PACKET LOSS DIFFERENTIATION OVER MANET BASED ON A BP NEURAL NETWORK

Journal Title: Journal of Information Technology and Application (JITA) - Year 2018, Vol 8, Issue 1

Abstract

An adaptive distributed routing algorithm is essential in MANETs, since there is no central routing system. Actually, there is no central point of coordination; each node is responsible for forwarding data packets to other nodes, thereby acting as router and host. A packet might travel through multiple intermediary ad hoc nodes in order to arrive to its destination, while the nature of wireless multi-hop channel is bringing in various types of packet losses. This paper focuses on three main reasons of online packet losses in MANETs: (1) losses due to wireless link errors; (2) losses due to congestion; and (3) losses due to route alteration. It proposes a deep learning-based algorithm for packet loss discrimination. The algorithm uses the backpropagation neural network (BPNN) concept. We performed simulation experiments for evaluating the performance of the proposed loss discrimination algorithm under different network con􀏐igurations. Through simulation results, we con􀏐irmed that the proposed algorithm improves packet loss discrimination and route alteration in the network. It also reduces congestion and increases network throughput.

Authors and Affiliations

Dimitris Kanellopoulos Pratik Gite

Keywords

Related Articles

E-MAIL FORENSICS: TECHNIQUES AND TOOLS FOR FORENSICINVESTIGATION OF ONE COURT CASE

E-mail has emerged as the most important application on the Internet for communication of messages, delivery of documents and carrying out transactions and is used not only from computers, but many other electronic gadge...

EVALUATION OF THE PERIOD OF SENSORS MOTION PARAMETERS OF THE TRAIN

The choice of polling period sensors for measuring the speed and acceleration of the train can be produced using the spectral representation of functions of velocity and acceleration from time to time. Using the spectral...

USING OPEN SOURCE SOFTWARE FOR WEB APPLICATION SECURITY TESTING

Web applications are a standard part of our everyday lives. Their purpose can vary signifi cantly, from e-banking to social networks. However, one thing is similar - users have generally high expectations from different...

THE WAY OF STUDENTS’ EFFICIENCY IMPROVEMENT IN KNOWLEDGE ACQUISITION AND TRANSFER KNOWLEDGE MODEL IN CLAROLINA CMS

In this work, throughout the research which was organized in one high school in Bosnia and Herzegovina, it will be shown the infl uence of exercises on the fi nal result in the e-learning environment at the fi nal test d...

USING KERBEROS PROTOCOL FOR SINGLE SIGN-ON IN IDENTITY MANAGEMENT SYSTEMS

Today, identity management systems are widely used in different types of organizations, from academic and government institutions to large enterprises. An important feature of identity management systems is the Single Si...

Download PDF file
  • EP ID EP611303
  • DOI 10.7251/JIT1801018K
  • Views 129
  • Downloads 0

How To Cite

Dimitris Kanellopoulos Pratik Gite (2018). PACKET LOSS DIFFERENTIATION OVER MANET BASED ON A BP NEURAL NETWORK. Journal of Information Technology and Application (JITA), 8(1), 18-26. https://europub.co.uk/articles/-A-611303