The Adaptive Routing Algorithm Depending on the Traffic Prediction Model in Cognitive Networks

摘要

As a cognitive network is forward looking and gains from current and previous information on the network to achieve an intended goal, a routing algorithm, Minimum Workload Routing Algorithm (MWL) in cognitive networks, is proposed, which is depending on the prediction traffic model—MMSE to construct the prediction traffic matrix and select the route with the lightest traffic load which is no more than the traffic threshold. Further more, we extend the scheme of MWL and promote the adaptive traffic prediction routing algorithm (ATPRA) considering both traffic load and length load of the global route and adaptively selecting a route of the lowest aggregated load by adjusting the threshold of traffic. Comparing with the pure shortest routing algorithm, MWL and ATPRA have good performances at decreasing delay, lowing packet loss rate, load balancing and avoiding the congestion, which is validated by the simulation.