Integrating evolution strategies and genetic algorithms with agent-based modeling for flushing a contaminated water distribution system

Abstract

Water utilities can prepare for water distribution iiazards, sucii as tiie presence of contaminants in the pipe networi< and faiiure of physical components, in contamination events, the compiex interactions among managers' operationai decisions, consumers' water consumption choices, and the hydrauiics and contaminant transport in the water distribution system may infiuence the contaminant piume so that a typicai engineering modei may not properiy predict pubiic heaith consequences. A compiex adaptive system (CAS) approach couples engineering modeis of a water distribution system with agent-based models of consumers and public officiais. Deveiopment of threat management strategies, which prescribe a set of actions to mitigate pubiic heaith consequences, is enabled through a simulation-optimization framework that coupies evoiutionary aigorithms with the CAS model. Evoiution strategies and genetic aigorithm-based approaches are deveioped and compared for an illustrative case study to identify a fiushing strategy for opening hydrants to minimize the number of exposed consumers and maintain acceptable levels of service in the networi<.

Contamination event diagnosis in drinking water networks: A review

“…Different impact metrics used in the literature include: Minimization of the number of contaminated nodes, using a function that defines whether a node is contaminated or not based on a threshold applied to the contaminant concentration, or minimization of the total contaminant concentration at nodes (Afshar & Najafi, 2014;Bashi-Azghadi et al, 2017;Moghaddam et al, 2020); Minimization of the number of exposed individuals, using a function that calculates the number of people affected at a node based on the population at the node (Zechman, 2013;Moghaddam et al, 2022); Minimization of the volume of contaminated water consumed, using a function of the demand when the concentration at a node is above a threshold (Preis & Ostfeld, 2008b;Guidorzi et al, 2009;Bashi-Azghadi et al, 2017;? ); Maximization of the flushed contamination mass by the hydrant set, using a function that calculates the contaminant mass that exits the network from hydrant flushing locations (Fasaee et al, 2020).…”

Artificial intelligence in the water domain: Opportunities for responsible use

“…A few articles combined the quantitative and physical engineering models of some socio-physical system with models that simulate the behavior of the human actors within the system. In the context of the detection and prevention of water contamination, Zechman (2013) developed a model that combined agent-based modeling with evolutionary algorithms to develop and evaluate different threat management strategies. Mewes and Schumann (2019) developed an agent-based irrigation planning model with a machine learning-based training component that is able to identify the current hydrological situation and adapt irrigation and cropping schemes accordingly within the model at runtime.…”

A Smart Water Grid for Micro-Trading Rainwater: Hydraulic Feasibility Analysis

“…Other agent-based models couple a population of agents with the hydraulic simulation of a water distribution system to evaluate how network flows are impacted by changing demands. Models capture water use changes during a water supply contamination event, based on exposure to the contaminant, communication from public officials, and social influence of peers [12,13,[72][73][74][75][76][77]. Another set of studies uses agent-based modeling coupled with hydraulic simulation to evaluate how flows in a reclaimed water network and a potable water network change as customers adopt or resist water reuse programs [14,27,78].…”