Dimensioning of store-and-transfer WDM networks with stratified ROADM node

Abstract

The so called Store-and-Transfer WDM Network (STWN) can store data in source storage and provision lightpaths at an optimal time when wavelengths are clear of conflicts. Consequently, blocking of requests can be decreased and resource utilization of the network can be improved. If traffic can be classified into delay-sensitive packet flows and deadline-constrained large data transfers, we can use a stratified node architecture to reduce cost of STWN node by reducing port count of optical and electronic switches. In this work, we investigate dimensioning of a network of flexible grid reconfigurable optical add/drop multiplexers and compare the result with that obtain by dimensioning of STWN. We propose a two-step method to determine the amount of spectrum required to satisfy the demand of large data transfers, which is given as a load matrix with a deadline and blocking rate. We also obtain the overall utilization over all links. The method firstly uses Markov chain to model variable bandwidth allocation over a lightpath and searches for amount of required spectrum of all source-destination pairs, and secondly optimizes routing and spectrum assignment for the matrix of amount of required spectrum to minimize maximum amount of spectrum used over each link. Numerical results show the following with all numbers given as absolute values: If bandwidth allocation method Min is used, the utilization can reach 0.7 and the amount of required spectrum is 30% more than that required by STWN. If bandwidth allocation method Dyna is used, the utilization can reach 0.9 and the amount of required spectrum is similar to that required by STWN. Also, under the same load, if blocking increases from 0.001 to 0.01, the amount of required spectrum decreases and the utilization increases 0.08, which denotes over-provisioning of spectrum and allowing preemption of spectrum during hours of peak traffic can effectively decrease blocking.