Hybrid EECS Framework: Reinforcement Learning-Driven Collaborative Sensing with Grey Wolf Optimized Routing for Energy-Efficient Wireless Sensor Networks

Wireless Sensor Networks (WSNs) play a pivotal role in monitoring and data collection across diverse application domains. As these networks scale in size and complexity, the demand for intelligent and energy-efficient sensing mechanisms becomes increasingly critical. This paper presents an enhanced Energy-Efficient Collaborative Sensing (EECS) framework for WSNs that integrates game-theoretic decision making with reinforcement learning and Grey Wolf Optimization (GWO)-based routing. The proposed model is designed to minimize energy consumption while maintaining high quality of service through adaptive and intelligent cooperation among sensor nodes. A key contribution of this work is the Selection Propensity Index (SPI), which guides the optimal selection of sensing nodes based on their dynamic utility and network conditions. In addition, the framework incorporates a Distributed Anticipatory Time-slot Allocation (DATA) algorithm based on reinforcement learning to enable efficient and collision-aware time-slot selection for collaborative communication. To further enhance network performance, GWO-driven neighbor selection is employed to achieve energy-aware and distance-efficient routing. Extensive simulations demonstrate that the proposed hybrid EECS framework significantly outperforms existing methods in terms of energy efficiency, packet drop ratio, throughput, and network stability. Specifically, the model achieves up to 202% improvement in network lifetime, approximately 30% higher throughput, and more than 60% faster operation under full-load conditions