Wireless sensor network coverage optimization based on the innovative enhanced whale optimization algorithm

Abstract In Wireless Sensor Networks (WSNs), optimizing network coverage is crucial for improving performance in applications such as environmental monitoring, surveillance, and socio-economic cyber systems. Although the Whale Optimization Algorithm (WOA) has demonstrated potential as a swarm-based optimization technique, it suffers from limitations such as inadequate exploration capability and a tendency to become trapped in local optima, particularly under random sensor-node deployment, resulting in suboptimal coverage. To address these challenges, this paper proposes the Innovative Enhanced Whale Optimization Algorithm (IEWOA), which aims to improve WSN coverage performance. The proposed enhancements include Sobol sequence-based population initialization to improve population diversity, a innovative nonlinear convergence mechanism to achieve an effective balance between exploration and exploitation, and the integration of a L $$\acute{e}$$ vy flight strategy to enhance the exploration capability of the algorithm. The performance of IEWOA is benchmarked against the Sine Cosine Algorithm (SCA), Tunicate Swarm Algorithm (TSA), Multi-Verse Optimizer (MVO), Arctic Puffin Optimization (APO), Mirage Search Optimization (MSO), and the original WOA using standard benchmark test functions. Furthermore, all seven algorithms are evaluated across five WSN coverage scenarios involving variations in sensing range, number of sensor nodes, target density, deployment-area size, and large-scale monitoring requirements. In addition, the deployment performance of IEWOA and the comparative algorithms is evaluated under different obstacle environments. Simulation results demonstrate that IEWOA consistently outperforms the other algorithms, achieving a more uniform sensor-node distribution, higher network coverage, and superior convergence performance.