SLIIT >
Research Symposium >
SLIIT Student Research -2017 >

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/500

Title: A Reinforcement Learning Approach To Enhance The Trust Level of MANETs
Authors: Jinarajadasa, Gihani
Jayantha, Wayomi
Wijerathne, Sammani
Jayasinghe, Gothami
Rupasinghe, Lakmal
Keywords: Mobile-ad-hoc network (MANET)
Reinforcement Learning(RL)
Ad-hoc On-demand Distance Vector (AODV)
RNN (Recurrent Neural Network)
Deep Learning
Network Simulator-3(NS-3)
Issue Date: 2017
Publisher: SLIIT
Series/Report no.: ;17-049
Abstract: Generally a Mobile-ad-hoc network (MANET) is consist of many interconnected free and autonomous nodes which is often composed by mobile devices. MANETs are decentralized and self-organized wireless communication systems which are able to arrange themselves in various ways and have no fixed infrastructure. Since MANETs are mobile, the network topology is changing rapidly and unpredictably. Because of this nature of the mobility of the nodes in MANETs, the main problems occurred are unreliable communications and weak security where the data can be compromised or misused easily. Therefore we are proposing a trust enhancement approach to a MANET considering Ad-hoc On-demand Distance Vector (AODV) protocol as the specific protocol, via Reinforcement Learning (RL) and Deep Learning concepts. The proposed system is consist of RL agent, who learns to detect and give predictions on trustworthy nodes, reputed nodes, and malicious nodes and classify them. The identified parameters from AODV simulation using Network Simulator-3(NS-3) are given to the designed RNN (Recurrent Neural Network) model and results are evaluated.
URI: http://hdl.handle.net/123456789/500
Appears in Collections:SLIIT Student Research -2017

Files in This Item:

File Description SizeFormat
17-049.pdf799.53 kBAdobe PDFView/Open
View Statistics

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback