Research on Coverage Optimization in Wireless Sensor Networks Based on an Improved Sparrow Search Algorithm.

Optimal node deployment in Wireless Sensor Networks (WSNs) is crucial for maximizing monitoring coverage. However, traditional metaheuristics like the Sparrow Search Algorithm (SSA) often suffer from premature convergence and redundant clustering, creating severe coverage holes. To address this, we introduce the Density-Aware Repulsive Sparrow Search Algorithm (DAR-SSA). Integrating electrostatic principles, DAR-SSA calculates a local density-based repulsive force vector to actively disperse nodes from high-density clusters. This physics-guided approach, combined with a dynamic explorer-exploiter allocation rule, ensures a computationally efficient balance between global and local search phases. Evaluated via a probabilistic sensing model, DAR-SSA significantly outperforms standard SSA, its variants (EFSSA, EASOA), and classical algorithms (PSO, GWO). In high-density urban deployments, DAR-SSA achieves a 95.25% effective coverage rate, compared to SSA's 76.74%. In low-density environments, coverage reaches 97.12%. Validated by Wilcoxon rank-sum tests, DAR-SSA proves to be a robust, efficient framework for mitigating spatial redundancy and maximizing WSN sensing coverage.