3rd International Workshop on Software Defined Sensor Networks

Research Article

Sensors Placement in Water Distribution Systems Based on Co-evolutionary Optimization Algorithm

Download515 downloads
  • @INPROCEEDINGS{10.4108/icst.iniscom.2015.258402,
        author={Chengyu Hu and Dijun Tian and Chao Liu and Xuesong Yan},
        title={Sensors Placement in Water Distribution Systems Based on Co-evolutionary Optimization Algorithm},
        proceedings={3rd International Workshop on Software Defined Sensor Networks},
        publisher={ICST},
        proceedings_a={SDSN},
        year={2015},
        month={4},
        keywords={sensors placement water distribution systems co-evolutionary optimization algorithm},
        doi={10.4108/icst.iniscom.2015.258402}
    }
    
  • Chengyu Hu
    Dijun Tian
    Chao Liu
    Xuesong Yan
    Year: 2015
    Sensors Placement in Water Distribution Systems Based on Co-evolutionary Optimization Algorithm
    SDSN
    ICST
    DOI: 10.4108/icst.iniscom.2015.258402
Chengyu Hu1, Dijun Tian1, Chao Liu1, Xuesong Yan1,*
  • 1: China university of geosciences
*Contact email: yanxuesongcug@gmail.com

Abstract

In recent years, water pollution incidents happen frequently, causing serious disasters and society impact. It is advocated that water quality monitoring sensors shall be deployed in water distribution systems to realize the real-time pollution detection such that we can effectively detect the water pollution event to reduce the risk. However, how to deploy water quality sensors in water distribution systems (WDS) is a non-trivial and challenging task. Sensors placement in WDS is characterized by its extremely high computation complexity, uncertainty because of large-scale water distribution system and dynamic water demand by consumers. Aiming to minimize the average time of detection over all contamination events by placing a limited number of sensors into the water network, we have developed a co-evolution optimization algorithm, which using multiple populations to evolve simultaneously. Results indicate that our proposed algorithm performs better comparing to genetic algorithm and particle swarm algorithm.