Deep Learning Method of Predicting MANET Lifetime Using Graph Adversarial Network Routing

Abstract

The prominence of mobile ad-hoc networks (MANETs) is on the rise. Within the domain of machine learning, a specialized subset known as deep learning (DL) employs diverse methodologies, each providing unique interpretations of the data it processes. In existing system the vulnerabilities of MANETs to security threats stem from factors such as node mobility, the potential for MANETs to provide economical solutions to real-world communication challenges, decentralized management, and constrained bandwidth. The efficacy of encryption and authentication methods in safeguarding MANETs encounters limitations. Intelligence will be the future development direction of network adaptive optimization technology in response to the increasingly complex mobile communication network. Data from mobile communication is a crucial part of the future information society. This paper propose adaptive optimization scheme , employs a machine learning algorithm that is capable of realizing the optimal parameter configuration and coordinating various optimization objectives in response to changes in state and environment. The coordination and advancement of social, versatile and area administrations make the customary informal organization easily change to portable correspondence organization. Creation of a system that can learn some rules from data and apply them to subsequent data processing is the research objective. This paper examines the machine learning-based algorithm for big data analysis and effectively addresses the issue of communication network data using graph theory and the experimental result shows higher lifetime prediction accuracy compare to previous system.