MANET: An Enhanced Reinforced Deep Learning Routing Algorithm

The importance of Mobile Ad Hoc Networks (MANETs) has grown recently due to the rise in mobile device usage and the development of Internet of Things (IoT) applications. Traditional routing methods struggle to adapt to the dynamic alterations in network topology and the limitations caused by constrained network resources. In order to address these issues, a Deep Learning-Based Reinforced Optimized Routing Algorithm (RDLORA) is proposed. Especially for MANET, RDLORA has been designed to provide flexible and intelligent routing solutions. This is accomplished by combining parameter settings, selecting the Cluster Head (CH) using a Reinforcement deep learning method, and integrating an intrusion detection system based on k-Nearest Neighbors ($k$-NN). Network Simulator NS2 is used to evaluate RDLORA's performance and show how effective it is in dynamic network environments. The simulation results proved that the proposed algorithm outperformed in terms of reduced latency potentially improved packet delivery ratio and throughput, which automatically improves the quality of transmission, and energy consumption It also enhances security in the transmission of data inside dynamic wireless networks.