A Recurrent Reward Based Learning Technique for Secure Neighbor Selection in Mobile AD-HOC Networks

K Sakthidasan Sankaran,K R Devabalaji,Thanikanti Sudhakar Babu,Hassan Haes Alhelou,N Vasudevan,T Yuvaraj

doi:10.1109/access.2021.3055422

Abstract

Mobile ad-hoc network is an assortment of distinct attribute-based mobile devices that are autonomous and are cooperative in establishing communication. These nodes exploit wireless links for communication that causes injection of the adversaries in the network. Therefore, detection and mitigation of adversaries and anomalies in the network are mandatory to retain its performance. To strengthen this concept, in this article, a novel secure neighbor selection technique using recurrent reward-based learning is introduced. This proposed technique inherits the benefits of conventional routing and intelligent machine learning paradigm for classifying the states of the nodes based on their communication behavior. Thorough learning of the behavior of the nodes unanimously at all the hop-levels of communication enables establishing secure and consistent routing and transmission paths to the destination. The performance of the proposed technique is estimated using the metrics throughput, packet delivery ratio, and delay and detection ratio. Experimental analysis proves the consistency of the proposed technique by improving throughput, packet delivery ratio, and detection ratio under less delay.

Highlights

Research focus over mobile ad-hoc networks (MANETs) has increased significantly in the present years due to its on-demand communication and infrastructure-less configuration abilities
Sankaran et al.: Recurrent Reward Based Learning Technique for Secure Neighbor Selection in Mobile AD-HOC Networks and lack of centralized administrative support are some of the issues that permit intruder or adversary to breach the communications of the network
PROPOSED METHODOLOGY The proposed SECURE NEIGHBOR SELECTION (SNS) with RR is featured by integrating machine learning (ML) in MANET operations

Summary

INTRODUCTION

Research focus over mobile ad-hoc networks (MANETs) has increased significantly in the present years due to its on-demand communication and infrastructure-less configuration abilities. Sankaran et al.: Recurrent Reward Based Learning Technique for Secure Neighbor Selection in Mobile AD-HOC Networks and lack of centralized administrative support are some of the issues that permit intruder or adversary to breach the communications of the network. Graph-theory-based network partitioning techniques were presented so far for realizing the detection of decentralized recognition in the fast response speed on using the characteristics highlights of power flow in the independency of various groups [6] One such application aims at employing deployed sensors in the pipeline network, the data driven detection problem occurred by failure of device or the interruption of network which in turn hinders the implementation of pipeline monitoring status. The contributions in this article are listed as follows: i) Designing a secure neighbor selection technique that exploits recurrent reward for discovering optimal path nodes to provide end-to-end communication reliability. Iii) Performing a comparative analysis of the proposed method with the existing techniques to prove its consistency

RELATED WORKS

PROPOSED METHODOLOGY

STATE DETERMINATION

Findings

CONCLUSION