3D genetic algorithms for underwater sensor networks. (22nd May 2013)

• Record Type: Journal Article
• Authors: Zou, Jianmin; Gundry, Stephen; Kusyk, Janusz; Uyar, M. Ümit; Sahin, Cem Safak
• Is Part Of: International journal of ad hoc and ubiquitous computing. Volume 13:Number 1(2013)
• Page Start: 10
• Page End: 22
• Publication Date: 2013-05-22
• Subjects: AUV -- autonomous underwater vehicles -- UWSN -- underwater sensor networks -- spatial node distribution -- genetic algorithms -- 3D topology control -- artificial intelligence -- network resilience -- simulation -- volumetric spatial control; Ubiquitous computing -- Periodicals; Embedded computer systems -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; Wireless communication systems -- Periodicals; Computer architecture -- Periodicals; 004.2
• Languages: English
• ISSNs: 1743-8225

Abstract

We introduce a genetic algorithm–based topology control mechanism, named 3D–GA, for Autonomous Underwater Vehicles (AUVs) operating in Underwater Sensor Networks (UWSNs). Using limited information collected from a node's local neighbours, 3D–GA runs autonomously at each AUV and provides guidance for its speed and direction towards a uniform spatial distribution while maintaining network connectivity. Imprecise and limited neighbourhood knowledge could potentially disrupt convergence towards a uniform and stable spatial coverage. We demonstrate that AUVs running our 3D–GA create a highly resilient network that can adapt to changing conditions such as the addition, loss or malfunction of number of AUVs. We also show that the ambiguity in detecting neighbours' exact locations does not prevent 3D–GA from achieving a uniform coverage but requiring AUVs travel longer distances to stabilise. Our simulation software results verify that 3D–GA is an effective tool for providing a robust solution for volumetric spatial control of AUVs in UWSNs.