대한토목학회논문집 (KSCE Journal of Civil and Environmental Engineering Research)

  • 제43권6호
  • /
  • Pages.763-774
  • /
  • 2023
  • /
  • 1015-6348(pISSN)
  • /
  • 2799-9629(eISSN)
대한토목학회 (Korean Society of Civil Engeneers)
권호 표지
DOI QR코드

DOI QR Code

생활용수 회귀수량의 분석을 위한 시계열 단기 예측모형 구축

Construction of a Short-term Time-series Prediction Model for Analysis of Return Flow of Residential Water

  • 이승연 (국토연구원 국토환경.자원연구본부) ;
  • 이상은 (국토연구원 안전국토연구센터)
  • 투고 : 2023.10.06
  • 심사 : 2023.11.10
  • 발행 : 2023.12.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

도시 하류의 가용수량과 관련된 생활용수 회귀수량은 아직까지 정확한 회귀수량 파악이 어려운 상황이다. 본 연구에서는 생활용수 물순환시스템을 면(面)적 개념으로 물 유입, 물 전달, 물 유출 단계로 정의하였다. 대상지는 전라남도 함평군 일대로 선정했으며 물순환계통도 작성 및 완전·불완전 계측지점의 분류를 통해 단일 유입~단일 유출지점으로 설정하였다. 총 6년(2017년 1월 1일~2022년 12월 31일)간 일단위의 유입량·유출량 자료로 시계열예측모형(ARIMA 모형, 전이함수모형)을 구축하였고 학습기간과 검증기간으로 분리하여 유입량·유출량을 예측하였다. 그 결과, 두 모형 모두 안정적인 잔차와 통계적 유의성 확보로 단기 예측 실현 가능성을 보여 초기 단계의 물순환시스템을 구현하였다. 향후에는 불완전 계측지점, 미계측지점, 기상조건을 추가하고 최적의 모형을 선정하여 대상 유역의 실제 회귀량을 예측하고 효율적인 물 운영이 가능하길 기대해본다.

The water availability in a river is related to the return flow of residential water. However it is still difficult to determine the exact return flow. In this study, the residential water-cycle system is defined as a process consisting of water inflow, water transfer and water outflow. The study area is Hampyeong-gun, Jeollanam-do, and is set as a single inflow to a single outflow through the water-cycle system after classification of complete and incomplete measurement points. The time-series prediction models(ARIMA model and TFM) are established with daily inflow and outflow data for 6 years. Inflow and outflow are predicted by dividing into training and test periods. As a result, both models show the feasibility of short-term prediction by deriving stable residuals and securing statistical significance, implementing the preliminary form of the water-cycle system. As a further study, it is suggested to predict the actual return flow of the target basin and efficient water operation by adding input factors and selecting the optimal model.

키워드

과제정보

This work is supported by the Korea Environmental Industry & Technology Institute (KEITI) grant funded by the Korea Ministry of Environment (2022003610003).

참고문헌

  1. Ding, L., Lv, Z., Han, M., Zhao, X. and Wang, W. (2019). "Forecasting China's wastewater discharge using dynamic factors and mixed-frequency data." Environmental Pollution, Elsevier, Vol. 255, 113148, https://doi.org/10.1016/j.envpol.2019.113148. 
  2. El-Din, A. G. and Smith, D. W. (2002). "A neural network model to predict the wastewater inflow incorporating rainfall events." Water Research, Elsevier, Vol. 36, No. 5, pp. 1115-1126, https://doi.org/10.1016/S0043-1354(01)00287-1. 
  3. Jeong, C. G. and Kim, S. J. (2015). "A study on the improvement of the calculation method of return flow for residential water." Magazine of Korea Water Resources Association, KWRA, Vol. 48, No. 12, pp. 34-42 (in Korean). 
  4. Karimi, H. S., Natarajan, B., Ramsey, C. L., Henson, J., Tedder, J. L. and Kemper, E. (2019). "Comparison of learning-based wastewater flow prediction methodologies for smart sewer management." Journal of Hydrology, Elsevier, Vol. 577, 123977, https://doi.org/10.1016/j.jhydrol.2019.123977. 
  5. Lee, J. H. (2012). "Study on the relationship between weather conditions, sewage and operational variables of WWTPs using multivariate statistical methods." Journal of Korean Society on Water Environment, KSWE, Vol. 28, No. 2, pp. 285-291 (in Korean). 
  6. Lee, W. W. and Jang, I. H. (2018). Analysis of Time Series Data Using Spss (3rd ed.). Freeacademy. pp. 118-197, https://product.kyobobook.co.kr/detail/S000001762430. 
  7. Ministry of Environment (ME) (2012). Korea Environment Corporation. Water quality TMS installation and operation manual for advanced and scientific water quality management (in Korean). 
  8. Ministry of Environment (ME) (2021). 1st National Water Management Master Plan 2021-2030, Collaboration with relevant ministries, 11-1480000-001756-14 (in Korean). 
  9. Ministry of Environment (ME) (2022a). 2021 Statistics of Wasteworks (in Korean). 
  10. Ministry of Environment (ME) (2022b). 2021 Statistics of Waterworks (in Korean). 
  11. Wei, X., Kusiak, A. and Sadat, H. R. (2013). "Prediction of influent flow rate: data-mining approach." Journal of Energy Engineering, ASCE, Vol. 139, No. 2, pp. 118-123.  https://doi.org/10.1061/(ASCE)EY.1943-7897.0000103
  12. Yoo, H. J., Lee, S. O., Choi, S. H. and Park, M. H. (2020). "Development of a data-driven model for forecasting outflow to establish a reasonable river water management system." Journal of Korean Society of Disaster and Security, KSDS, Vol. 13, No. 4, pp. 75-92, https://doi.org/10.21729/KSDS.2020.13.4.75 (in Korean). 
  13. Zhang, Q., Li, Z., Snowling, S., Siam, A. and El-Dakhakhni, W. (2019). "Predictive models for wastewater flow forecasting based on time series analysis and artificial neural network." Water Science and Technology, IWA, Vol. 80, No. 2, pp. 243-253, https://doi.org/10.2166/wst.2019.263.