Assessing and modelling the water quality in a water distribution system (WDS) are highly important to ensure a reliable supply with sufficient water quality. Owing to the high computational burden of such an analysis, frequently, simplifications are required or surrogate models are used (e.g., reducing the level of detail of the network model), neglecting significant aspects. For large (currently all-pipe) models and/or recurrent simulations (e.g., integrated studies, sensitivity analysis, deep uncertainty analysis, design, and optimization), the computational burden further increases. In this study, a novel complex network analysis-based approach for high-computational efficiency water quality assessment in a WDS is developed and comprehensively tested (R² values in comparison with state-of-the-art nodal water qualities in median of 0.95 are achieved). The proposed model is successfully utilized in a design study to identify the design solutions exceeding water quality thresholds with a correct identification rate between 96% and 100%. The computational efficiency is determined to be a factor 4.2e-06 less than that of state-of-the-art models. Therefore, the proposed model significantly improves the water quality assessment for such tasks in large WDSs.
Keywords: Edge betweenness centrality; mathematical graphs; network dispersion.
Copyright © 2021. Published by Elsevier Ltd.