Skip to Main Content
Shortest path algorithms such as shortest path first (SPF) and constrained shortest path first (CSPF) are widely used in online traffic engineering where connections need to be set up one at a time as connection requests arrive sequentially. We propose an approach, called design-based routing (DBR), whereby optimized paths computed offline are used to guide online path setups. Offline path computation in generalized multiprotocol label switching (GMPLS) networks does not pose a significant challenge since optical core or metro networks typically consist of a few dozen to hundreds of nodes compared to hundreds to more than one thousand nodes in pure data networks. DBR takes advantage of available demand information based on customer prescriptions, traffic projections, and historical measurements to build an approximate traffic demand matrix for path optimization. By means of simulation, we perform comparative evaluations of opaque GMPLS networks under static and dynamic connections with different protection modes. The results indicate that DBR outperforms SPF and CSPF under a wide range of operating conditions and is robust to inaccuracies in the estimation of the traffic demand matrix. We then construct routing schemes with resource management and online measurement. The simulation results indicate that resource management provides an effective way to mitigate greed inherent in CSPF, and online measurement provides an effective way to improve DBR performance when the traffic demand information used in the design of DBR paths is different from the actual traffic demand.