QGFL-TEEN: An Intelligent Hybrid Protocol for Energy-Efficient and Adaptive Routing in Wireless Sensor Networks

Wireless sensor networks (WSNs) have emerged as a promising technology in modern wireless communication systems. These networks have been widely used in real-time applications that require reliable communication along with energy efficiency, which heightens the need for protocols that can provide both stable communication and reduced energy consumption. In essence, traditional hierarchical protocols, such as the threshold-sensitive energy-efficient sensor network (TEEN), have demonstrated effectiveness in lowering redundant transmissions. However, they often suffer limitations in adaptive energy management and the optimal selection of the cluster head (CH). Motivated by this fact, this paper proposes QGFL-TEEN. This new hybrid frame integrates reinforcement learning (RL), genetic algorithms (GAs), and fuzzy logic (FL) with the TEEN protocol to enhance energy efficiency, stability, and network lifespan. The obtained results have demonstrated that the proposed frame attains up to 87.55% improvement in network lifetime and 91.14% enhancement in stability compared to the standard TEEN protocol. Moreover, the framework maintains higher packet delivery rates and lower energy consumption across all simulation rounds, confirming its effectiveness for scalable and resilient WSN deployments.