DRBRO- Dynamic Reinforcement Based Route Optimization for Efficient Route Discovery in Mobile Ad-hoc Networks

Efficient route discovery plays a crucial role to enhance the performance of wireless networks, particularly in mobile ad-hoc networks (MANETs) and wireless sensor networks (WSNs).Traditional routing protocols like AODV and DSR facing challenges with high congestion and excessive control overhead, high latency.This paper proposes the Dynamic Reinforcement-Based Route Optimization (DRBRO), a novel route discovery methodology that integrates clustering and reinforcement learning techniques to improve adaptive and energy-efficient routing.The proposed approach dynamically selects stable paths based on link quality, energy consumption and network traffic conditions.Performance results using NS2 Simulation proved that DRBRO enhances packet delivery ratio, reduces energy consumption and improve network throughput compared to traditional routing protocols.These findings confirms that the role of AI-driven optimization in route discovery, showing that DRBRO a reliable solution for real-time wireless applications.