Energy Optimization in Smart Agriculture Wireless Sensor Networks Based on the RK4PSO Algorithm

Inspired by the particle swarm optimization-based low-energy adaptive hierarchy of clusters (PSO-LEACH) protocol, this article proposes a particle swarm optimization algorithm with fourth-order Runge-Kutta (RK4PSO) algorithm, aimed at optimizing cluster head (CH) selection within the PSO-LEACH protocol, thereby reducing network energy consumption (EC). First, a fourth-order Runge-Kutta numerical integration method is introduced to reconstruct the particle motion model, significantly improving the accuracy of particle position and velocity estimation, thus enhancing the global search capability of the algorithm. Second, a population evolution mechanism based on an elite retention strategy is designed, with dynamic integration of the global optimal solution to guide the population’s iterative direction, thereby improving the algorithm’s convergence speed. Furthermore, adaptive individual and social cognitive coefficients are employed to adjust the particle weight distribution, further improving its robustness. Finally, simulation results demonstrate that the RK4PSO-LEACH protocol significantly improves the compactness of the cluster structure, reduces intracluster communication distance and lowers communication EC. Under the condition of a packet size of 3500 bits, the network lifetime before the death of the first node is extended by 103% and 56.4% compared to PSO-LEACH and traditional LEACH protocols, respectively, thus validating the significant advantages of the proposed algorithm in optimizing energy efficiency in wireless sensor networks (WSNs).