An adaptive routing algorithm for ATM networks using a learning automaton

In the dynamic environment of the ATM networks, where the traffic load and the network topology change significantly over the time, the use of an adaptive routing algorithm is mandatory. In this paper, a dynamic solution to the routing problem in ATM networks is presented suitable for real-time application. The proposed methodology employs a learning automaton, called stochastic estimator learning algorithm (SELA), specially designed for the routing problem. The feedback of the SELA is a function of the utilizations of the links that comprise a possible route to a specific routing problem. Simulation results show the effectiveness of the proposed scheme in comparison with some of the most known routing algorithms. Some interesting directions for future works are also discussed.