Water Contaminants Detection Using Sensor Placement Approach in Smart Water Networks

Shahra, Essa and Wu, Wenyan (2020) Water Contaminants Detection Using Sensor Placement Approach in Smart Water Networks. Journal of Ambient Intelligence and Humanized Computing. pp. 1-16. ISSN ISSN 1868-5137

[img]
Preview
Text
AIHCJ_paper_final author version.pdf - Accepted Version

Download (2MB)

Abstract

Incidents of water pollution or contamination have occurred repeatedly in recent years, causing significant disasters and negative health impacts. Water quality sensors need to be installed in the water distribution system (WDS) to allow real-time water contamination detection to reduce the risk of water contamination. Deploying sensors in WDS is essential to monitor and detect any pollution incident at the appropriate time. However, it is impossible to place sensors on all nodes of the network due to the relatively large structure of WDS and the high cost of water quality sensors. For that, it is necessary to reduce the cost of deployment and guarantee the reliability of the sensing, such as detection time and coverage of the whole water network. In this paper, a dynamic approach of sensor placement that uses an Evolutionary Algorithm (EA) is proposed and implemented. The proposed method generates a multiple set of water contamination scenarios in several locations selected randomly in the WDS. Each contamination scenario spreads in the water networks for several hours, and then the proposed approach simulates the various effect of each contamination scenario on the water networks. On the other hand, the multiple objectives of the sensor placement optimization problem, which aim to find the optimal locations of the deployed sensors, have been formulated. The sensor placement optimization solver, which uses the EA, is operated to find the optimal sensor placements. The effectiveness of the proposed method has been evaluated using two different case studies on the example of water networks: Battle of the Water Sensor Network (BWSN) and another real case study from Madrid (Spain). The results have shown the capability of the proposed method to adapt the location of the sensors based on the numbers and the locations of contaminant sources. Moreover, the results also have demonstrated the ability of the proposed approach for maximising the coverage of deployed sensors and reducing the time to detect all the water contaminants using a few numbers of water quality sensors

Item Type: Article
Identification Number: https://doi.org/10.1007/s12652-020-02262-x
Date: 25 June 2020
Uncontrolled Keywords: Water distributed system, Water quality monitoring, water contaminants detection, Sensor placement, Optimisation, Evolutionary algorith
Subjects: G700 Artificial Intelligence
H100 General Engineering
H600 Electronic and Electrical Engineering
Divisions: Faculty of Computing, Engineering and the Built Environment
Depositing User: Wenyan Wu
Date Deposited: 29 Jun 2020 08:35
Last Modified: 29 Jun 2020 08:35
URI: http://www.open-access.bcu.ac.uk/id/eprint/9370

Actions (login required)

View Item View Item

Research

In this section...