A delay/disruption tolerant routing algorithm based on traffic prediction

Delay/Disruption tolerant networks (DTNs) are a class of emerging networks that experience frequent and long-duration partitions. These networks have a variety of applications in situations such as crisis environments and deep-space communication. In this paper, the problem of traffic prediction in DTNs is studied. While traffic prediction in the Internet and mobile ad hoc networks has been studied extensively, due to the unique characteristic of frequent partitioning in DTNs, traffic prediction in DTNs is a considerably different and challenging problem. It brings new issues to the design of routing algorithms. In this paper, we propose new semantic models for DTN traffic prediction and develop traffic prediction based routing algorithm. This paper present a framework to evaluate these algorithms in DTNs. The object is to understand how routing performance is affected by the availability of traffic prediction and to guide the design of DTN routing protocols. Simulations show that efficient traffic prediction routing for DTNs can be constructed using only partial knowledge. In addition, routing algorithms that with traffic prediction achieve better delivery ratios, especially when available knowledge is limited.