A simulation-optimization approach for reducing background leakage in water systems

Abstract

This paper forms an entry to the battle of background leakage assessment for water networks (BBLAWN). The proposed methodology for this problem is a sequential assessment of intervention types. In an initial stage, a diagnosis of the network is performed through simulating its hydraulic behaviour with no infrastructure or operational modifications. An optimization technique is developed to recommended improvements of a particular type, such as pipes to replace. These techniques are applied sequentially to yield a list of suggested improvements for the network. Our approach requires a hydraulic model that simulates background leakage, custom implementations of heuristic algorithms and optimization solvers.