Abstract
Wireless Sensor and Actor Networks (WSANs) are critical for industrial automation in the context of Industry 4.0, yet the optimal placement of actors to ensure connectivity and coverage remains an NP-hard problem. This study addresses the Actor Placement Problem (APP) in constrained, two-zone industrial environments. We propose a hybrid system, the PSO-HC-DGA hybrid system, which integrates Particle Swarm Optimization (PSO), Hill Climbing (HC), and the Distributed Genetic Algorithm (DGA). We evaluate four crossover methods (UNDX, SPX, BLX-α, and psBLX) combined with two actor replacement methods (RIWM and FC-RDVM) for small-, medium-, and large-scale scenarios. The simulation results demonstrate that psBLX is the most effective of the four crossover methods. In the small-scale scenario, it achieved better load balancing combined with RIWM, while in the medium-scale scenario, psBLX achieved full sensor coverage with RIWM and good load balancing with FC-RDVM. For the large-scale scenario, we compared the performance of the implemented hybrid system with that of a PSO system. The hybrid system showed 100% connectivity and achieved better sensor coverage than the PSO system. The Kruskal-Wallis test confirmed that the performance differences in load balancing were statistically significant. We conclude that the proposed hybrid system using psBLX enables robust and high-performance deployment in two-zone industrial WSANs.