Optimized Multi-Path Relay Node Selection Using Deep Reinforcement Learning for Reliable and Energy-Efficient MANET Routing
Mobile Ad-hoc Network (MANET) are highly dynamic and infrastructure-less wireless network in which frequent topology changes, node mobility, packet collision, and energy constraints significantly affect routing performance and network reliability. This research suggests a Deep Reinforcement Learning (DRL)-based Optimized Multi-Path Relay Node Selection method for dependable and energy-efficient MANET routing. The suggested method takes into account important network metrics such as residual energy, node mobility, link stability, congestion level, and packet collision probability in order to intelligently choose the best relay nodes and different routing options using a Deep Q-Network (DQN)-based learning model. In comparison to traditional MANET routing protocols, simulation results show that the suggested DRL-based relay node selection technique greatly improves network lifetime, Packet Delivery Ratio (PDR), throughput and routing stability while lowering packet collision, end-to-end delay and energy consumption.