Energy-efficient priority encoding strategies using machine learning based hybrid MAC protocol for wireless sensor networks

In the present work, a Priority-Aware Periodic Hybrid MAC protocol () is proposed to achieve intelligent, energy-efficient, and priority-based data transmission in Wireless Sensor Networks (WSNs). WSNs frequently encounter challenges in efficiently managing heterogeneous traffic—such as event-driven, periodic, and emergency data—while maintaining low latency and reduced energy consumption. Traditional MAC protocols rely on static scheduling, lacking the adaptability needed to handle critical or time-sensitive data under varying network conditions, leading to packet delays, energy wastage, and reduced responsiveness. The proposed protocol integrates a machine learning-based priority encoding mechanism that evaluates data transmission priorities based on three key factors: data priority, emergency data, and buffer overflow. It operates in two distinct modes—Normal and Priority—to dynamically adapt to changing network requirements. In Normal mode, sensor nodes transmit data using either TDMA or BMA schemes depending on traffic type, while the central controller optimally determines sampling rates for periodic data. When emergency or high-priority conditions occur, the system switches to Priority mode to ensure timely and reliable data delivery. Simulation results demonstrate that the proposed outperforms existing TDMA, EA-TDMA, EBMA, and ASHMAC protocols in terms of energy efficiency, and latency reduction, thereby offering a robust framework for priority-aware, energy-efficient communication in WSNs.