Graphical Probabilistic Routing Model for OBS Networks with Realistic Traffic Scenario

摘要: Burst contention is a well-known challenging problem in Optical Switching (OBS) networks. Contention resolution approaches are always reactive and attempt to minimize the BLR based on local information available at core node. On other hand, proactive approach that avoids burst losses before they occur desirable. To reduce probability of contention, more robust routing algorithm than shortest path needed. This paper proposes new mechanism for JET-based OBS networks, called Graphical Probabilistic Routing Model (GPRM) selects less utilized links, hop-by-hop basis by using bayesian network. We assume no wavelength conversion buffering be nodes simulate proposed under dynamic load demonstrate it reduces Loss Ratio compared static Network Simulator 2 (ns-2) NSFnet network topology with realistic traffic matrix. Simulation results clearly show outperforms terms BLR.