Journal of Korean Society of Water and Wastewater (상하수도학회지)

The Korean Society of Water and Wastewater (대한상하수도학회)
권호 표지
DOI QR코드

DOI QR Code

Water demand forecasting at the DMA level considering sociodemographic and waterworks characteristics

사회인구통계 및 상수도시설 특성을 고려한 소블록 단위 물 수요예측 연구

  • Saemmul Jin (Department of Environmental Engineering, University of Seoul) ;
  • Dooyong Choi (K-water Research Institute) ;
  • Kyoungpil Kim (K-water Research Institute) ;
  • Jayong Koo (Department of Environmental Engineering, University of Seoul)
  • Received : 2023.10.17
  • Accepted : 2023.11.20
  • Published : 2023.12.15
Download PDF
⟨ Previous Next ⟩

Abstract

Numerous studies have established a correlation between sociodemographic characteristics and water usage, identifying population as a primary independent variable in mid- to long-term demand forecasting. Recent dramatic sociodemographic changes, including urban concentration-rural depopulation, low birth rates-aging population, and the rise in single-person households, are expected to impact water demand and supply patterns. This underscores the necessity for operational and managerial changes in existing water supply systems. While sociodemographic characteristics are regularly surveyed, the conducted surveys use aggregate units that do not align with the actual system. Consequently, many water demand forecasts have been conducted at the administrative district level without adequately considering the water supply system. This study presents an upward water demand forecasting model that accurately reflects real water facilities and consumers. The model comprises three key steps. Firstly, Statistics Korea's SGIS (Statistical Geological Information System) data was reorganized at the DMA level. Secondly, DMAs were classified using the SOM (Self-Organizing Map) algorithm to consider differences in water facilities and consumer characteristics. Lastly, water demand forecasting employed the PCR (Principal Component Regression) method to address multicollinearity and overfitting issues. The performance evaluation of this model was conducted for DMAs classified as rural areas due to the insufficient number of DMAs. The estimation results indicate that the correlation coefficients exceeded 0.9, and the MAPE remained within approximately 10% for the test dataset. This method is expected to be useful for reorganization plans, such as the expansion and contraction of existing facilities.

Keywords

References

  1. Asan, U., Ercan, S. (2012). An Introduction to Self-Organizing Maps. In: Kahraman, C. (eds) Computational Intelligence Systems in Industrial Engineering. Atlantis Computational Intelligence Systems, 6, Atlantis Press, Paris.
  2. Billings, R.B. and C.V. Jones. (2008). Forecasting Urban Water Demand. Denver, CO: American Water Works Association.
  3. Chung S.H. (2005). Development of strategic evaluation methodology for performance of water losses management in water distribution system, Doctor's Thesis, University of Seoul, 5-75.
  4. Jeong G.M., Kang D.S. and Kim K.P. (2022). Analysis on drinking water use change by COVID-19: a case study of residential area in S-city, South Korea, J. Korea Water Resour. Assoc., 55(1), (2022), 11-21. https://doi.org/10.3741/JKWRA.2022.55.1.11
  5. Huh M.H. (2003). Principal components self-organizing map PC-SOM, Korean J. Appl. Stat., 16(2), 
  6. Kohonen, T. (2001). Self-organizing maps 3rd edition, Springer, Berlin Heidelberg.
  7. Koizumi Akira, Japan Water Research Center. (1991). Practice of water demand forecasting for waterworks planning.
  8. Koo, J.A., Yu, M.J, Kim, S.G., Shim, M.H., and Koizumi Akira (2005). Estimation of long-term water demand by principal component and cluster analysis and practical application, J. Korean Soc. Environ. Eng., 27(8), 870-876.
  9. Kim K.B, Park H.K, Kim T.Y, Hyung J.S. and Koo J.Y. (2022). Water consumption forecasting and pattern classification according to demographic factors and automated meter reading, J. Korean Soc. Water Wastewater 36(3), 149-165. https://doi.org/10.11001/jksww.2022.36.3.149
  10. Kim N.E., Kim. S.E., Kim. S.C. and Cha. D.H. Seoul Water Institute (2021). Research on water supply response to variations in water usage factors.
  11. Kim S.G, Pyon S.S, Kim Y.S. and Koo J.Y. (2006). Forecasting the long-term water demand using system dynamics in seoul, J. Korean Soc. Water Wastewater, 20(2), 187-196.
  12. Lee, J.S. and Hong, W.H. (2012). "Estimation of water demand using living water units in Daegu city", Proceedings of Autumn Annual Conference of AIK, 25 October, Gwang-Ju, Architectural Institute of Korea.
  13. Makki A.A., Stewart R.A., Beal C.D. and Panuwatwanich K. (2015). Novel bottom-up urban water demand forecasting model:Revealing the determinants, drivers and predictors of residential indoor end-use consumption, Resources, Conservation and Recycling, 95, 15-37. https://doi.org/10.1016/j.resconrec.2014.11.009
  14. Mamade A., Loureiro D., Covas D., Coelho S.T. and Amado C. (2014). Spatial and Temporal Forecasting of Water Consumption at the DMA Level Using Extensive Measurements, Procedia Engineering, 70, 1063-1073. https://doi.org/10.1016/j.proeng.2014.02.118
  15. Ministry of Environment and Land, Infrastructure and Transport, (2014). Handbook for Water Supply Demand Forecasting Tasks.
  16. SGIS PLUS, https://sgis.kostat.go.kr/view/index
  17. Yu, M.J, Koo, J.A., Koo, Y.H. and Kim, S.G. (2004). Forecasting houly water demand using linear and non-linear model, J. Korean Soc. Environ. Eng., 26(3), 277-283.