Dynamic Cluster Head Optimization for Multipath Routing in Mobile Ad Hoc Networks via Hybrid Stochastic Bandgap Optimization Mixstyle Neural Networks

Abstract

Mobile ad hoc networks (MANETs) are wireless networks that may be rapidly built and self-organize. They are ideal for military operations, disaster relief, outdoor events, and communications in areas without radio infrastructure. In order to find more security flaws, it is advised to employ intrusion detection, which controls the system. For further security against unauthorized access and prevention, intrusion monitoring is essential. Depending on how long the system lasts, a mobile node's capacity to forward packets may be impacted by the loss of its power supply. This research proposes the use of hybrid stochastic bandgap optimization (SBO) and mixstyle neural networks (MNNs) to optimize the cluster head for multipath routing in mobile ad hoc networks. The proposed method combines both SBO and MNNs. The SBO method is used to choose the optimum pathways, and the MNN method is used to select the multipath routing in MANET. The MATLAB platform is used to build the suggested solution, which is then assessed based on several performance metrics, including detection rate, energy consumption, delay, and throughput. The suggested method outperformed other approaches like deep convolutional neural networks (DCNNs) and bacteria for aging optimization algorithm (BFOA) with a maximum detection rate of 96% and a low energy consumption of 0.12 mJ.