Intelligent Routing in MANETs: Bridging AI and Protocol Design for Next-Gen Networks

Abstract

Decentralized wireless networks with self-configuring nodes that can interact without the need for fixed infrastructure are known as mobile ad hoc networks, or MANETs. Reliable and effective communication is a difficulty for traditional routing methods because of node mobility, bandwidth limitations, and energy limits. A potential remedy for these issues is the use of machine learning (ML) and artificial intelligence (AI) into the design of routing protocols. MANETs can optimize routing choices, adjust flexibly to shifting network conditions, and enhance overall network performance in real-time thanks to AI-driven techniques.
In order to improve routing efficiency, scalability, and energy consumption, this study investigates the use of AI techniques in MANETs, including deep learning, reinforcement learning, and clustering algorithms. By enabling adaptive resource allocation, predictive traffic management, and intelligent path selection, AI-based protocols can greatly boost network resilience, lower latency, and increase throughput. In order to handle the intricate dynamics of MANETs, the study also looks at hybrid AI techniques that incorporate several learning philosophies.
The study also addresses the difficulties in putting AI-driven routing into practice, such as security issues, computing cost, and handling extremely dynamic network conditions. It also emphasizes how AI might be integrated with cutting-edge technologies like edge computing, 5G, and the Internet of Things to facilitate the creation of next-generation MANETs. In order to overcome the current constraints and spur innovation in AI-based routing protocols for MANETs, the study concludes by outlining future research topics.
The goal of this research is to help develop more intelligent, effective, and self-optimizing MANETs for next-generation communication networks by bridging the gap between AI and routing protocols.