DOI QR코드

DOI QR Code

물 사용량 예측을 위한 선형 모형과 딥러닝 알고리즘의 비교 분석

Comparative analysis of linear model and deep learning algorithm for water usage prediction

  • 김종성 (인하대학교 수자원시스템 연구소) ;
  • 김동현 (인하대학교 사회인프라공학과) ;
  • 왕원준 (인하대학교 사회인프라공학과) ;
  • 이하늘 (인하대학교 사회인프라공학과) ;
  • 이명진 (인하대학교 수자원시스템 연구소) ;
  • 김형수 (인하대학교 사회인프라공학과)
  • Kim, Jongsung (Institute of Water Resources System, Inha University) ;
  • Kim, DongHyun (Department of Civil Engineering, Inha University) ;
  • Wang, Wonjoon (Department of Civil Engineering, Inha University) ;
  • Lee, Haneul (Department of Civil Engineering, Inha University) ;
  • Lee, Myungjin (Institute of Water Resources System, Inha University) ;
  • Kim, Hung Soo (Department of Civil Engineering, Inha University)
  • 투고 : 2021.09.27
  • 심사 : 2021.10.29
  • 발행 : 2021.12.31

초록

물 사용량 예측은 최적의 용수 공급 운영 방안을 수립하고 전력 소비량 절감을 위하여 꼭 필요한 과정이라고 할 수 있다. 그러나 수용가 단위의 물 사용량은 용도, 사용자의 패턴, 날씨 등의 다양한 요인으로 인해 변화하는 비선형적 특성을 지니고 있다. 따라서 본 연구에서는 비선형적인 수용가 단위의 물 사용량을 예측하기 위하여 다양한 기법들을 연계한 KWD 프레임워크를 제안하고자 하였다. 즉, 먼저 개별 수용가 마다 용도에 따른 유사한 패턴을 파악하기 위해 K-means (K) 군집분석을 수행하였고, 잡음성분을 제거함으로써 핵심적인 주기패턴을 파악하기 위해 Wavelet (W) 방법을 적용하였다. 또한 비선형적 특성을 학습시키기 위해 Deep learning (D) 알고리즘을 적용하였다. 그리고 기존의 선형 시계열 모형인 ARMA 모형과 비교하여 KWD 프레임워크의 성능을 분석하였다. 그 결과 제안된 모형의 상관성은 92%, ARMA 모형은 약 39%로 KWD 프레임워크가 2배 이상의 성능을 가지는 것으로 분석되었다. 따라서 본 연구에서 제안한 방법을 활용할 경우 정확한 물 사용량 예측이 가능해질 것이며, 상황에 따른 최적의 공급 방안을 수립할 수 있을 것이다.

It is an essential to predict water usage for establishing an optimal supply operation plan and reducing power consumption. However, the water usage by consumer has a non-linear characteristics due to various factors such as user type, usage pattern, and weather condition. Therefore, in order to predict the water consumption, we proposed the methodology linking various techniques that can consider non-linear characteristics of water use and we called it as KWD framework. Say, K-means (K) cluster analysis was performed to classify similar patterns according to usage of each individual consumer; then Wavelet (W) transform was applied to derive main periodic pattern of the usage by removing noise components; also, Deep (D) learning algorithm was used for trying to do learning of non-linear characteristics of water usage. The performance of a proposed framework or model was analyzed by comparing with the ARMA model, which is a linear time series model. As a result, the proposed model showed the correlation of 92% and ARMA model showed about 39%. Therefore, we had known that the performance of the proposed model was better than a linear time series model and KWD framework could be used for other nonlinear time series which has similar pattern with water usage. Therefore, if the KWD framework is used, it will be possible to accurately predict water usage and establish an optimal supply plan every the various event.

키워드

과제정보

이 논문은 2017년도 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No. 2017R1A2B3005695).

참고문헌

  1. Abbaszadeh, P. (2016). "Improving hydrological process modeling using optimized threshold-based wavelet de-noising technique." Water Resources Management, Vol. 30, No. 5, pp. 1701-1721. https://doi.org/10.1007/s11269-016-1246-5
  2. Altunkaynak, A., and Nigussie, T.A. (2017). "Monthly water consumption prediction using season algorithm and wavelet transform-based models." Journal of Water Resources Planning and Management, Vol. 143, No. 6, 04017011. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000761
  3. Alvisi, S., Franchini, M., and Marinelli, A. (2007). "A short-term, pattern-based model for water-demand forecasting." Journal of Hydroinformatics, Vol. 9, No. 1, pp. 39-50. https://doi.org/10.2166/hydro.2006.016
  4. Arthur, D., and Vassilvitskii, S. (2006). "How slow is the k-means method?." Proceedings of The Twenty-second Annual Symposium on Computational Geometry, ACM, New York, NY, U.S., pp. 144-153.
  5. Atsalakis, G., Minoudaki, C., Markatos, N., Stamou, A., Beltrao, J., and Panagopoulos, T. (2007). "Daily irrigation water demand prediction using adaptive neuro-fuzzy inferences systems (anfis)." Proceeding 3rd IASME/WSEAS International Conference on Energy, Environment, Ecosystems and Sustainable Development, WSEAS, Agios Nikolaos, Greece.
  6. Choi, G.S., Yu, C., Jin, R.M., Yu, S.K., and Chun, M.G. (2009). "Short-term water demand forecasting algorithm using AR model and MLP." Journal of Korean Institute of Intelligent Systems, Vol. 19, No. 5, pp.713-719. https://doi.org/10.5391/JKIIS.2009.19.5.713
  7. Choi, J.H., and Kim, J.B. (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, Vol. 55, No. 7, pp. 31-39. https://doi.org/10.5573/ieie.2018.55.7.31
  8. Chun, B., Lee, T., Kim, S., Kim, J., Jang, K., Chun, J., Jang, W.S., Shin, Y. (2020). "Estimation of DNN-based Soil moisture at mountainous regions." Journal of The Korean Society of Agricultural Engineers, Vol. 62, No. 5, pp. 93-103. https://doi.org/10.5389/KSAE.2020.62.5.093
  9. Firat, M., Turan, M.E., and Yurdusev, M.A. (2010). "Comparative analysis of neural network techniques for predicting water consumption time series." Journal of hydrology, Vol. 384, No. 1-2, pp. 46-51. https://doi.org/10.1016/j.jhydrol.2010.01.005
  10. Han, S.M., Hwang, G.S., Choe, S.Y., and Park, J.W. (2014). "A study on classifying algorithm of disaster recovery resources using statistical method." Journal of Korean Society of Hazard Mitigation, Vol. 14, No. 1, pp. 49-58. https://doi.org/10.9798/KOSHAM.2014.14.1.49
  11. Intelligence, G.W., Yearbook, I.D., Summit, G.W., and Card, R. (2011). "Global water intelligence." Global Water Intelligence, Vol. 12, No. 10, pp. 1-72.
  12. Kim, D., Kim, J., Kwak, J., Necesito, I.V., Kim, J., and Kim, H.S. (2020a). "Development of water level prediction models using deep neural network in mountain wetlands." Journal of Wetlands Research, Vol. 22, No. 2, pp. 106-112. https://doi.org/10.17663/JWR.2020.22.2.106
  13. Kim, D., Kim, J., Wang, W., Lee, J., Jung, J., and Kim, H.S. (2020b). "Analysis of morphological characteristics of collapsed reservoirs in Korea." Journal of the Korean Society of Hazard Mitigation, Vol. 20, No. 5, pp. 207-216. https://doi.org/10.9798/kosham.2020.20.5.207
  14. Koo, J.Y., Yu, M.J., Kim, S.G., Shim, M.H., and Akira, K. (2005). "Estimation of long-term water demand by principal component and cluster analysis and practical application." Journal of Korean Society of Environmental Engineers, Vol. 27, No. 8, pp. 870-876.
  15. Kwon, H.H., Kim, M.J., and Kim, O.G. (2012). "A development of water demand forecasting model based on Wavelet transform and Support vector machine." Journal of Korea Water Resources Association, Vol. 45, No. 11, pp. 1187-1199. https://doi.org/10.3741/JKWRA.2012.45.11.1187
  16. Kwon, S., Kim, S., Tak, O., and Jeong, H. (2017). "A study on the clustering method of row and multiplex housing in Seoul using K-means clustering algorithm and hedonic model." Journal of Intelligence and Information Systems, Vol. 23, No. 3, pp. 95-118. https://doi.org/10.13088/JIIS.2017.23.3.095
  17. Kyoung, M.S., Kim, S.D., Kim, B.K. and Kim, H.S. (2007). "Construction of hydrological drought severity-area-duration curves using cluster analysis." Journal of the Korean Society of Civil Engineers, Vol. 27, No. 3B, pp. 267-276.
  18. Lee, D., Kim, J., and Kim, H. (2009). "Statistical analysis on non-household unit water use for business categories." Journal of the Korean Society of Civil Engineers, Vol. 29, No. 4B, pp. 385-396.
  19. Nam, W.H., Kim, T., Hong, E.M., Hayes, M.J., and Svoboda, M.D. (2015). "Water supply risk assessment of agricultural reservoirs using irrigation vulnerability model and cluster analysis." Journal of the Korean Society of Agricultural Engineers, Vol. 57, No. 1, pp. 59-67. https://doi.org/10.5389/KSAE.2015.57.1.059
  20. Tabesh, M., and Dini, M. (2009). "Fuzzy and Neuro- fuzzy models for short-term water demand forecasting in Tehran." Iranian Journal of Science & Technology, Vol. 33, No. B1, pp. 61-77.
  21. Yoo, Y., Lee, M., Lee, T., Kim, S., and Kim, H.S. (2019). "Decomposition of wave components in sea level data using discrete wavelet transform." Journal of Wetlands Research, Vol. 21, No. 4, pp. 365-373. https://doi.org/10.17663/JWR.2019.21.4.365