Swarm intelligence based localization in wireless sensor networks

Abstract

Wireless sensor networks (WSNs) increasingly penetrate our everyday life and are already employed in a wide range of application areas, such as habitat monitoring, precision agriculture, home automation, and logistics. Localization of sensor nodes in a network is a highly desirable capability in all these applications. The ability to precisely determine the position of nodes in sensor networks enables many new upcoming technologies such as robotics, automated driving, traffic monitoring, or inventory management. For all these applications, different requirements regarding accuracy, reliability, and speed of position estimation are posed. WSNs is a field with many optimization problems that have to be addressed. Optimization of power consumption of nodes in WSNs is the main problem that have to be addressed. WSN node has a limited power backup so this makes it a very critical issue. This paper formulates the concern on how WSNs can take advantage of the computational intelligent techniques using multi-objective particle swarm optimization (MOPSO), with an overall aim of concurrently minimizing localization time, energy consumption during localization, and maximizing the number of nodes fully localized. The localization method optimized the power consumption during a Trilateration-based localization (TBL) procedure, through the adjustment of sensor nodes' output power levels. Finally, a parameter study of the applied PSO variant for WSN localization is performed, leading to results that display up to 32% better algorithmic improvements than the baseline outcomes in the measured objectives.