 패턴이 유사한 가구를 결정하는 주요한 특징으로 사용된다. 그 결과 21가구가 13개의 군집으로 분류되었고 각 군집은 1가구, 2가구, 3가구 또는 5가구로 구성된다. 수집된 데이터 및 최종 사용자의 물 수요 패턴과 관련하여 여러 가구가 동일한 클러스터로 분류되는 이유를 본 논문에서 소개한다.

This work introduces a new approach that classifies individual household water usage by examining the characteristics of smart meter end-user demand data. Here, one of the most well-known unsupervised machine learning, K-means algorithm, is applied to classify water consumptions by each household. The intensity and duration of end-user demands are used as main features to determine the households with similar water consumption pattern. The results showed that 21 households are classified into 13 clusters with each cluster having one, two, three, or five houses. The reasoning why multiple households are classified into the same cluster is described in this paper with respect to the collected data and end-user water consumption behavior.

키워드

과제정보

이 성과는 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No. 2020R1C1C1006481). 가구수요량 스마트 미터 데이터를 흔쾌히 공유해주신 University of Cincinnati의 Steven Buchberger 교수님께도 감사 드립니다.

참고문헌

  1. Buchberger, S.G., and Wells, G.J. (1996). "Intensity, duration and frequency of residential water demands." Journal of Water Resources Planning and Management, ASCE, Vol. 122, No. 1, pp. 11-19. https://doi.org/10.1061/(ASCE)0733-9496(1996)122:1(11)
  2. Buchberger, S.G., Carter, J., Lee, Y., and Schade, T.G. (2003). Random demands, travel times, and water quality in deadends. AWWA Research Foundation, Denver, CO, U.S.
  3. Choi, J., and Kim, J. (2018). "Analysis of water consumption data from smart water meter using machine learning and deep learning algorithms." Journal of the Institute of Electronics and Information Engineers, IEIE, Vol. 55, No. 7, pp. 31-39. https://doi.org/10.5573/ieie.2018.55.7.31
  4. Cominola, A., Nguyen, K., Giuliani, M., Stewart, R.A., Maier, H.R., and Castelletti, A. (2019). "Data mining to uncover heterogeneous water use behaviors from smart meter data." Water Resources Research, Vol. 55, No. 11, pp. 9315-9333. https://doi.org/10.1029/2019wr024897
  5. Gourmelon, N., Bayer, S., Mayle, M., Bach, G., Bebber, C., Munck, C., Sosna, C., and Maier, A. (2021). "Implications of experiment set-ups for residential water end-use classification." Water, Vol. 13, No. 2, 236. https://doi.org/10.3390/w13020236
  6. Joo, J.C., Ahn, H.S., Ahn, C.H., Ko, K.R., and Oh, H.J. (2012a). "Field application of waterworks automatic meter reading and analysis of household water use." Journal of Korean Society of Environmental Engineers, KSSE, Vol. 34, No. 10, pp. 656-663. https://doi.org/10.4491/KSEE.2012.34.10.656
  7. Joo, J.C., Ahn, H.S., Ahn, C.H., Ko, K.R., and Oh, H.J. (2012b). "Recent developments and field application of foreign waterworks automatic meter reading." Journal of Korean Society of Environmental Engineers, KSSE, Vol. 34, No. 12, pp. 863-870. https://doi.org/10.4491/KSEE.2012.34.12.863
  8. Kim, J.B. (2015). "Evolution of water supply system! smart water management for customer - Smart water city pilot project-." Journal of Korean Society of Water and Wastewater, KSWW, Vol. 29, No. 4, pp. 511-517. https://doi.org/10.11001/jksww.2015.29.4.511
  9. Kim, S.H. (2012). "A study on the trend analysis of real-time residential water consumption." Journal of the Korea Academia-Industrial cooperation Society, JKAIS, Vol. 13, No. 8, pp. 3757-3763. https://doi.org/10.5762/KAIS.2012.13.8.3757
  10. Nguyen, K.A., Stewart, R.A., Zhang, H., and Jones, C. (2015). "Intelligent autonomous system for residential water end use classification: Autoflow." Applied Soft Computing, Vol. 31, pp. 118-131. https://doi.org/10.1016/j.asoc.2015.03.007
  11. Pesantez, J.E., Berglund, E.Z., and Kaza, N. (2020). "Smart meters data for modeling and forecasting water demand at the user-level." Environmental Modelling & Software, Vol. 125, 104633. https://doi.org/10.1016/j.envsoft.2020.104633
  12. Wu, L., Peng, Y., Fan, J., Wang, Y., and Huang, G. (2021). "A novel kernel extreme learning machine model coupled with K-means clustering and firefly algorithm for estimating monthly reference evapotranspiration in parallel computation." Agricultural Water Management, 245, 106624. https://doi.org/10.1016/j.agwat.2020.106624
  13. Xenochristou, M., Hutton, C., Hofman, J., and Kapelan, Z. (2021). "Short-term forecasting of household water demand in the UK using an interpretable machine learning approach." Journal of Water Resources Planning and Management, Vol. 147, No. 4, 04021004. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001325