Multi-objective Optimization of Sensor Placement to Detect Contamination in Water Distribution Networks

Author(s):  
Dolores Margarida ◽  
Carlos Henggeler Antunes
2021 ◽  
Vol 218 ◽  
pp. 18-31
Author(s):  
Douglas F. Surco ◽  
Diogo H. Macowski ◽  
Flávia A.R. Cardoso ◽  
Thelma P.B. Vecchi ◽  
Mauro A.S.S. Ravagnani

2020 ◽  
Vol 20 (7) ◽  
pp. 2630-2647
Author(s):  
Mohammad Solgi ◽  
Omid Bozorg-Haddad ◽  
Hugo A. Loáiciga

Abstract Intermittent operation of water distribution networks (WDNs) is an undesirable yet inevitable strategy under some circumstances such as droughts, development, electricity blackouts, and water pollution, mostly in developing countries. Intermittent utilization of WDNs poses several disadvantages encompassing water quality degradation, deterioration of the water-distribution system, and extra operational and maintenance costs due to frequently interrupted supply, unfair water distribution among consumers, and reduction of system serviceability. This paper proposes a multi-objective optimization model to address the negative consequences of intermittent water shortages. The model is intended to maximize the quantitative and qualitative reliability and the fairness in water supply, and to minimize the frequency of supply interruption. The developed model also considers pragmatic limitations, water quality, water pressure, and supply reservoir's constraints to plan the operation of intermittent water distribution systems under water shortage. The model's efficiency is tested with a WDN in Iran and compared with a standard operation policy (SOP) for water distribution. According to the evaluated efficiency criteria concerning reliability, resiliency, and vulnerability of water quality and quantity of water supply, the developed model is superior to the SOP rule and improves the performance of the network under intermittent operation. In addition, the results demonstrate there is a tradeoff between the uniformity of water distribution and the frequency of supply interruption that shows operators’ and customers’ conflicting priorities.


Water ◽  
2021 ◽  
Vol 13 (12) ◽  
pp. 1625
Author(s):  
Andrea Ponti ◽  
Antonio Candelieri ◽  
Francesco Archetti

The sensor placement problem is modeled as a multi-objective optimization problem with Boolean decision variables. A new multi objective evolutionary algorithm (MOEA) is proposed for approximating and analyzing the set of Pareto optimal solutions. The evaluation of the objective functions requires the execution of a hydraulic simulation model of the network. To organize the simulation results a data structure is proposed which enables the dynamic representation of a sensor placement and its fitness as a heatmap. This allows the definition of information spaces, in which the fitness of a placement can be represented as a matrix or, in probabilistic terms as a histogram. The key element in the new algorithm is this probabilistic representation which is embedded in a space endowed with a metric based on a specific notion of distance. Among several distances between probability distributions the Wasserstein (WST) distance has been selected: WST has enabled to derive new genetic operators, indicators of the quality of the Pareto set and criteria to choose among the Pareto solutions. The new algorithm has been tested on a benchmark water distribution network with two objective functions showing an improvement over NSGA-II, in particular for low generation counts, making it a good candidate for expensive black-box multi-objective optimization


Water ◽  
2019 ◽  
Vol 11 (10) ◽  
pp. 2018
Author(s):  
Jimmy H. Gutiérrez-Bahamondes ◽  
Yamisleydi Salgueiro ◽  
Sergio A. Silva-Rubio ◽  
Marco A. Alsina ◽  
Daniel Mora-Meliá ◽  
...  

Efficient design and management of water distribution networks is critical for conservation of water resources and minimization of both energy requirements and maintenance costs. Several computational routines have been proposed for the optimization of operational parameters that govern such networks. In particular, multi-objective evolutionary algorithms have proven to be useful both properly describing a network and optimizing its performance. Despite these computational advances, practical implementation of multi-objective optimization algorithms for water networks is an abstruse subject for researchers and engineers, particularly since efficient coupling between multi-objective algorithms and the hydraulic network model is required. Further, even if the coupling is successfully implemented, selecting the proper set of multi-objective algorithms for a given network, and addressing the quality of the obtained results (i.e., the approximate Pareto frontier) introduces additional complexities that further hinder the practical application of these algorithms. Here, we present an open-source project that couples the EPANET hydraulic network model with the jMetal framework for multi-objective optimization, allowing flexible implementation and comparison of different metaheuristic optimization algorithms through statistical quality assessment. Advantages of this project are discussed by comparing the performance of different multi-objective algorithms (i.e., NSGA-II, SPEA2, SMPSO) on case study water pump networks available in the literature.


Sign in / Sign up

Export Citation Format

Share Document