Adaptive Hybrid Sperm Swarm Optimization and Genetic Algorithm (aHSSOGA) in clustering of Wireless Sensor Networks

Abstract Wireless Sensor Networks face significant energy constraints that directly impact network lifetime and data collection efficiency. While Low-Energy Adaptive Clustering Hierarchy (LEACH) has been foundational since the early 2000s, persistent challenges including isolated nodes and energy hotspots limit its effectiveness. This work proposes adaptive Hybrid Sperm Swarm Optimization and Genetic Algorithm (aHSSOGA), a metaheuristic approach that combines adaptive parameter tuning with refined objective functions to optimize cluster head selection. Unlike conventional methods, aHSSOGA dynamically adjusts crossover and mutation probabilities based on operator performance and incorporates velocity dampening to balance exploration and exploitation. The five refined objective functions specifically target isolated node and hotspot mitigation. Implemented with an enhanced LEACH re-clustering mechanism that reduces overhead, aHSSOGA demonstrates substantial improvements over LEACH, HSAPSO, HFAPSO, HGWOSFO, and standard HSSOGA across six key performance metrics: average residual energy (5.55% to 9.12% improvement), network lifetime (7.18% to 19.26% improvement), re-clustering frequency (93.5% reduction), total data delivery (11.98% to 32.36% improvement), network throughput, and end-to-end delay. These results confirm that adaptive hybrid metaheuristics with refined objectives provide a practical and effective solution for extending WSN operational lifespan.