Journal of High Speed Networks - Special issue on optical networking
Optical burst switching (OBS) - a new paradigm for an optical Internet
Journal of High Speed Networks - Special issue on optical networking
Algorithms for burst rescheduling in WDM optical burst switching networks
Computer Networks: The International Journal of Computer and Telecommunications Networking
Computer Networks: The International Journal of Computer and Telecommunications Networking
On ordered scheduling for optical burst switching
Computer Networks: The International Journal of Computer and Telecommunications Networking
ICOIN'05 Proceedings of the 2005 international conference on Information Networking: convergence in broadband and mobile networking
Control architecture in optical burst-switched WDM networks
IEEE Journal on Selected Areas in Communications
Performance comparison of OBS and SONET in metropolitan ring networks
IEEE Journal on Selected Areas in Communications
Efficient burst scheduling algorithms in optical burst-switched networks using geometric techniques
IEEE Journal on Selected Areas in Communications
Modeling the impact of control plane losses on the performance of optical burst switched core node
IEEE Communications Letters
Hi-index | 0.00 |
In this paper, we consider the case of an Optical Burst Switching (OBS) network where the Switch Control Units (SCU) do not work at the peak rate. As a consequence, some Burst Control Packets (BCPs) will have to wait in queue to be processed, and then the BCP sojourn time will be variable. On the contrary, the optical burst does not leave the optical domain and the delay suffered is close to the propagation delay. Hence, chances are that the BCP arrives late to a given switch and, in that case, the optical burst will be dropped. We propose a Load-adaptive Offset Time algorithm (LOT) that takes into account the BCP variable sojourn time for the offset time calculation. The algorithm performs on-line calculation of the Discrete Fourier Transform (DFT) of the BCPs waiting time pdf. Our findings show that this procedure is very efficient both in terms of bandwidth usage and processing load. For example, considering a Gaussian service time for the BCPs, it turns out than less than 45 coefficients are necessary to calculate the offset time for a SCU utilization factor larger than 0.1.