A Water Consumption Prediction Model for Municipal Consumers

Subject Areas : Article frome a thesis

Sajjad Zarifzadeh ¹ , Fatemeh Kaveh-Yazdy ²

1 - Assistant Prof. of Computer Engineering, Computer Engineering Dept., Yazd University, Yazd, Iran
2 - Senior Data Scientist, Data Science Institute, Yazd University, Yazd, Iran

Received: 2020-06-20 Accepted : 2021-09-01 Published : 2022-04-21

Keywords: Regression, Quantile Regression, Consumption Prediction, Random Forest, Anomaly,

Abstract :

Smart water resource management is the best short-time solution for water resource shortage around
the world. Predicting water demand is the major prerequisite to be aware of the required water within a
short time. The proposed prediction framework uses the billing records of water consumers in Yazd city
to extract consumption history. In addition, external data resources such as business calendar data, urban
water production, meteorological parameters, the financial value of buildings, and in-stream pressure
are collected and employed in the prediction model. The proposed framework tracks the changes in
consumption behaviors of consumers, which are grouped according to their volume of water usage to
remove consumers with anomalous consumption behaviors. The cleaned grouped records of
consumption are utilized in the fitting of a quantile regressor with three breakpoints to forecast the water
demand of the consumers for the next month. Results of the experiments showed that the proposed
model’s prediction percentage error is less than 10%. Besides, the model is able to recognize consumers
with anomalous consumption behaviors.

References:

1.               Alvi, M. S. Q., Mahmood, I.,  Javed, F., Malik, A. W., and Sarjoughian, H., 2018. Dynamic behavioural modeling, simulation and analysis of household water consumption in an urban area: a hybrid approach, in Proceedings of the 2018 Winter Simulation Conference:  2411–2422.

2.               Haque, M. M., de Souza, A. and Rahman, A., 2017. Water Demand Modelling Using Independent Component Regression Technique, Water Resour. Manag., 31(1): 299–312.

3.       Arandia, E., Ba, A., Eck, B. and McKenna, S., 2016. Tailoring Seasonal Time Series Models to Forecast Short-Term Water Demand, J. Water Resour. Plan. Manag., 142(3): 4015067.

4.       Firat, M., Turan, M. E. and Yurdusev, M. A., 2010. Comparative analysis of neural network techniques for predicting water consumption time series, J. Hydrol., 384 (1-2): 46–51.

5.               Tiwari, M. K., and Adamowski, J., 2013. Urban water demand forecasting and uncertainty assessment using ensemble wavelet-bootstrap-neural network models, Water Resour. Res., 49 (10): 6486–6507.

6.       Yazdani, S., Abedi, S., and Abedi, S., 2014. Forecasting Models for Domestic and Agricultural Water Consumptions in Tehran Province (Case Study: Amirkabir Dam), Iran. J. Agric. Econ. Dev. Res., 45 (1): 41–48. [In Persian]

7.               Mousavi, S. N.  and Kavoosi-Kalashami, M., 2016, Evaluation of Seasonal, ANN, and Hybrid Models in Modeling Urban Water Consumption A Case Study of Rash City, J. Water Wastewater, 27(4): 93–98. [In Persian]

8.       Mirdehghan, S., Saadatjoo, F., Mirjalili, M., 2014. Water consumption forecast and effective features: Yazd City, The first national computer engineering symposium, Tehran, Iran.

9.       Ejlali, R. G., Ghasedi-Fathabadi, M., 2014, Water consumption forecast using artificial neural networks: Soufian City, National symposium of design and computation in civil engineering and architecture using high-tech methods, Maragheh, East Azarnaijan, Iran. [In Persian]

10.   Tabesh, M., Dini, M. Khoshkholgh, A. J. and Zahraie, B., 2008. Estimation of Tehran Daily Water Demand Using Time Series Analysis, Iran-Water Resour. Res., 4 (2): 57–65.

11.   Aram            A.-R. and Agheli, L., 2012. A Hybrid Model for Forecasting Daily Urban Water Demand, J. Quant. Econ., 9 (1): 1–17.

12.   Abdi-dehkordi, M., Meftah-halqi, M., Kahe, M., 2014, Determining meteorological parameters affecting urban water consumption using fuzzy clustering algorithm (Case study: Gorgan city), Sol. and Wat. Res. Consrv., 68(2): 293-301.

13.   Gooshe, S., Yazdanpanah, M. J., Tabesh, M., 2008. Forecasting Tehran’s Short-time Water Consumption using Artificial Neural Networks, University of Tehran School of Engineering Journal, 41 (1): 11-24. [In Persian]

14.   Karimi, D., 2004. Applications of Fuzzy Logic in Forecasting Tehran’s Short-time Water Consumption, Tarbiat Moddares University. [In Persian].

15.           Rasifaghihi, N., Li, S. S. and Haghighat, F., 2020. Forecast of urban water consumption under the impact of climate change, Sustain. Cities Soc., 52: 101848.

16.           Mouatadid, S. and Adamowski, J., 2017. Using extreme learning machines for short-term urban water demand forecasting, Urban Water J., 14 (6): 630–638.

17.           Papageorgiou, E. I., Poczeta, K. and Laspidou, C., 2016. Hybrid model for water demand prediction based on fuzzy cognitive maps and artificial neural networks, IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 1523–1530.

18.           Villarín, M. C., 2019. Methodology based on fine spatial scale and preliminary clustering to improve multivariate linear regression analysis of domestic water consumption, Appl. Geogr., 103: 22–39.

19.   Dias, T. F., Kalbusch, A. and Henning, E., 2018. Factors influencing water consumption in buildings in southern Brazil, J. Clean. Prod., 184: 160–167.

20.   Taghvaei, A., Pourjafar, M. R., Hossein-Abadi, M., and Riyahi-Medvar, H., 2011.  Developing an Expert System Model for Predicting Annual Urban Residential Water Demand Using Artificial Neural Network (Case Study: Ilam City), Arman. Archit. Urban Dev., 4(6): 63–74.

21.           Sardinha-Lourenço, A., Andrade-Campos, A., Antunes, A. and Oliveira, M. S., 2018. Increased performance in the short-term water demand forecasting through the use of a parallel adaptive weighting strategy, J. Hydrol., 558: 392–404.

22.           Ebrahim-Banihabib, M. and Mousavi-Mirkalaei, P., 2019. Extended linear and non-linear auto-regressive models for forecasting the urban water consumption of a fast-growing city in an arid region, Sustain. Cities Soc., 48: 101585.

23.           Eslamian, S. A., Li, S. S. and Haghighat, F., 2016, A new multiple regression model for predictions of urban water use, Sustain. Cities Soc., 27: 419–429.

24.           Goli Ejlali, R., 2018. Hybrid Artificial Neural Network-Geostatistics Model for Urban Water Consumption Prediction. A Case Study: Osku City, J. Water Wastewater, 29(5): 98–111. [In Persian]

25.   Tabesh, M. and Dini, M., 2010.  Forecasting Daily Urban Water Demand Using Artificial Neural Networks, A Case Study of Tehran Urban Water, J. Water Wastewater, 21 (1): 84–95.

26.           Flores, J. J., López Farías, R. , Puig, V. and Rodriguez Rangel, H., 2017. Short-term demand forecast using a bank of neural network models trained using genetic algorithms for the optimal management of drinking water networks, Journal of Hydroinformatics, 19: 1–16.

27.           Gato, S., Jayasuriya, N.  and Roberts, P., 2007. Temperature and rainfall thresholds for base use urban water demand modelling, J. Hydrol., 337(3): 364–376.

28.           Beheshti, S. , Sahebalam, A. and Nidoy, E., 2019. Structure dependent weather normalization, Energy Sci. Eng., 7(2): 338–353.

29.           Donevska K. and Panov, A., 2019. Climate change impact on water supply demands: case study of the city of Skopje, Water Supply, vol. 19(7): 2172–2178.

30.           Vonk, E., Cirkel, D. G. and Blokker, M., 2019. Estimating peak daily water demand under different climate change and vacation scenarios, Water (Switzerland), 11(9): 1874-1882.

31.           Colace, F., De Santo, M., Greco, L. and Napoletano, P., 2015. Weighted Word Pairs for query expansion, Inf. Process. Manag., 51(1): 179–193.

32.           Sadiq W. A. and Karney, B., 2005, Modeling Water Demand Considering Impact of Climate Change – a Toronto Case Study, J. Water Manag. Model, 13(1): 1-11.

33.           Ouyang, Y., Wentz, E. A., Ruddell, B. L. and Harlan, S. L., 2014. A Multi-Scale Analysis of Single-Family Residential Water Use in the Phoenix Metropolitan Area, JAWRA J. Am. Water Resour. Assoc., 50(2): 448–467.

34.   Taylor, B. A., 2012. Predicting normalised monthly patterns of domestic external water demand using rainfall and temperature data, Water Sci. Technol. Water Supply, 12(2): 168–178.

35.   Zhang, D., Ni, G., Cong, Z. , Chen, T.  and Zhang, T., 2014. Statistical interpretation of the daily variation of urban water consumption in Beijing, China, Hydrol. Sci. J., 59(1): 181–192.

36.           Tiwari, M. K. and Adamowski, J. F., 2015. Medium-Term Urban Water Demand Forecasting with Limited Data Using an Ensemble Wavelet–Bootstrap Machine-Learning Approach, J. Water Resour. Plan. Manag., 141(2): 04014053.

37.   Yasar, A., Bilgili, M. and Simsek, E., 2012. Water Demand Forecasting Based on Stepwise Multiple Nonlinear Regression Analysis, Arab. J. Sci. Eng., 37(8): 2333–2341.

38.   Toms J. D., and Lesperance, M. L., 2003. Piecewise Regression: A Tool For Identifying Ecological Thresholds, Ecology, 84(8): 2034–2041.

39.   Li, H. , Deng, X. , Kim, D.-Y., and Smith, E. P., 2014. Modeling maximum daily temperature using a varying coefficient regression model, Water Resour. Res., 50(4): 3073–3087.

40.   Community-Contributors, scikit-learn 0.22.2 Documentation: LassoCV, 2020, [Online]. Available: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LassoCV.html#sklearn.linear_model.LassoCV.

41.   Community-Contributors, scikit-learn 0.22.2 Documentation: RandomForestRegressor, 2020.

42.           Hastie, T., Tibshirani, R. and Friedman, J., 2009. The elements of statistical learning: data mining, inference and prediction, 2nd ed. Springer.

43.           Sun, Q., Zhou, W.-X. and Fan, J., 2018. Adaptive Huber Regression, J. Am. Stat. Assoc., 2018(1): 1–24.

44.           Wagner, A. K., Soumerai, S. B., Zhang, F. and Ross-Degnan, D., 2002. Segmented regression analysis of interrupted time series studies in medication use research, J. Clin. Pharm. Ther., 27 (4): 299–309.

45.   Vijai, P., and Sivakumar, P. B., 2018. Performance comparison of techniques for water demand forecasting, Procedia Comput. Sci., 143(1): 258–266.

                Kaveh-Yazdy, F. and Zarifzadeh, S., 2021. Water Meter Replacement Recommendation for Municipal Water Distribution Networks using Ensemble Outlier Detection Methods, J. AI Data Min., 9(4): 425–438.