Abstract
In this paper, we investigate the application of Bayesian Networks (BN) for the 1-step ahead forecasting of daily water demand. The water demand time series is associated with the series containing information for daily precipitation and mean temperature that play the role of the additional explanatory variables. To enable the application of the standard Bayesian network as a predictive model, all considered time series are discretized. The number of discretization intervals is assumed as a parameter of the following learn-and-test trials. To test forecasting accuracy, we propose a novel discrete type of mean absolute error measure. Then, the concept of growing window is used to learn and test several Bayesian networks. For comparative experiments, different algorithms for learning structure and parameters of the BNs are applied. The experiments revealed that a simple two-node BN outperformed all of the other complex models tested for the considered data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abramson, B., Brown, J., Edwards, W., Murphy, A., Winkler, R.L.: Hailfinder: a Bayesian system for forecasting severe weather. Int. J. Forecast. 12(1), 57–71 (1996)
Adamowski, J., Adamowski, K., Prokoph, A.: A spectral analysis based methodology to detect climatological influences on daily urban water demand. Math. Geosci. 45(1), 49–68 (2013)
Billings, R.B., Jones, C.V.: Forecasting Urban Water Demand. American Water Works Association (2008)
Biondi, D., Luca, D.D.: Performance assessment of a bayesian forecasting system (BFS) for real-time flood forecasting. J. Hydrol. 479(0), 51–63 (2013)
Donkor, E., Mazzuchi, T., Soyer, R., Alan Roberson, J.: Urban water demand forecasting: review of methods and models. J. Water Resour. Plan. Manag. 140(2), 146–159 (2014)
Froelich, W., Salmeron, J.L.: Evolutionary learning of fuzzy grey cognitive maps for the forecasting of multivariate, interval-valued time series. Int. J. Approx. Reason. 55(6), 1319–1335 (2014)
Jensen, F.V.: Bayesian Networks and Decision Graphs. Springer (2001)
Juszczuk, P., Froelich, W.: Learning fuzzy cognitive maps using a differential evolution algorithm. Pol. J. Env. Stud. 12(3B), 108–112 (2009)
Pulido-Calvo, I., Gutirrez-Estrada, J.C.: Improvedfrigation water demand forecasting using a soft-computing hybrid model. Biosyst. Eng. 102(2), 202–218 (2009)
Pulido-Calvo, I., Montesinos, P., Roldn, J., Ruiz-Navarro, F.: Linear regressions and neural approaches to water demand forecasting in irrigation districts with telemetry systems. Biosyst. Eng. 97(2), 283–293 (2007)
Qi, C., Chang, N.B.: System dynamics modeling for municipal water demand estimation in an urban region under uncertain economic impacts. J. Env. Manag. 92(6), 1628–1641 (2011)
Scutari, M.: Bayesian network structure learning, parameter learning and inference. http://www.bnlearn.com/ (2014)
Vlachopoulou, M., Chin, G., Fuller, J.C., Lu, S., Kalsi, K.: Model for aggregated water heater load using dynamic Bayesian networks. In: Proceedings of the DMIN’12 International Conference on Data Mining, pp. 1–7 (2012)
Acknowledgments
The work was supported by ISS-EWATUS project which has received funding from the European Union’s Seventh Framework Programme for research, technological development and demonstration under grant agreement no. 619228.
The authors would like also to thank the water distribution company in Sosnowiec (Poland) for gathering water demand data and the personal of the weather station of the University of Silesia for collecting and preparing meteorological data.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Magiera, E., Froelich, W. (2015). Application of Bayesian Networks to the Forecasting of Daily Water Demand. In: Neves-Silva, R., Jain, L., Howlett, R. (eds) Intelligent Decision Technologies. IDT 2017. Smart Innovation, Systems and Technologies, vol 39. Springer, Cham. https://doi.org/10.1007/978-3-319-19857-6_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-19857-6_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19856-9
Online ISBN: 978-3-319-19857-6
eBook Packages: EngineeringEngineering (R0)