KIPSO: Kalman-Inertia Particle Swarm Optimization Approach for Wireless Sensor Nodes Deployment

Random deployment of wireless sensor nodes within a monitoring area introduces several challenges, including blind spot formation and coverage redundancy.Given that coverage efficiency fundamentally determines the performance efficacy of a Wireless Sensor Network (WSN), formulating an optimization algorithm that effectively balances the conflicting objectives of exploration and exploitation presents a significant challenge.Particle Swarm Optimization (PSO) and its variants have been widely investigated for this purpose, with considerable focus directed at optimizing convergence control parameters.To address the convergence challenge innovatively, this work proposes the Kalman-Inertia Particle Swarm Optimization (KIPSO) algorithm.KIPSO leverages the Kalman filter estimation accuracy to dynamically adjust particle inertia weights during the PSO process.This adaptation enhances both the convergence rate and the precision of the solutions obtained.The experimental and analytical work performed in this study demonstrates that by dynamically adjusting inertia, KIPSO is capable of avoiding local minima and improving node placement, resulting in better coverage and reduced interference compared to methods such as PSO and VFPSO.This leads to enhanced overall network coverage, reduced energy consumption, and prolonged network lifetime.