Energy efficiency in Wireless Sensor Networks (WSNs) is a crucial challenge due to the limited power supply of sensor nodes. This paper introduces an AI-driven adaptive clustering mechanism to address this issue, enhancing energy efficiency and prolonging network lifespan. The proposed framework integrates machine learning (ML) techniques with bio-inspired optimization algorithms, such as Genetic Algorithm (GA) and Salp Swarm Optimization (SSO), for dynamic cluster head (CH) selection and adaptive clustering. Unlike traditional protocols like LEACH and HEED, which rely on static or random CH selection, our approach leverages real-time network conditions, node heterogeneity, and energy status to optimize clustering decisions. Simulation results reveal significant improvements in energy consumption, network stability, and scalability. The proposed method reduces total energy consumption by approximately 30% compared to LEACH and 20% compared to HEED. Furthermore, the network lifetime is extended by 25%, and data throughput is increased by 20%. This improvement is achieved through intelligent CH selection, which balances the energy load among nodes and prevents premature node failures. This study highlights the potential of AI-driven optimization for adaptive clustering in WSNs, making it suitable for energy-critical applications such as environmental monitoring, smart cities, and healthcare. By demonstrating the effectiveness of combining ML with bio-inspired algorithms, the proposed method provides a robust solution to the energy depletion challenges in WSNs. Future research will focus on incorporating reinforcement learning and multi-objective optimization to further enhance adaptability and address diverse performance metrics.
Hakkem et al. (Fri,) studied this question.