Optimizing energy-efficient cluster head selection in wireless sensor networks using a binarized spiking neural network and honey badger algorithm

Abstract

Wireless Sensor Networks (WSNs) play a vitalparton some applications, like environmental monitoring, healthcare, industrial automation. Optimizing the performance of WSN is essential to ensure efficient data delivery while conserving energy resources. This manuscript addresses the challenges of Multi-Objective Cluster Head Selection and Energy-Aware Routing in WSNs through the development of the Binarized Spiking Neural Network optimized with the Honey Badger Algorithm (EACHS-BzSpNNHBA-WSN). The appropriate cluster heads selection is vital for the overall presentation of WSNs, influencing data aggregation, routing, and energy consumption. Conventional approaches often struggle to balance the conflicting objectives of maximizing network lifetime, minimizing energy consumption, and ensuring timely data delivery. Therefore, there is a pressing need for innovative solutions capable of addressing these multi-objective optimization challenges. In this study, the EACHS-BzSpNNHBA-WSN framework is proposed, leveraging the computational power of Binarized Spiking Neural Networks and the optimization capabilities of the Honey Badger Algorithm to identify optimal cluster heads in WSNs. By formulating the cluster head selection as a multi-objective optimization problem, the aim is to achieve robust data delivery while minimizing energy consumption and extending the network lifetime. The proposed framework is implemented in MATLAB platform. The performance assessment is conducted using various metrics, including the number of active nodes, packet drop rate, energy consumption, network lifetime, delay, throughput, packet delivery ratio. Comparative analysis with existing models demonstrates the effectiveness of the EACHS-BzSpNNHBA-WSN approach.