Wavelet Transform을 이용한 물수요량의 특성분석 및 다원 ARMA모형을 통한 물수요량예측

Water Supply forecast Using Multiple ARMA Model Based on the Analysis of Water Consumption Mode with Wavelet Transform.

  • 발행 : 1998.06.01

초록

시계열자료의 분해능력이 뛰어난 wavelet 변환을 사용하여 물소비특성을 분석하였다. Wavelet 변환의 기저함수로는 물수요량의 경우 Coiflets5 함수, 기온측정치의 경우 Coiflets3 함수를 사용하였으며 해석결과 212 scale에서 목표된 장기간에 걸친 변화추이는 hyperbolic tangent 함수의 형태로 전기간에 걸처 꾸준한 증가세를 보였다. 또한 절기혹은 경기주기와 밀접한 관련이 있을 것으로 생각되는 추가수요가 6월과 12월말을 정점으로 발생하였으며 이 추가 수요량은 하절기의 경우 $1,700\;\textrm{cm}^3/hr$, 동절기의 경우 $500\;\textrm{cm}^3/hr$ 정도인 것으로 관측되었다. 정수장 생산량 시계열자료에 내재한 주기성분은 주기가 각각 3.13day, 33.33 hr, 23.98hr와 12hr인 것으로 규명되었다. 진폭은 주기가 23,98hr인 성분이 가장 큰 것으로 밝혀졌으며 2i[i = 1,2,…12] scale에서 목도된 단주기성분들은 Gaussian PDF를 따르는 것이 확인되엇다. 잔차성분의 상호독립성, 자색파여부와 FPE의 최소화를 기준으로 할 경우 물수요량의 최적예측모형으로는 기온을 입력자료로한 다원 AR[32, 16, 23]과 다원 ARM [20, 16, 10, 23]인 것으로 판단된다.

Water consumption characteristics on the northern part of Seoul were analyzed using wavelet transform with a base function of Coiflets 5. It turns out that long term evolution mode detected at 212 scale in 1995 was in a shape of hyperbolic tangent over the entire period due to the development of Sanggae resident site. Furthermore, there was seasonal water demand having something to do with economic cycle which reached its peak at the ends of June and December. The amount of this additional consumption was about $1,700\;\textrm{cm}^3/hr$ on June and $500\;\textrm{cm}^3/hr$ on December. It was also shown that the periods of energy containing sinusoidal component were 3.13 day, 33.33 hr, 23.98 hr and 12 hr, respectively, and the amplitude of 23.98 hr component was the most humongous. The components of relatively short frequency detected at $2^i$[i = 1,2,…12] scale were following Gaussian PDF. The most reliable predictive models are multiple AR[32,16,23] and ARMA[20, 16, 10, 23] which the input of temperature from the view point of minimized predictive error, mutual independence or residuals and the availableness of reliable meteorological data. The predicted values of water supply were quite consistent with the measured data which cast a possibility of the deployment of the predictive model developed in this study for the optimal management of water supply facilities.

키워드

참고문헌

  1. 대한상하수도학회지 v.9 no.1 상기급수량의 단기예측 현인환;목동우
  2. Time series analysis-foreacasting and control Box, G.E.P.;Jenkins, G.M.
  3. Wavelets and their applications Wavelet analysis and signal processing Coifman, R.R.;Wickerhauser, M.V.;Ruskai, M. B.(ed.)
  4. Water Resour. Res. v.3 no.1 The impact of price on residential water demand and its relation to system design and price stucture Howe, C.W.;Linaweaver, F.P. Jr.
  5. System modeling and idetification Johansson, R.
  6. Stochastic water resources technology Kottegoda, N.T.
  7. Signal processing tool box Krauss, T.P.;Shure, L.;Little, J.N.
  8. IEEE Pattern Anal. and Machine Intell v.11 no.7 A theory for multiresoution signal decompostition: The wavelet representation Mallat, S.
  9. Water Resour. Res. v.26 no.2 A class of time series water demand models with nonlinear climatic effects Miaou, S.P.
  10. Wavelets and their applications Ruskai, M.B.;Beylkin, G.;Coifman, R.;Daubechies, I.;Mallat, S.;Meyer,Y.;Raphel, L.
  11. Wavelets and filter banks Strang, G.;Nguyen, T.
  12. Wavelets and other orthogonal systems with application Walter, G.G.