To efficiently support the highly dynamic traffic patterns of the current Internet in large-scale switches, we propose a new hybrid optical network design: Overspill Routing In Optical Networks (ORION). By taking advantage of the reduced (electronic) processing requirements of all-optical wavelength switching, the electronic bottleneck is relieved. At the same time, ORION achieves a level of statistical multiplexing comparable to the more traditional point to point WDM solutions, circumventing the bandwidth inefficiencies of all-optical wavelength switched networks, caused by dynamic traffic patterns. The result is a true hybrid optical network design, forming a bridge between these two switching concepts. In this paper the generic concept of ORION is described. An example node design, based on current advanced optical technologies, is described in detail. The ORION concept is also evaluated, comparing it with its two composing technologies, optical wavelength switching and point to point WDM, as well as a third, more trivial, hybrid one, through several case studies

The emerging wavelength switched networks reduce the strain on packet forwarding. Unfortunately, that solution is not really efficient on a bandwidth level, and is not ideally suited for bursty traffic. Packet switched solutions, whether electronic or optical, can use statistical multiplexing to cope with bursty traffic and yield better bandwidth efficiency. We present a novel network concept that can combine these two worlds, withholding their advantages. We introduce this Overspill Routing In Optical Networks (ORION), and discuss several aspects of it: the overall architecture and network concept, node design and implementation, and evaluation at network level as well as node level.

The emerging wavelength switched networks reduce the strain on packet forwarding. Unfortunately, that solution is not really efficient on a bandwidth level, and is not ideally suited for bursty traffic. Packet switched solutions, whether electronic or optical, can use statistical multiplexing to cope with bursty traffic and yield better bandwidth efficiency. In earlier work we presented a novel network concept, Overspill Routing In Optical Networks (ORION), that can combine these two worlds, withholding their advantages. In this document we further evaluate the benefits of this architecture, focusing on ORION over a predimensioned groomed topology. This is a latex adaption to the word template.

Overspill routing in optical networks, ORION, is a network architecture combining lower IP switching capacity requirements with high bandwidth efficiencies. We present results from an ORION emulation platform, which is fully compatible with GMPLS. (2 pages)

Optical Packet Switching can cope well with the bursty nature of data traffic that is becoming predominant. OPS nodes will be used in a network, where traffic demand will show a growth evolution. In stead of immediately installing a large OPS node that is only sparsely used in the first years, we prefer solutions allowing the switch to grow as traffic demand grows. We look into modular, multi-stage solutions for two well-known OPS node designs. We evaluate the cost evolution for different design choices, using several scenarios. We show that multistage OPS node designs can result in cheaper, modular upgradeable designs.

We come back on a technique to build modular switch nodes. This approach allows for a more cost effective expansion of OPS nodes. We give two example designs, showing that the method is useful only for Broadcast & Select OPS nodes when taking price decrease in function of time into account.

Grid computing offers high levels of computational, storage and network capacity by bundling and sharing resources through a uniform interface. In its current form, Grids are restricted to only a small application area, and deployment proceeds mainly for specific problems. However, if Grids are to become as ubiquitous as electrical power delivery by making it available to the public at large, several network-related problems will have to be solved first. In this paper, we show the limitations of the currently deployed optical networks, by evaluating future applications for the Grid. Subsequently, we propose a novel architecture based on Optical Burst Switching, and clearly show the advantages of our approach.

While the technological evolution since C. Clos's seminal article (see Bell Sys. Tech. J., vol.32, p.406-24, 1953) on multistage switch architectures has been huge, his work and ideas still live on. We discuss node architectures for optical packet switching and show how the multistage approach proposed by Clos can be adopted to solve scalability issues and construct switches with large port counts. As in the old days, the driving factors behind the introduction of multistage concepts also include economic issues: compared to a single-stage architecture, the number of components to realize the switching fabric is reduced.

Within the STOLAS project, an EC-funded project in the 5th Framework Programme which has recently been concluded, an orthogonal optical labeling scheme using Frequency Shift Keying modulation for the 155 Mbit/s label and intensity modulation for the 10 Gbit/s payload data has been explored. This scheme enables to improve the throughput of packet-switched networks by efficient label processing, and by optical routing of the payload of the packet bursts. The label-swapping is done in intensitydriven wavelength converters, deploying cross-phase modulation in SOAs implemented in an MZI configuration. The packet bursts are switched by means of passive waveguide routers, as a function of their wavelength. The paper addresses the networking aspects of this FSK/IM orthogonal labeling scheme, and discusses the advantages and disadvantages when comparing it with alternative schemes. The key components for implementing an orthogonal labelcontrolled router node are addressed, as well as the node architecture, its economical aspects, and experimental results obtained. The impact of these results on the upgradability and the scalability of a network deploying orthogonal labeling are discussed, and the prospects for application in future high-capacity optical packetswitched networks. A first deployment of this labeling technique may be made in hybrid circuit-packet-switched networks, e.g. for routing of overspill packets.

Grid computing offers high levels of computational, stor- age and network capacity by bundling and sharing re- sources through a uniform interface. In its current form, Grids are restricted to only a small application area, and deployment proceeds mainly for specific problems. How- ever, if Grids are to become as ubiquitous as electrical power delivery by making it available to the public at large, several network-related problems will have to be solved first. In this paper, we show the limitations of the cur- rently deployed optical networks, by evaluating future ap- plications for the Grid. Subsequently, we propose a novel architecture based on Optical Burst Switching, and clearly show the advantages of our approach.

Previously we introduced a novel network paradigm: Overspill Routing In Optical Networks (ORION), which combined the advantages of circuit and packet switching. It has a low packet processing load on IP-routers and an efficient wavelength usage in the transport network. We have reported on extensive network dimensioning studies. We now zoom in on a node level, where packet streams can be studied in some more detail. We present a case study showing the effectiveness of ORION.

To support the highly dynamic traffic patterns of the current Internet in large- scale switches efficiently, earlier work proposed a new hybrid optical network design: Overspill Routing In Optical Networks (ORION). This network concept takes advantage of the reduced (electronic) processing requirements of all- optical wavelength switched concepts, thereby relieving the electronic switching bottleneck. At the same time, ORION achieves a level of statistical multiplexing comparable to the more traditional point-to-point WDM solutions, circumventing the bandwidth inefficiencies, caused by dynamic traffic patterns, of all-optical wavelength switched networks. In this paper we demonstrate how the relative trade-offs of (standard) ORION and other technologies, wavelength switched WDM, point to point WDM and composed, change as a function of the dynamism of the applied traffic (i.e. changing burstiness). We also show the effect of increasing wavelength capacities, and thus bandwidth granularity.

This paper discusses and evaluates, in terms of number of wavelength channels and router port count, different grooming strategies exploiting the benefits of statistical multiplexing. For the network design, a hybrid solution, combining the advantages of both the end-to-end and the link-by-link grooming scenario, is proposed.

New networking paradigms try to combine packet switching and circuit switching, keeping the best of both worlds and getting rid of the drawbacks. One promising technology is overspill routing in optical networks (ORION). In this paper we develop a control technique to set up LSPs in this novel network environment. It is based on the GMPLS paradigm and needs no extra control messages.

Advances in both computer hardware and software has given end users access to increasingly complex applications. However, this evolution imposes a continuous cycle of replacement and renewal of infrastructure, which is both in terms of required resources as from an economical viewpoint a wasteful process. We aim to eliminate this inefficiency through the use of consumer grids, in which users are given access to powerful computing and storage resources, all connected through a high-performance optical burst switched network. Since these consumer grids should be accessible by the public at large, the main requirements are massive scalability, a robust design, and the delivery of non-trivial amounts of computing resources. We show how the basic functional requirements of our architecture can be realised, and demonstrate several extensions which permit the full spectrum of end user applications on our platform. Keywords—grid computing, optical burst switching, anycast routing

Optical packet/burst switching is considered a promising technique to improve the performance of optical networks. Key components in these technologies are the optical switching nodes. Some of these node architectures suffer from internal blocking. Synchronous operation allows overcoming most of the problems introduced by this internal blocking. However, in asynchronous networks internal blocking can have a more pronounced effect. In this paper, we propose a windowing technique to improve the performance of internally blocking optical switching nodes in asynchronous operation. Simulations will show significant improvements can be made.