Adaptive MARL-Assisted Hybrid Bat-Artificial Bee Colony Optimization for Energy-Efficient Clustering and Routing in IoT-Enabled Wireless Sensor Networks

Energy efficiency remains a major challenge in IoT-enabled wireless sensor networks because sensor nodes operate with limited battery capacity and are often deployed in environments where battery replacement is impractical. Existing clustering and routing protocols frequently optimize cluster-head selection and routing separately, leading to uneven energy consumption, premature node failure, increased routing overhead, and reduced network reliability. This paper proposes an Adaptive Multi-Agent Reinforcement Learning-Assisted Hybrid Bat-Artificial Bee Colony (MARL-BA-ABC) framework for joint cluster-head selection and routing optimization in IoT-enabled wireless sensor networks. The proposed framework combines the Bat Algorithm for local exploitation, the Artificial Bee Colony algorithm for global exploration, and Multi-Agent Reinforcement Learning for adaptive routing. Cluster-head selection and routing are jointly optimized using residual energy, communication distance, traffic load, node density, and link quality. A multi-objective optimization model is formulated to minimize energy consumption, end-to-end delay, routing overhead, and load imbalance while improving packet delivery ratio, residual energy preservation, and network lifetime. Simulation results show that the proposed MARL-BA-ABC framework outperforms Low-Energy Adaptive Clustering Hierarchy (LEACH), Hybrid Energy-Efficient Distributed Clustering (HEED), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Bat Algorithm (BA), and Artificial Bee Colony (ABC), achieving a First Node Death of 2200 rounds, residual energy of 1.32 J, packet delivery ratio of 98.1%, throughput of 410 kbps, and average end-to-end delay of 7.4 ms.