Deep Learning and Optimization Approaches in Deep Hyperbolic Graph Attention Network-Based Collaborative Routing Algorithm for Clustered IoT-MANETs: A Review

Abstract

The rapid growth of Internet of Things (IoT) technologies has increased the demand for efficient routing mechanisms in Mobile Ad Hoc Networks (MANETs). IoT-MANET environments are highly dynamic and infrastructure-less, making traditional routing protocols such as AODV and DSR less effective due to frequent topology changes, node mobility, and energy constraints. Recent research has focused on integrating deep learning and optimization techniques to improve routing performance. Graph Neural Networks (GNNs) and Graph Attention Networks (GATs) enable intelligent routing by modeling network topology as graph structures and learning relationships among nodes. Additionally, hyperbolic graph learning provides an efficient way to represent hierarchical network structures commonly found in clustered IoT-MANET systems. This review highlights recent advances in deep hyperbolic graph attention network-based collaborative routing algorithms and optimization approaches for clustered IoT-MANET environments. It also discusses improvements in network performance metrics such as packet delivery ratio, energy efficiency, and routing scalability, while identifying future research directions for developing intelligent and energy-efficient routing frameworks for next-generation IoT networks.

Deep Learning, Hyperbolic Graph Attention Network (HGAT), Graph Neural Networks (GNN), Internet of Things (IoT), Mobile Ad Hoc Networks (MANETs), Cluster-Based Routing, Collaborative Routing, Network Optimization, Energy-Efficient Routing.