AI based Optimized low latency solution for path selection in an Ad-hoc Network

In ad-hoc networks, efficient data path selection is crucial for ensuring low latency, high reliability, and adaptive performance. Traditional routing protocols often suffer from delays due to dynamic topology changes, congestion, and link failures. To overcome these challenges, Artificial Intelligence (AI)-based optimization techniques can be leveraged to provide an adaptive and intelligent path selection mechanism. This paper explores the application of machine learning (ML) algorithms to improve the efficiency and reliability of pathfinding in ad hoc networks. We propose a framework that integrates reinforcement learning, supervised learning, and clustering algorithms to predict optimal paths based on network conditions such as node mobility, link quality, and traffic patterns. The system dynamically adjusts to changes in the network by learning from real-time data, reducing route discovery latency, and improving overall network performance. Simulation results demonstrate that the proposed ML-based routing mechanism outperforms conventional protocols like AODV and DSR in terms of packet delivery ratio, end-to-end delay, and network throughput. This work highlights the potential of machine learning to address the unique challenges of ad hoc networks and pave the way for more robust, adaptive communication systems.