Energy‐Efficient Cluster Head Selection in Heterogeneous WSNs Using Aquila Optimizer and Fuzzy Logic (AO‐FL)

ABSTRACT Cluster‐based communication is the most widely adopted solution for energy and communication management in heterogeneous wireless sensor networks (HWSNs). However, the efficient selection of cluster heads (CHs) remains a critical challenge due to the dynamic topology and energy limitations inherent in such networks. Existing algorithms like Genetic Algorithms (GAs) and LEACH often face issues such as premature convergence, imbalanced energy usage, and limited adaptability. To address these limitations, this work proposes a hybrid AO‐FL approach that combines the global optimization capability of the Aquila Optimizer (AO) with the adaptive decision‐making of Fuzzy Logic for energy‐efficient CH selection. The fuzzy logic system first shortlists eligible CH candidates based on residual energy, distance to the base station, and current traffic load. The AO then performs a global search to determine optimal CHs from these candidates. Simulation experiments in NS‐2.35 demonstrate that the proposed method significantly improves energy efficiency by 4.29%, throughput by 5.47%, and network lifetime by 1.43% compared to established protocols like SEP, DEEC, Z‐SEP, PSO‐ECSM, and EPOA‐CHS. The results confirm the potential of AO‐FL as a robust and scalable clustering solution for sustainable operation in dynamic, resource‐constrained HWSNs.