Optimizing IoT Wireless Sensor Networks: A Comparative Analysis of Particle Swarm Optimization (PSO) and Genetic Algorithms (GA)

Abstract

The IoT can be defined as a system of various types of computing and digital devices, machines, objects, animals, and humans that are connected through networks to send data without the need for direct person-to-person or computer-to-person interfaces. Every component in this structure is given a unique identity. While under the domain of IoT, WSN serves as a wireless sensor network that does not have an established infrastructure but consists of many wireless sensors for surveillance over systems, the environment, and the physical world. Because of its versatile usage like surveillance and environmental monitoring, Wireless Sensor Networks (WSNs) are vital in many applications. The performance of these networks is largely dependent on how sensor nodes are distributed across the area to provide good coverage and connectivity. In this paper, we propose a new method for node placement optimization in WSNs, which tries to solve the problem of coverage holes at the stage of initial deployment. Genetic Algorithms (GA) and Particle Swarm Optimization (PSO) are implemented using MATLAB to deal with the problem's complex and non-linear nature. These algorithms help find optimal node positions, thus improving coverage while ensuring no coverage gaps occur. A way to achieve this is through iterations, which involve fitness evaluation, selection of promising solutions, and genetic operators like crossover and mutation or position updates for PSO to investigate and improve the final solution. The simulation results mentioned in this paper demonstrate the usefulness of those methods, displaying major increases in coverage and the removal of all gaps that could appear in the initial deployment. This research contributes to the field of wireless sensor network optimization, specifically addressing coverage issues using GA and PSO algorithms …