We describe the architecture, design, and implementation of a novel just-in-time (JIT) signaling protocol for optical burst switching (OBS) in wavelength division multiplexed (WDM) optical networks. The JIT-OBS paradigm is designed for ultra-low-latency unidirectional transport of data-bursts across an optical network. It combines the desirable features of circuit-switching and packet-switching. It features out-of-band control signal processing that eliminates buffering of data-burst at intermediate nodes, while minimizing the setup time, and maximizing the cross-connect bandwidth efficiency.We motivate and describe the architecture of JIT signaling, and analyze its basic performance. We present the detailed signaling message design and discuss the rationale and considerations that went into this design. We describe and examine various scenarios that illustrate the operations of the JIT signaling protocol (JIT-SP) in connection establishment and teardown. Finally, we describe and summarize the JIT signaling software prototype in the Washington, DC Testbed network implemented under the MONET project.

In this paper, we give an overview and classification of optical burst switching schemes and present burst reservation concepts. The performance of various basic reservation mechanisms proposed in literature is compared. Furthermore, a new analysis is introduced that allows to calculate the loss probabilities of a two-class system based on the reservation mechanism just-enough-time (JET) for arbitrary offsets. Finally, a variety of new results is presented including the dependence of burst loss probabilities on offset, burst length distribution, and interarrival distribution. Keywords Optical burst switching, reservation mechanisms, performance analysis, quality of service, IP over WDM. 1. Introduction At the beginning of the new millenium several trends can be observed in the field of communication networks. First, bandwidth requirement in networks seems to grow without limits. Internet protocol (IP) based data networks play a central role. This is not only due to the fact that dat...

this paper is organized as follows: section 2. introduces the functionality and design issues of OBS and shortly resumes the reservation mechanism JET that allows service differentiation. In section 3. an approximative analysis for the burst loss probability for an arbitrary number of classes and arbitrary QoS offsets is presented. In section 4. we evaluate the performance of different scenarios by analysis and simulation. The focus lies on burst characteristics resulting from an assembly process at the edge of the optical network. Furthermore, we discuss service differentiation for various parameters in an OBS network scenario

The concept of optical burst switching (OBS) aims to allow access to optical bandwidth in dense wavelength division multiplexed (DWDM) networks at fractions of the optical line rate to improve bandwidth utilization efficiency. This paper studies an alternative network architecture combining OBS with dynamic wavelength allocation under fast circuit switching to provide a scalable optical architecture with a guaranteed QoS in the presence of dynamic and bursty traffic loads. In the proposed architecture, all processing and buffering are concentrated at the network edge and bursts are routed over an optical transport core using dynamic wavelength assignment. It is assumed that there are no buffers or wavelength conversion in core nodes and that fast tuneable laser sources are used in the edge routers. This eliminates the forwarding bottleneck of electronic routers in DWDM networks for terabit-per-second throughput and guarantees forwarding with predefined delay at the edge and latency due only to propagation time in the core. The edge burst aggregation mechanisms are evaluated for a range of traffic statistics to identify their impact on the allowable burst lengths, required buffer size and achievable edge delays. Bandwidth utilization and wavelength reuse are introduced as new parameters characterizing the network performance in the case of dynamic wavelength allocation. Based on an analytical model, upper bounds for these parameters are derived to quantify the advantages of wavelength channel reuse, including the influence of the signaling round-trip time required for lightpath reservation. The results allow to quantify the operational gain achievable with fast wavelength switching compared to quasistatic wavelength-routed optical networks and can be applied to the desig...

This paper provides a framework for analysis and performance evaluation of Optical Burst Switching (OBS) networks. In particular, a new reduced load fixed point approximation model to evaluate blocking probabilities in OBS networks is introduced. The model is versatile enough to cover known OBS reservation policies such as Just-Enough-Time (JET), Just-InTime (JIT), Burst Segmentation and Route-dependent Priorities. The accuracy of the model is confirmed by simulation and the various policies are compared.

We consider an edge optical burst switching (OBS) node with or without converters, and with no buffering. The OBS node serves a number of users, each connected to the switch over a fiber link that supports multiple wavelengths. Each wavelength is associated with a 3-state Markovian burst arrival process. The arrival process permits short and long bursts to be modeled. We model the edge OBS node as a closed non-product-form queueing network, with multiple heterogeneous classes, and we develop a suite of approximate decomposition algorithms to analyze it. Our approximate algorithms have a good accuracy, and they provide insight into the effect of various system parameters on the performance of the edge OBS node.

In this letter, we analyze optical burst switching (OBS) systems. The analysis leads to a framework which provides guidelines for OBS design. We identify conditions for OBS feasibility and the relationship between burst size, or equivalently burst assembly delay, and throughput, taking into consideration control packet processing and the number of available wavelengths per fiber.

In this paper, we give an overview and classification of optical burst switching schemes and burst reservation concepts. We compare the performance of different burst reservation mechanisms for an OBS node that does not distinguish different classes. The one that performed best and allows service differentiation, called Just-Enough-Time, is then evaluated by simulations and an approximative analysis for a two-class OBS node. A variety of new results show the pros and cons of the evaluated reservation mechanism with respect to service differentiation. 1

We present a detailed analysis of the JIT, JET, and Horizon wavelength reservation schemes for optical burst switched (OBS) networks. Our analysis accounts for several important parameters, including the burst o#set length, and the optical switching and hardware processing overheads associated with bursts as they travel across the network. The contributions of our work include: (i) analytical models of JET and Horizon (on a single OBS node) that are more accurate than previously published ones, and which are valid for general burst length and o#set length distributions; and (ii) the determination of the regions of parameter values in which a more complex reservation scheme reduces to a simpler one. We compare the performance of the three wavelength reservation schemes on a single OBS node under various sets of parameter values. Our major finding is that, under reasonable assumptions regarding the current and future state-of-the-art in optical switch and electronic hardware technologies, the simplicity of JIT seems to outweigh any performance benefits of Horizon and JET.

We present a detailed analysis of the JIT, JET, and Horizon wavelength reservation schemes for optical burst switched (OBS) networks. Our analysis accounts for several important parameters, including the burst o#set length, and the optical switching and hardware processing overheads associated with bursts as they travel across the network. The contributions of our work include: (i) analytical models of JET and Horizon (on a single OBS node) that are more accurate than previously published ones, and which are valid for general burst length and o#set length distributions; (ii) the determination of the regions of parameter values in which a more complex reservation scheme reduces to a simpler one; and (iii) a new reservation scheme, JIT , which is as simple to implement as JIT, but whose performance tracks that of Horizon and JET. We compare the performance of the four wavelength reservation schemes on a single OBS node, as well as on a path of OBS nodes with cross tra#c, under various sets of parameter values.