Forecasting Hourly Water Demands by Pattern Recognition Approach
Publication: Journal of Water Resources Planning and Management
Volume 119, Issue 6
Abstract
Hourly water‐demand data is forecasted with a model based on a combination of pattern recognition and time‐series analysis. Three repeating segments are observed in the daily demand pattern: “rising,” “oscillating,” “falling,” then “rising” again the following day. These are called “states” of the demand curve, and are defined as successive states of a Markov process. The transition probabilities between states are “learned,” and low‐order auto‐regressive integrated moving average (ARIMA) models fitted to each segment, using a modest amount of historical data. The model is then used to forecast hourly demands for a period of one to several days ahead. The forecast can be performed in real time, on a personal computer, with low computational requirements, at any time the system state deviates from the planned, or when new data become available. The process of model development, application, and evaluation is demonstrated on a water system in Israel.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Boston Water Study. (1966). Maguire Associates, Boston, Mass.
2.
Box, G. E. P., and Jenkins, G. M. (1970). Time series analysis, forecasting and control. Holden Day, San Francisco, CA.
3.
Christensen, P. E., and Macdassi, T. J. (1989). “Computerized analysis and prediction of hourly demand curves.” AWWA Speciality Comp. Conf., American Water Works Association, Denver, Colo.
4.
Gray, D. F. (1978). “Use of consumption predictors.” Tech. Rep. 4/78. Engrg. Dept., Cambridge Univ., Cambridge, England.
5.
Hartley, J. A., and Powell, R. S. (1991). “The development of a combined demand prediction system.” Civil Engrg. Systems, 8(4), 231–236.
6.
Jowitt, P. W., and Xu, C. (1992). “Demand forecasting for water distribution systems.” Civ. Engrg. Systems, 9, 105–121.
7.
Maidment, D. R., Miaou, S. P., and Crawford, M. M. (1985). “Transfer function models for daily urban water use.” Water Resour. Res., 21(4), 425–432.
8.
Maidment, D. R., and Parzen, E. (1984). “Time patterns of water use in six Texas cities.” J. Water Resour. Plan. Mgmt., ASCE, 110(1), 90–106.
9.
Moss, S. M. (1978). “On line optimal control of a water supply system.” PhD thesis, Cambridge, Univ., Cambridge, England.
10.
Mottl', V. V., and Muchnik, I. B. (1984). “Segmentation of structural curves using dynamic programming methods.” Automation and Remote Control, 45(1/Part 2), 88–94 (translated from Russian).
11.
Mottl', V. V., Muchnik, I. B., and Yacovlev, V. G. (1983). “Optimal segmentation of experimental curves.” Automation and Remote Control, 44(8), 1035–1044 (translated from Russian).
12.
Sterling, M. J. H., and Bagrelia, A. B. (1985). “Adaptive forecasting of daily water demands.” Comparative models for electrical load forecasting,” D. W. Bunn and E. D. Farmers, eds., John Wiley and Sons, New York, N.Y., 213–215.
13.
Yacovlev, V. G., and Vorob'yov, S. A. (1986). “Estimation of model parameters of random processes with instantly changing properties.” 2nd IFAC Symp. Stochastic Control, International Federation of Automatic Control, 244–248.
Information & Authors
Information
Published In
Journal of Water Resources Planning and Management
Volume 119 • Issue 6 • November 1993
Pages: 611 - 627
Copyright
Copyright © 1993 American Society of Civil Engineers.
History
Received: Sep 28, 1992
Published online: Nov 1, 1993
Published in print: Nov 1993
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.