ENHANCING AODV ROUTING PROTOCOL USING GRAPH LEARNING-BASED SPATIAL-TEMPORAL CONVOLUTIONAL NETWORK TO ENSURE QUALITY OF SERVICE IN 5G-BASED MANET

Abstract

Translate Article

Mobile ad hoc networks (MANETs) have several uses, including smart cities, medical applications, military uses, and rescue operations. They are also anticipated to be extremely well-liked in 5G since they have both basic and cutting-edge capabilities of the upcoming communication technology. Recently, there has been a lot of focus on 5G-based MANET. Its main characteristic is that quality of service (QoS) requirements are quite strict and nodes are continuously subjected to heavy traffic loads. Existing routing technologies have demonstrated shortcomings when implemented in 5G-based MANETs. In this manuscript, enhancing the ad hoc on-demand distance vector (AODV) routing protocol using graph learning-based spatial-temporal convolutional network to ensure quality of service in 5G-based MANET (EAODV-GLSTCN-QoS-5GMANET) is proposed. This research proposes a unique technique (GLSTCN-AODV) to increase the performance of MANET by integrating AODV protocol with the graph learning-based spatial-temporal convolutional network (GLSTCN). The GLSTCN's primary function in AODV is to update the state information database of each node to destination, maintain link stability, and find guaranteed QoS routes. The proposed EAODV-GLSTCN-5GMANET is implemented in MATLAB, and the performance of EAODV-GLSTCN-5GMANET is estimated under performance metrics likes packet delivery ratio (PDR), end-to-end (E2E) delay, and throughput. Finally, the proposed EAODV-GLSTCN-5GMANET method provides 27.20%, 25.81%, and 32.18% higher packet delivery ratio and 17.20%, 26.41%, and 32.18% higher throughput when comparing with existing techniques like improved technique of AODV routing protocol utilizing reinforcement learning for ensuring QoS in 5G-based MANET (AODV-RL-5GMANET), new deep Q-network design for QoS multicast routing in cognitive radio MANETs (DQN-MCR-CRMANET) and novel topology control algorithm for improving 5G-based MANET performance by flexibly adjusting coverage radius (TCA-MANET-FACR), respectively.