Evaluation of the Effect of Data Size on Monthly Water Demand Estimation; Ankara (Etimesgut) Case Study

Year 2024, , 660 - 668, 31.12.2024

Kamil Aybuğa , Gamze Yücel Işıldar

https://doi.org/10.35229/jaes.1447207

Abstract

One of the most crucial steps in urban water management planning and operation is demand forecasting. Forecasting water demand consists a series of predictions that can be made using various methods. However, the predictive power and explanatory level of these methods vary depending on factors such as the amount of data and temporal resolution. Especially in univariate analyzes (using only time series), to reach a satisfying level of predictive power, appropriate amount of data should be benefited.
In this research, the effectiveness and the required data size of data smoothing methods, which can also be employed as pre-processing and forecasting methods in time series analysis, is discussed. For this purpose, WMA, EMA, LTP, QTP, Holt DES methods were applied to monthly water consumption data of a selected district of Ankara Province and their effectiveness in prediction was evaluated. According to the findings, the predictive power of classical time series smoothing methods in estimating monthly water demand; varies depending on the mathematical model they fit into, the size of the data used and variations that occur due to reasons such as seasonality, and that different data sizes. Thus, different data sizes may be needed to produce high-accuracy forecasts.

Keywords

Residential water demand;, Demand forecasting;, Time-series Analysis;, Monthly water demand;, Ankara;

Aylık Su Talebinin Tahmininde Veri Büyüklüğünün Etkisinin Değerlendirilmesi; Ankara (Etimesgut) Örneği

Abstract

Kentsel su yönetiminin planlama ve işletme süreçlerine yönelik en önemli adımı, talep tahminidir. Su talebinin kestirimi, birbirinden çok farklı yöntemlerle ortaya konulabilen bir dizi tahminden oluşmaktadır. Genel olarak literatürde pek çok yöntem ile karşılaşılmaktadır. Ancak bu yöntemlerin kestirim gücü ve açıklayıcılık düzeyi verilerin miktarı ve zamansal çözünürlüğü gibi unsurlarla ilişkili biçimde değişkenlik göstermektedir. Özellikle tek değişkenli (sadece zaman serisi kullanılan) analizlerde uygun miktarda veriler kullanılması gerekmektedir.
Bu araştırmada, zaman serisi analizinde veri ön işleme ve kestirim yöntemi olarak da kullanılabilen veri düzleştirme (smoothing) yöntemlerinin aylık su talebinin kestirimindeki etkinliği ve doğru tahminler üretilmesi için gerekli veri büyüklüğü ele alınmıştır. Bu maksatla, Ankara İline ait aylık su tüketim verilerine WMA, EMA, LTP, QTP, Holt DES yöntemleri uygulanarak tahmin konusundaki etkinlikleri değerlendirilmiştir. Elde edilen bulgulara göre, aylık düzeyde su talebinin tahmininde klasik zaman serisi düzleştirme yöntemlerinin kestirim gücünün; serilerin hangi matematiksel modele uyduğu, verilerin büyüklüğü ve mevsimsellik gibi nedenlerle ortaya çıkan varyasyonlar gibi nedenlerle ilişkili şekilde değiştiği ve yüksek doğrulukta tahminler üretilmesi konusunda her yöntem için farklı veri büyüklüğüne ihtiyaç duyulabileceği anlaşılmaktadır.

Keywords

Konut su tüketimi;, Tahmin;, Ankara;, Aylık tüketim, Zaman serisi analizi;

References

• Altunkaynak, A., Özger, M. & Çakmakci, M. (2005). Water Consumption Prediction of Istanbul City by Using Fuzzy Logic Approach. Water Resources Management 19(5), 641-654. DOI: 10.1007/s11269- 005-7371-1
• Altunkaynak, Abdusselam & Assefa, Tewodros. (2017). Monthly Water Consumption Prediction Using Season Algorithm and Wavelet Transform–Based Models. Journal of Water Resources Planning and Management. 143(6), 04017011. DOI: 10.1061/(ASCE)WR.1943-5452.0000761
• Alvisi, S., Franchini, M. & Marinelli, A. (2007). A short- term, pattern-based model for water-demand forecasting. Journal of Hydroinformatics, 9(1), 39- 50. DOI: 10.2166/hydro.2006.016
• Arandia, E., Ba, A., Eck, B. & McKenna, S. (2016). Tailoring seasonal time series models to forecast short-term water demand. Water Resources Planning and Management, 142(3), 04015067. DOI: 1061/(ASCE)WR.1943-5452.0000591
• Bata, M., Carriveau, R. & Ting, D S. (2020). Short-term water demand forecasting using hybrid supervised and unsupervised machine learning model. Smart Water, 5, 2 (2020). DOI: 10.1186/s40713-020- 00020-y
• Billings, B. & Jones, C. (1996). Forecasting Urban Water Demand, American Water Works Association, Denver, 179p.
• Chen, J. & Boccelli, D. (2014). Demand forecasting for water distribution systems. Procedia Engineering, 70, 339-342. DOI: 10.1016/j.proeng.2014.02.038
• Donkor, E., Mazzuchi, T., Soyer, R. & Roberson, J. (2014). Urban water demand forecasting: a review of methods and models. Journal of Water Resources Planning and Management,140(2), 146-159. DOI: 10.1061/(ASCE)WR.1943-5452.0000314
• Du, H., Zhao, Z. & Hui-feng, X. (2020). ARIMA-M: A New Model for Daily Water Consumption Prediction Based on the Autoregressive Integrated Moving Average Model and the Markov Chain Error Correction. Water, 12(3), 760, DOI: 10.3390/w12030760
• Firat, M., Turan, M. E., & Yurdusev, M. A. (2010). Comparative analysis of neural network techniques for predicting water consumption time series. Journal of Hydrology, 384 (1-2), 46-51. DOI: 0.1016/j.jhydrol.2010.01.005
• Froukh, M.L. (2001). Decision-Support System for Domestic Water Demand Forecasting and Management. Water Resources Management, 15, 363-382. DOI: 10.1023/A:1015527117823
• Fullerton, T. J., Ceballos, A. & Walke, A. (2016). Short- term forecasting analysis for municipal water demand. Journal of American Water Works Association, 108(1), 27-38. DOI: 10.5942/jawwa.2016.108.0003
• Hanif, H., Rasmani, K. & Ramli, N. (2013). Challanges in determining attributes to generate models for estimation of residential water consumption based on consumer data. AIP Conference. Proceedings, 22 April 2013, Putrajaya, Malaysia, DOI: 10.1063/1.4801281
• Hartley, J. & Powell, R. (1991). The Development of a Combined Water Demand Prediction Systems. Civil Engineering Systems, 8(4), 231-236. DOI: 10.1080/02630259108970631
• Homwongs, C., Satsri, T. & Foster, J.W. (1994). Adaptive forecasting of hourly municipal water consumption. Journal of Water Resources Planning & Management, 120(6), 888-905. DOI: 10.1061/(ASCE)0733-9496(1994)120:6(888)
• House-Peters, L. & Chang, H. (2011). Urban water demand modeling: review of concepts, methods, and organizing principles. Water Resources Research, 47(5), W05401. DOI: 10.1029/2010WR009624
• Jain, A., Varshney, A. & Joshi, U. (2001). Short-Term Water Demand Forecast Modelling at IIT Kanpur Using Artificial Neural Networks. Water Resources Management, 15, 299-321. DOI: 10.1023/A:1014415503476
• Jowitt, P.W. & Chengchao, X. (1992). Demand Forecasting for Water Distribution Systems. Civil Engineering Systems, 70(2014), 105-121. DOI: 10.1016/j.proeng.2014.02.038
• Karamaziotis, P., Raptis, A., Nikolopoulos, K., Litsiou, K. & Assimakopoulos, V. (2020). An empirical investigation of water consumption forecasting methods. International Journal of Forecasting, 36(2), 588-606. DOI: 10.1016/j.ijforecast.2019.07.009
• Maidment, D.R., Miaou, S. & Crawford, M.M. (1985). Transfer Function Models of Daily Urban Water Use. Water Resources Research, 21(4), 425-432. DOI: 10.1029/wr021i004p00425
• Miaou, S.P. (1990). A class of time series urbran water demand models with nonlinear climatic effects. Water Resources Research, 26(2), 169-178. DOI: 10.1029/WR026i002p00169
• Msiza, I., Nelwamondo, F. & Marwala, T. (2008). Water demand prediction using artificial neural networks and support vector regression. Journal of Computation, 3(11), 1-8. DOI: 10.4304/jcp.3.11.1-8
• Namdari, H., Ashrafi, S.M. & Haghighi, A. (2024). Deep learning–based short-term water demand forecasting in urban areas: a hybrid multichannel model. AQUA - Water Infrastructure, Ecosystems and Society, 73(3), 380-395. DOI: 10.2166/aqua.2024.200
• Niknam, A., Zare, H., Hosseini-Nasab, H., Mostafaeipour, A. & Herrera, M. (2022). A Critical Review of Short-Term Water Demand Forecasting Tools-What Method Should I Use? Sustainability, 14(9), 5412. DOI: 10.3390/su14095412
• Okeya, I., Kapelan,, Z., Hutton, C. & Naga, D. (2014). Online modelling of water distribution system using data assimilation. Procedia Engineering, 70, 1261- 1270. DOI: 10.1016/j.proeng.2014.02.139
• Ponte, B., de la Fuente, D., Pino, R. & Rosillo, R. (2015). Real-Time Water Demand Forecasting System through an Agent-Based Architecture. International Journal of Bio-Inspired Computation, pp. 147-156. DOI: 10.1504/IJBIC.2015.069559
• Sardinha-Lourenço, A., Andrea-Campos, A., Antunes, A. & Oliveira, M. (2018). Increased performance in the short-term water demand forecasting thorugh the use of a parallel adaptive weighting strategy. Journal of Hydrology, 558, 392-404. DOI: 10.1016/j.jhydrol.2018.01.047
• Smith, J., (1998). A model of daily municipal water use for short-term forecasting. Water Resources Research, 24(2), 201-206. DOI: 10.1029/WR024i002p00201
• Suhartono, S., Isnawati, S., Salehah, N A., Prastyo, D D., Kuswanto, H. & Lee, M H. (2018). Hybrid SSA- TSR-ARIMA for water demand forecasting. International Journal of Advances in Intelligent Informatics, 4(3), DOI: 10.26555/ijain.v4i3.275
• Taştan, H. (2017). Estimation of dynamic water demand function: the case of Istanbul. Urban Water Journal, 15(1), 75-82. DOI: 10.1080/1573062X.2017.1395899
• Tillman, D., Larsen, T A., Pahl-Wostl, C. & Gujer, W. (1999). Modeling the actors in water supply systems. Water Science & Technology, 39(4). DOI: 10.1016/s0273-1223(99)00055-4
• Tiwari, M. & Adamowski, J. (2013). Urban water demand forecasting and uncertainty assessment using ensemble wavelet–bootstrapneural network models. Water Resources Research, 49(10), 6486-6507. DOI: 10.1002/wrcr.20517
• Wewer, C. & Taormina, R. (2024). Conformal Prediction Intervals For Water Demand Forecasting. EGU General Assembly 2024, 14-19 April 2024, Vienna, Austria, EGU24-8166. DOI: 10.5194/egusphere- egu24-8166
• Xu, Y., Zhang, J., Long, Z. & Chen, Y. (2018). A new hybrid approach for short-term water demand time series forecasting. 2018 13th World Congress on Intelligent Control and Automation (WCICA), 04-08 July 2018, Changsha, China, 534-539, DOI: 10.1109/wcica.2018.8630722
• Yalçıntaş M, Bulu M, Küçükvar M, Samadi H. (2015). A Framework for Sustainable Urban Water Management through Demand and Supply Forecasting: The Case of Istanbul. Sustainability.; 7(8),11050-11067. DOI: 10.3390/su70811050
• Yasar, A., Bilgili, M., & Simsek, E. (2012). Water Demand Forecasting Based on Stepwise Multiple Nonlinear Regression Analysis. Arabian Journal for Science and Engineering, 37(8), 2333-2341. DOI: 10.1007/s13369-012-0309-z
• Yurdusev, M. A. & Firat, M., (2009). Adaptive neuro fuzzy inference system approach for municipal water consumption modeling: An application to Izmir, Turkey. Journal of Hydrology, 365(3-4), 225-234. DOI: 10.1016/j.jhydrol.2008.11.036
• Zubaidi, S L., Al-Bugharbee, H., Muhsen, Y R., Hashim, K., Alkhaddar, R. & Hmeesh, W H. (2019). The Prediction of Municipal Water Demand in Iraq: A Case Study of Baghdad Governorate. 2019 12th International Conference on Developments in eSystems Engineering (DeSE), Kazan, Russia, 07-10 October 2019, 274-277. DOI: 10.1109/dese.2019.00058
• Zubaidi, S L., Kot, P., Alkhaddar, R., Abdellatif, M. & Al- Bugharbee, H. (2018). Short-Term Water Demand Prediction in Residential Complexes: Case Study in Columbia City, USA., 11th International Conference on Developments in eSystems Engineering (DeSE), 02-05 September 2018, Cambridge, UK, 31-35, DOI: 10.1109/dese.2018.00013.