Energy efficient group priority MAC protocol using hybrid Q-learning honey Badger Algorithm (QL-HBA) for IoT Networks

Area of Science:

• Computer Science
• Network Engineering
• Artificial Intelligence

Background:

• Selecting appropriate Medium Access Control (MAC) layer protocols is crucial for optimizing Internet of Things (IoT) network performance based on application-specific service characteristics.
• Existing protocols may not adequately address the diverse requirements of IoT applications, leading to inefficiencies in delay, energy consumption, and throughput.

Purpose of the Study:

• To propose a novel Energy Efficient and Group Priority MAC (EEGP-MAC) protocol designed for IoT networks.
• To enhance network efficiency by optimizing MAC protocol selection using a hybrid intelligent algorithm.

Main Methods:

• The EEGP-MAC protocol utilizes a Hybrid Q-Learning Honey Badger Algorithm (QL-HBA) for intelligent MAC protocol selection.
• Network devices are grouped by the PAN coordinator based on location, energy, and traffic type, with priorities assigned using a combined metric.
• The QL-HBA algorithm optimizes contention node selection within groups, considering factors like neighbor count and traffic load.

Main Results:

• Simulations in NS3 demonstrate that EEGP-MAC achieves 11% less delay compared to the QL-DGMAC protocol.
• The proposed protocol shows a 16% reduction in energy consumption.
• EEGP-MAC results in a 10% increase in throughput across various network sizes.

Conclusions:

• The EEGP-MAC protocol effectively enhances IoT network performance by intelligently managing MAC layer operations.
• The integration of QL-HBA offers a robust mechanism for optimizing group priorities and resource allocation.
• EEGP-MAC presents a significant improvement over existing protocols, making it suitable for diverse IoT applications.