Stochastic sampling design for water distribution model calibration

Behzadian, Kourosh ORCID:, Kapelan, Zoran, Savic, Dragan and Ardeshir, Abdollah (2007) Stochastic sampling design for water distribution model calibration. In: Water Management Challenges in Global Change, 4 September 2007, London, UK.

[thumbnail of PDF/A]
A.Behzadian et al CCWI 2007 witout Header.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (1MB) | Preview


A novel approach to determine optimal sampling locations under the parameter of uncertainty
in a water distribution system (WDS) for the purpose of its hydraulic model calibration is presented. The
problem is formulated as a multi-objective optimisation problem under calibration parameter uncertainty. The
objectives are to maximise the calibrated model accuracy and to minimise the number of sampling devices as
a surrogate of sampling design cost. Model accuracy is defined as the average of normalised traces of model
prediction covariance matrices, each of which is constructed from a randomly generated sample of calibration
parameter values. To resolve the computational time issue, the optimisation problem is solved using a multiobjective
genetic algorithm and adaptive neural networks (MOGA-ANN). The results show that significant
computational savings can be achieved by using MOGA-ANN compared to the Monte Carlo Simulation
(MCS) model or the GA model based on all full fitness evaluations without significant decrease in the final
solution accuracy.

Item Type: Conference or Workshop Item (Paper)
ISBN: 978-041545415-5
Keywords: Leak Detection; Leakage; Water Distribution Systems
Subjects: Computing
Depositing User: Kourosh Behzadian
Date Deposited: 25 Sep 2023 10:52
Last Modified: 25 Sep 2023 10:52


Downloads per month over past year

Actions (login required)

View Item View Item