Burst-cluster transmission with probabilistic pre-emption for reliable data transfer in high-performance OBS networks
Recently, optical switching and packet processing technologies have been developed and high-performance optical burst switching
(OBS) networks are constructed by using these technologies. In high-performance OBS networks, several types of applications
such as Grid computing and HDTV can be provided for users according to immediate reservation protocol. Because some applications
require that data is transmitted reliably over high-performance OBS networks, it is indispensable to provide reliable data
transfer service for high-priority users. Therefore, in this paper, we propose a reliable burst transmission method which
can be available for the immediate reservation protocol. In the proposed method, both burst-cluster transmission and probabilistic
pre-emption are used at edge and core nodes. By using these methods together, the reliable data transfer and the service differentiation
can be provided. We evaluate by simulation the performance of the proposed method in the 14-node NSFNET. Numerical examples
show that the proposed method can transmit higher-priority bursts more reliably than the conventional method while not increasing
the overall burst loss probability so much. In addition, we investigate effective parameter settings from some simulation
Available from: ufrj.br
- "Several mechanisms have been proposed to address QoS support in optical-burst switched networks. Some approaches are based on the modification of signaling protocols  and also on burst preemption –. The modification of signaling protocols, however, may increase the end-toend delay of high-priority bursts because of the extra offset introduced  and burst preemption are hard to implement in practice. "
[Show abstract] [Hide abstract]
ABSTRACT: In this article, we analyze the performance of the load-level-based admission control (LLAC) mechanism for optical burst-switched networks in a multilink scenario. The goal of our mechanism is to differentiate the blocking probability of a given service class according to the network load and a class-associated parameter, called load level. We develop a multilink analytical model based on the reduced load approximation method to analyze the proposed mechanism in more realistic scenarios. The multilink model provides an estimation error up to 13 times lower than the one provided by the single model for the analyzed configurations. Both are compared with simulation results. In addition, our results show that the load-level-based mechanism effectively differentiates the services in all analyzed configurations when compared with other similar mechanisms.
[Show abstract] [Hide abstract]
ABSTRACT: In order to improve the fairness in terms of the number of hops for high-performance optical burst switching networks, we propose a method called hop-based burst-cluster transmission. In this method, bursts with different numbers of hops are assembled simultaneously, and a hop-based burst-cluster is generated so that the bursts within the cluster are arranged in order from the smallest to the largest number of hops. Then the hop-based burst-cluster is transmitted along with multiple control packets. Here, within the same cluster, a burst whose number of hops is small is transmitted before a burst whose number of hops is large. The control packets are processed according to the modified processing algorithm, and hence a burst whose number of hops is large has more chances in the wavelength reservation than a burst whose number of hops is small. As a result, the burst loss probability of many hops decreases and the burst loss probability of few hops increases, improving the fairness. In addition, hop-based burst-cluster transmission can also decrease the overall burst loss probability. We evaluate the performance of hop-based burst-cluster transmission for the 14-node NSFNET and ARPA2 with simulation. In numerical examples, we compare the performance of the proposed method with conventional burst transmission, and we investigate the impacts of the amount of traffic, the processing time of a control packet, the switching time of an optical switch, and the number of wavelengths. We show that the proposed method can not only improve the fairness but also decrease the overall burst loss probability in both the networks.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.