Abstract: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 horiz… Show more
“…Separately, the performance of a switch equipped with FDLs but without converters has been treated in [19,9,10]. The analysis of a switch including both solutions turns out to be more complex since the multidimensional nature of a multi-wavelength switch has to be combined with the special queuing behavior of the optical buffer.…”
Section: Related Workmentioning
confidence: 99%
“…The granularity of the FDL is a parameter with a significant influence on the loss probability for the single-wavelength buffer, as shown in [3,9,19]. In Fig.…”
Section: Combined Effect Of Fdls and Wcsmentioning
In this paper, we analyze an optical burst switching (OBS) switch endowed with both wavelength converters (WCs) and fiber delay lines (FDLs) to resolve contention. We consider the case where the number of wavelengths is large by introducing a mean field model that provides exact results when the number of wavelengths tends to infinity. We have confirmed through simulations that the mean field model provides accurate approximations for switches with a large but finite number of wavelengths, which are of interest in view of wavelength division multiplexing (WDM). Furthermore, our model allows a very general behavior for the arrival process and the packet size distribution, as well as two different wavelength allocation policies: minimum horizon and minimum gap. Our results include a detailed analysis of the effect that these parameters have on the burst loss rate, and on the minimum number of WCs required to attain a zero loss rate as the number of wavelengths becomes large. We have found that at high loads there is little value in adding FDLs and, if included, shorter granularities result in fewer WCs required to achieve a zero loss rate. The inclusion of FDLs becomes more significant under mid loads and bursty traffic, where the addition of several FDLs may reduce the conversion requirements. Also, increasing the number of WCs under the minimum horizon policy may worsen the This work has been supported by the FWO-Flanders through project "Stochastic modeling of optical buffers and switching systems based on Fiber Delay Lines" (G.0538.07). loss rate, while this is never the case for the minimum gap policy.
“…Separately, the performance of a switch equipped with FDLs but without converters has been treated in [19,9,10]. The analysis of a switch including both solutions turns out to be more complex since the multidimensional nature of a multi-wavelength switch has to be combined with the special queuing behavior of the optical buffer.…”
Section: Related Workmentioning
confidence: 99%
“…The granularity of the FDL is a parameter with a significant influence on the loss probability for the single-wavelength buffer, as shown in [3,9,19]. In Fig.…”
Section: Combined Effect Of Fdls and Wcsmentioning
In this paper, we analyze an optical burst switching (OBS) switch endowed with both wavelength converters (WCs) and fiber delay lines (FDLs) to resolve contention. We consider the case where the number of wavelengths is large by introducing a mean field model that provides exact results when the number of wavelengths tends to infinity. We have confirmed through simulations that the mean field model provides accurate approximations for switches with a large but finite number of wavelengths, which are of interest in view of wavelength division multiplexing (WDM). Furthermore, our model allows a very general behavior for the arrival process and the packet size distribution, as well as two different wavelength allocation policies: minimum horizon and minimum gap. Our results include a detailed analysis of the effect that these parameters have on the burst loss rate, and on the minimum number of WCs required to attain a zero loss rate as the number of wavelengths becomes large. We have found that at high loads there is little value in adding FDLs and, if included, shorter granularities result in fewer WCs required to achieve a zero loss rate. The inclusion of FDLs becomes more significant under mid loads and bursty traffic, where the addition of several FDLs may reduce the conversion requirements. Also, increasing the number of WCs under the minimum horizon policy may worsen the This work has been supported by the FWO-Flanders through project "Stochastic modeling of optical buffers and switching systems based on Fiber Delay Lines" (G.0538.07). loss rate, while this is never the case for the minimum gap policy.
“…Although all formulas were found under the assumption of a stable system, note that the heuristic also performs well for overloaded systems, that is, with ρ eq > 1. For a motivation hereof, see [11] (Sect. 3.4).…”
Section: Heuristicmentioning
confidence: 99%
“…Over the years, several authors have developed analytic models for such optical buffers, especially in the case of memoryless arrivals [7][8][9][10][11]. Since arrival processes in (optical) communication networks are known to be bursty, a sep-arate study of the impact of correlation in the arrival process on performance is crucial, but was only given attention to recently.…”
In novel switching approaches such as Optical Burst Switching, the involved buffers can only provide a degenerate waiting room, with delays restricted to multiples of a basic value, the granularity. Although the resulting performance loss was already studied analytically, previous work is either limited by the assumption of independent arrivals, or it involves a matrix with size growing fast with buffer size or arrival process complexity.Overcoming this, we developed a generic and accurate loss performance model for a degenerate GI/G/1 buffer in discrete time, that yields results instantly for any constellation of burst sizes, inter-arrival times, granularity, load and buffer size. This paper presents our model and compares its results to simulations, illustrating the impact of different types of correlation in the arrival process on loss performance. Our basic model is general and accurate, it can thus serve as a basic tool for optical switch design.
“…The effect of wavelength conversion without buffering was studied in [1], while the behavior of FDLs in a switch without converters, i.e., in a single wavelength switch, was treated in [8,9,20]. Introducing FDLs in a multi-wavelength switch drastically increases the complexity of the system and its analysis.…”
This paper presents an approach to evaluate the performance of an optical switch equipped with both limited-range wavelength conversion and Fiber Delay Lines to resolve contention. We propose an analytical model that allows a general behavior for the packet size distribution while the inter-arrival times are assumed to be of PhaseType and can easily be relaxed to be generally distributed if needed. As the set of reachable wavelengths is a major issue in limited-range wavelength conversion, we first focus on a simple wavelength set configuration that allows the comparison of different policies and their effect on the loss rate of the system. In addition, a linear association between the loss rate of the simple and a more complex set configuration is identified. Using this association and the results from the analytical model, we derive an approximation for the more complex case, where the interactions among adjacent wavelengths play an important role. The approximation works well for different parameter instances and is particularly useful for the mid load case, when simulations become computationally prohibitive. This work has been supported by the FWO-Flanders through project "Stochastic modeling of optical buffers and switching systems based on Fiber Delay Lines" (G.0538.07).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.