A Fast Convergence Solution for Distance Vector Routing Protocol Using Hidden Markov Model (HMM)

Due to low complexity, power and bandwidth saving Distance Vector Routing is the most popular dynamic routing protocol which is using in many networks such as ad hocnetworks. However, this protocol has a serious drawback in practice called Count To Infinity problem or slow convergence.There are many proposed solutions in literature to solve the problem, but all of these methods depend on the network topology, and impose much computational complexity to thenetwork. In this paper, we use hidden markov model (HMM), which is one of the most important machine learning tools, tosolve the problem. As the results show, this method is completely independent from the network topology and simple with low computational complexity.

Keywords:

Count To Infinity , Distance Vector Routing (DVR) , Hidden Markov Model (HMM) , Slow convergence