Secure Energy Aware Optimal Routing using Reinforcement Learning-based Decision-Making with a Hybrid Optimization Algorithm in MANET

Abstract

Mobile ad hoc networks (MANETs) are wireless networks that are perfect for applications such as special outdoor events, communications in areas without wireless infrastructure, crises and natural disasters, and military activities because they do not require any preexisting network infrastructure and can be deployed quickly. Mobile ad hoc networks can be made to last longer through the use of clustering, which is one of the most effective uses of energy. Security is a key issue in the development of ad hoc networks. Many studies have been conducted on how to reduce the energy expenditure of the nodes in this network. The majority of these approaches might conserve energy and extend the life of the nodes. The major goal of this research is to develop an energy-aware, secure mechanism for MANETs. Secure Energy Aware Reinforcement Learning based Decision Making with Hybrid Optimization Algorithm (RL-DMHOA) is proposed for detecting the malicious node in the network. With the assistance of the optimization algorithm, data can be transferred more efficiently by choosing aggregation points that allow individual nodes to conserve power The optimum path is chosen by combining the Particle Swarm Optimization (PSO) and the Bat Algorithm (BA) to create a fitness function that maximizes across-cluster distance, delay, and node energy. Three state-of-the-art methods are compared to the suggested method on a variety of metrics. Throughput of 94.8 percent, average latency of 28.1 percent, malicious detection rate of 91.4 percent, packet delivery ratio of 92.4 percent, and network lifetime of 85.2 percent are all attained with the suggested RL-DMHOA approach.