Development of MD-LSTM for malicious detection and hybrid coati and dolphin swarm optimization for QoS-aware multicast routing in MANET environment

Abstract

Mobile Ad-hoc Networks (MANETs) also known as infrastructure-less network consist of mobile nodes that create a form of internet connectivity. Routing protocols are essential in MANETs, playing a crucial role in their functionality and extensively studied for enhancing the efficiency. Most of the routing protocols select unstable and congested intermediate nodes thereby it frequently causes the network path failures and packet loss. The recent studies in wireless MANET have focused on developing the new strategies for multicast routing. Quality of Service (QoS) enhances predictability of network performance in MANET. However, the application of QoS in ad hoc networks faces challenges due to the limited battery life and dynamic capacity of mobile devices. To boost the performance of MANETs, a novel hybrid heuristic approach for QoS-aware multicast transmission is proposed. The inherent openness of the network also increases its vulnerability to malicious attacks. Therefore, the malicious node detection is handled by Multiscale Dilated Long Short-Term Memory (MD-LSTM), where the attacked nodes are identified. Subsequently, the multicast routing is accomplished by proposing the Hybrid Coati Optimization Algorithm and Dolphin Swarm Optimization (HCDSO), which is used to find the optimal paths for mitigating the attacked nodes. This algorithm is also used to derive the multi-objective function along with different constraints. Finally, the analysis is effectively done by utilizing different performance measures. The accuracy of the suggested framework attains 97.75 in 1st dataset, 96.6 in 2nd dataset and 97.75 in 3rd dataset. On the contrary, the proposed method outperforms better results for malicious detection and multicast routing in MANET while enhancing the throughput performance than the existing techniques.