Multi-copy routing is a way that creates and forwards copies to the nodes without the copies so that increases the message delivery probability in the Vehicular Delay Tolerant Network (VDTN). The cost of generating many copies is potential congestion. To solve this problem, a feasible approach is to limit the number of copies generated. However, when the mobility of nodes is not sufficient and when the density of nodes near the source node is relatively high, the inappropriate process of copy distribution may result in copies remaining in a small area and too high local density of copies. Consequently, the overall performance is reduced due to low destination encountering probability in the whole area caused by too many local copies distribution. In this paper, by using node encounter rate to describe the activity and density of nodes, an effective Q-learning based VDTN multi-copy routing algorithm is proposed. The Q-learning reward factor is determined by the node encounter rate so that the distribution of message copies is controlled and the too high local density of copies can be alleviated. Simulation results show that the proposed algorithm outperforms the related algorithms, and offers better delivery rate, negligible message latency and network overhead under different network node speeds, node density, and load conditions.
Learning for Adaptive Multi-Copy Relaying in Vehicular Delay Tolerant Network
IEEE Transactions on Intelligent Transportation Systems ; 25 , 3 ; 3054-3063
2024-03-01
1045029 byte
Article (Journal)
Electronic Resource
English
Vehicular delay-tolerant networks?a novel solution for vehicular communications
Online Contents | 2013
|