Table of Contents Author Guidelines Submit a Manuscript
The Scientific World Journal
Volume 2014, Article ID 452362, 9 pages
Research Article

Self-Adaptive Trust Based ABR Protocol for MANETs Using Q-Learning

1Dayananda Sagar College of Engineering, Bangalore 560078, India
2Sona College of Technology, Salem 636005, India

Received 14 March 2014; Revised 7 July 2014; Accepted 9 July 2014; Published 28 August 2014

Academic Editor: Fei Yu

Copyright © 2014 Anitha Vijaya Kumar and Akilandeswari Jeyapal. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Mobile ad hoc networks (MANETs) are a collection of mobile nodes with a dynamic topology. MANETs work under scalable conditions for many applications and pose different security challenges. Due to the nomadic nature of nodes, detecting misbehaviour is a complex problem. Nodes also share routing information among the neighbours in order to find the route to the destination. This requires nodes to trust each other. Thus we can state that trust is a key concept in secure routing mechanisms. A number of cryptographic protection techniques based on trust have been proposed. Q-learning is a recently used technique, to achieve adaptive trust in MANETs. In comparison to other machine learning computational intelligence techniques, Q-learning achieves optimal results. Our work focuses on computing a score using Q-learning to weigh the trust of a particular node over associativity based routing (ABR) protocol. Thus secure and stable route is calculated as a weighted average of the trust value of the nodes in the route and associativity ticks ensure the stability of the route. Simulation results show that Q-learning based trust ABR protocol improves packet delivery ratio by 27% and reduces the route selection time by 40% over ABR protocol without trust calculation.