Optical Burst Switching (OBS) is a new paradigm for future all-optical networks. OBS networks are difficult to investigate analytically, so most of the current research is based on simulations. This has created a need for accurate traffic sources. In this paper, we present an overview of different traffic sources and
make a distinction between simulating burst assembly and generating bursts (where no information about burst contents is carried). The following types of sources are discussed: emulating assembled traffic using exponentially distributed burst length and interarrival time, emulating assembled traffic with burst length and interarrival time distributions and burst assembly simulation with LRD input traffic. We discuss advantages and disadvantages of each approach, mainly
in respect to its efficiency. For example, simulating burst assembly with LRD input traffic, while considered perfect in terms of quality of produced traffic, is also the least effective and requires long simulation times. We show the area of applicability of each type
of traffic generator, comparing it to a small number of burst assemblers, or to highly aggregated OBS traffic. We also present two new types of traffic sources: one that can generate traffic with LRD properties in a much more efficient way than full burst assembly simulation, and one that uses conditional burts length and
interarrival time distributions. Finally, simulation results are presented to confirm our findings.
Optical Burst Switching (OBS) is a new paradigm for future all-optical networks. It has been noted that performance of an OBS node depends on the wavelength assignment algorithm that is used. In this paper we present a new class of wavelength allocation algorithms
called cost-based algorithms. We note that bursts compete for more types of resources than wavelengths alone. For example if a given burst is to be allocated successfully, a Fiber Delay Line (FDL) or a wavelength converter may have to be used. It can be expected,
however, that the set of available resources will be limited. If at a given time all the converters are used, then any arriving burst will have to be allocated on the same wavelength - if it is available. Similarly, the unavailability of FDLs will decrease the probability of a burst being accepted. In a cost-based algorithm, each resource is assigned a metric (or price). Channels are priced according to their suitability for a particular burst. When a control packet arrives at a core node, all the possible ways of handling the corresponding burst are found (the outgoing channel, with or without a FDL or wavelength converter), and the one with a lowest metric is chosen. To show how the performance of a cost-based algorithm
compares to other algorithms we present the results of our simulations for a node with full conversion capability and a shared FDL.