Delay/Disruption-Tolerant Networks (DTN) invented to describe and cover all types of long-delay, disconnected, intermittently connected networks . The term is characterized by frequent network partitioning, intermittentconnectivity, large or variable delay, asymmetric data rate, and low transmission reliability . In DTNthere is a trade-off off between delivery ratio and overhead . In this study, we proposed context-adaptive reinforcement learning based routing(CARL-DTN), to determine optimal replicas of the message based on the real-timedensity . The result shows that the proposed protocol has better performance in terms of message delivery ratio . The proposal protocol uses a real-time physical context, social-social-tie strength, and real time message context using fuzzy logic in therouting decision. The proposed protocol is also considered for therelay node selection by employing Q-Learning algorithm to estimate the estimate theencounter probability between nodes and to learn about nodes available in theneighbor by discounting reward. The performance of the proposed protocols isevaluated based on various simulation scenarios

Author(s) : Fuad Yimer Yesuf, M. Prathap

Links : PDF - Abstract

Code :
Coursera

Keywords : based - context - delay - proposed - real -

Leave a Reply

Your email address will not be published. Required fields are marked *