Prediction of non-revenue water ratio in water distribution systems

Abstract

In the evaluations of water distribution systems (WDSs) in terms of water loss and perfor-mance, the Non-Revenue Water ratio (NRW) stands out as one of the most important pa-rameters. Within the scope of this study, in order to predict the NRW ratio, a large number of models at different variable combinations were generated using the Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN) methods. The performance of the models formed has been evaluated by taking R2, RMSE, MAE, SI, and Bias criteria as references. According to the study results, the model performances increase with the number of inputs in general, and the ANN models are more successful than ANFIS. Considering the modeling, the best-performing combination through the ANN method is WSQ-NJ-NL-NF, this one is the WSQ-NJ-NL-MPD combination in the ANFIS method which has three vari-ables common. As a result, using variables common is significant for NRW predictions. On the other hand, NRW prediction performances need to improve by taking different variable combinations and methodological approaches into account, according to the ANFIS model results.

Keywords

• ANFIS
• ANN
• Modeling
• Non Revenue Water
• Water Distribution Systems

References

1. REFERENCES
2. [1] Kanakoudis V, Tsitsifli S. Water volume vs. revenues-oriented water balance calculation for urban water networks: The “Minimum Charge Difference” component makes a difference! Available at: https://www.researchgate.net/profile/Vasilis-Kanakoudis/publication/270645306_Water_volume_vs_revenues_oriented_water_balance_calculation_for_urban_water_networks_the_Minimum_Charge_Difference_component_makes_a_difference/links/54d3e9180cf246475804046c/Water-volume-vs-revenues-oriented-water-balance-calculation-for-urban-water-networks-the-Minimum-Charge-Difference-component-makes-a-difference.pdf. Accessed on May 15, 2024.
3. [2] Van Den Berg C. Drivers of non-revenue water: A cross-national analysis. Util Policy 2015;36:71–78. [CrossRef]
4. [3] Rajani B, Kleiner Y. Comprehensive review of structural deterioration of water mains: Physically based models. Urban Water 2001;3:151–164. [CrossRef]
5. [4] González-Gómez F, Martínez-Espiñeira R, García-Valiñas MA, García-Rubio M. A. Explanatory factors of urban water leakage rates in Southern Spain. Utilities Policy 2012;22:22–30. [CrossRef]
6. [5] Tabesh M, Asadiyami Yekta AH, Burrows R. An integrated model to evaluate losses in water distribution systems. Water Resour Manag 2009;23:477–492. [CrossRef]
7. [6] Tabesh M, Roozbahani A, Roghani B, Faghihi NR, Heydarzadeh R. Risk assessment of factors influencing non-revenue water using bayesian networks and fuzzy logic. Water Resour Manage 2018;32:3647–3670. [CrossRef]
8. [7] González-Gómez F, García-Rubio MA, Guardiola J. Why is non-revenue water so high in so many cities? Int J Water Resour Dev 2011;27:345–360. [CrossRef]

9. [8] Güngör-Demirci G, Lee J, Keck J, Guzzetta R, Yang P. Determinants of non-revenue water for a water utility in California. J Water Supply Res Technol AQUA 2018;67:270–278. [CrossRef]
10. [9] Şişman E, Kızılöz B. Trend-risk model for predicting non-revenue water: An application in Turkey. Util Policy 2020;67:101137. [CrossRef]
11. [10] Kizilöz B, Şişman E. A new performance analysis model for urban water supply systems evaluation. Desalin Water Treat 2021;235:177–192. [CrossRef]
12. [11] Kizilöz B, Şişman E. Exceedance probabilities of non-revenue water and performance analysis. Int J Environ Sci Technol 2021;18:2559–2570. [CrossRef]
13. [12] Jang D, Choi G. Estimation of non-revenue water ratio using MRA and ANN in water distribution networks. Water 2018;10:2. [CrossRef]
14. [13] Jang D, Choi G. Estimation of non-revenue water ratio for sustainable management using artificial neural network and Z-score in Incheon, Republic of Korea. Sustainability 2017;9:1933. [CrossRef]
15. [14] Kiziloz B, Şişman E. Estimation of non-revenue water rate using artificial neural networks and adaptive neuro fuzzy inference systems. In Proceedings of the 4. Eurasian Conference on Civil and Environmental Engineering; 2019 Jun 17–18; İstanbul, Türkiye. ECCOCE; 2019. p. 1175–1186.
16. [15] Şişman E, Kizilöz B. Artificial neural network system analysis and Kriging methodology for estimation of non-revenue water ratio. Water Sci Technol Water Supply 2020;20:1871–1883. [CrossRef]
17. [16] Kızılöz B, Şişman E. Prediction models for non-revenue water ratio. Ömer Halisdemir Univ J Eng Sci 2021;10:276–283.
18. [17] Kızılöz B, Şişman E. Non-revenue water ratio prediction with serial triple diagram model. Water Supply 2021;21:4263–4275. [CrossRef]
19. [18] ISU. 2018 faaliyet raporu. Available at: https://www.isu.gov.tr/component/GetFiles.ashx?t=2&FileName=7fcb77ca-f3d2-4cf8-b1bd-1e930bdde327.pdf. Accessed on May 15, 2024.
20. [19] Şen Z, Şişman E, Kizilöz B. A new innovative method for model efficiency performance. Water Supply 2022;22:589–601. [CrossRef]
21. [20] Şen Z. Fuzzy Logic and Hydrological Modeling. 1st ed. Boca Raton: CRC Press; 2009. [CrossRef]
22. [21] Kizilöz B. Prediction model for the leakage rate in a water distribution system. Water Supply 2021;21:4481–4492. [CrossRef]
23. [22] Kizilöz, B. Prediction of daily failure rate using the serial triple diagram model and artificial neural network. Water Supply 2022;22:7040–7058. [CrossRef]