Selecting fibre delay line distributions for travelling buffers in an all-optical packet switched cross-connect

Geldenhuys, R.; Leuschner, F.W.; Liu, Y.; Khoe, G.D.; Calabretta, Nicola; Dorren, Hjs Harm

doi:10.1109/ccece.2003.1226037

Cited by 3 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Configurations, where no such regularity was imposed a priori, were considered in e.g. [6,13] and [28] and the already cited work of Almeida et al Further, we assume the buffer feeds into a single outgoing channel. As a consequence, a single fiber for each value of realizable delay n D (n = 0, 1, .…”

Section: Fiber Delay Line Optical Buffersmentioning

confidence: 99%

Queueing analysis of a single-wavelength Fiber-Delay-Line buffer

2006

View full text Add to dashboard Cite

We present in rather mathematical detail the queueing analysis of a single-wavelength Fiber-Delay-Line buffer. Such optical buffer system cannot realize all possible delay values, but only a limited set, typically multiple integers of some basic unit called the granularity. This leads to an under-utilization of the available channel capacity, and a bad design choice for the granularity can seriously impair performance.The analysis makes extensive use of generating functions and focusses on the scheduling horizon as seen by arriving bursts and the waiting time these incur in an infinite system. From the expressions obtained, several measures of interest are derived, notably heuristics for the burst loss probability and the mean waiting time in finite systems, which can be used to evaluate performance for any given value of the input load. The model we propose allows for rather general burst-size distributions, but for special instances thereof, the formulae can be made more explicit. A number of numerical examples highlight some of the peculiar aspects of Fiber-Delay-Line buffers.

show abstract

Section: Fiber Delay Line Optical Buffersmentioning

confidence: 99%

Queueing analysis of a single-wavelength Fiber-Delay-Line buffer

2006

View full text Add to dashboard Cite

show abstract

“…The distribution of is given by if if (9) By using the distribution of [ (9)], the distribution of [ (8)] can be evaluated using matrix inversion. The mean number of packets that enter the switch in a given time slot, , is the mean of the binomial distribution associated with the random variable, , and hence, (10) The mean number of packets that are dropped in a time slot, , is the mean number of packets represented by that exceeds the number of FDLs, , and hence, (11) Thus, the probability of blocking of the switch, , is the ratio of the mean number of packets that are dropped to the mean number of packets that enter the switch in a given time slot. Thus, (12) The utilization of the FDLs is load dependent.…”

Section: Performance Analysismentioning

confidence: 99%

“…The propagation time delay is usually chosen to be a multiple of the packet transmission time. Optical buffering schemes that use FDL for contention resolution can be divided into two categories: feedforward [9], [11], [14], [15], and feedback FDL buffering [1], [3], [12], [17]. In feed-forward buffering, a contending packet is delayed at the output port and leaves the node after the propagation delay of the traversed FDL.…”

Section: Introductionmentioning

confidence: 99%

A Surjective-Mapping Based Model for Optical Shared-Buffer Cross-Connect

Fayoumi

Jayasumana

2007

IEEE/ACM Trans. Networking

View full text Add to dashboard Cite

Abstract-A Surjective-Mapping based Model (SMM) is developed to evaluate the performance of a slotted optical shared-buffer cross-connect. The model is simple, accurate, and yet provides comprehensive performance characteristics of the switch. The model also overcomes the limitations of traditional Markovian based models in evaluating moderate to large switches, associated with the explosion of number of states. The model is verified using simulation results for different switch sizes and different numbers of delay lines. The model enables dimensioning the switch architecture to meet the target performance. Performance of optical shared-buffer cross-connect is analyzed in detail, in terms of blocking probability, delay distribution, and delay line utilization.

show abstract