Estimation of NRW using Main Parameters of Water Distribution Systems

8 pages•Published: September 20, 2018

Dongwoo Jang, Gyewoon Choi, Jintak Choi and Hyoseon Park

Abstract

The non-revenue water (NRW) is the water losses from unbilled authorized consumption, obvious losses and actual losses among the total amount of water supply (tap water supplied from water purification plants) in the water distribution systems. Various studies analyze data using statistical methods and identify the relationship as a method to estimate the NRW. For estimating the NRW of the water distribution systems, selected main parameters were used to this study. The main parameters were used to ANN model simulation, and compared to observed NRW data to determine the accuracy of NRW estimation. In the results, the method using artificial neural network was found to be more accurate in estimating the NRW than multiple regression analysis. In this study, the effective parameters of the NRW were determined, especially physical and operational parameters have high relationship to the NRW estimation.

Keyphrases: non revenue water, statistical analysis, water distribution systems

In: Goffredo La Loggia, Gabriele Freni, Valeria Puleo and Mauro De Marchis (editors). HIC 2018. 13th International Conference on Hydroinformatics, vol 3, pages 959-966.

Links:	https://easychair.org/publications/paper/GGxZ
	https://doi.org/10.29007/1gpk

BibTeX entry

@inproceedings{HIC2018:Estimation_NRW_using_Main,
  author    = {Dongwoo Jang and Gyewoon Choi and Jintak Choi and Hyoseon Park},
  title     = {Estimation of NRW using Main Parameters of Water Distribution Systems},
  booktitle = {HIC 2018. 13th International Conference on Hydroinformatics},
  editor    = {Goffredo La Loggia and Gabriele Freni and Valeria Puleo and Mauro De Marchis},
  series    = {EPiC Series in Engineering},
  volume    = {3},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2516-2330},
  url       = {/publications/paper/GGxZ},
  doi       = {10.29007/1gpk},
  pages     = {959-966},
  year      = {2018}}

Download PDF Open PDF in browser