Davy De Winter

A hybrid thin-client protocol for multimedia streaming and interactive gaming applications

Despite the growing popularity and advantages of thin-client systems, they still have some important shortcomings. Current thin-client systems are ideally suited to be used with classic office-applications but as soon as multimedia and 3D gaming applications are used they require a large amount of bandwidth and processing power. Furthermore, most of these applications heavily rely on the Graphical Processing Unit (GPU). Due to the architectural design of thin-client systems, they cannot profit from the GPU resulting in slow performance and bad image quality. In this paper, we propose a thin-client system which addresses these problems: we introduce a realtime desktopstreamer using a videocodec to stream the graphical output of applications after GPU-processing to a thin-client device, capable of decoding a videostream. We compare this approach to a number of popular classic thin-client systems in terms of bandwidth, delay and image quality. The outcome is an architecture for a hybrid protocol, which can dynamically switch between a classic thin-client protocol and realtime desktopstreaming.

A broad view on overspill routing in optical networks: a real synthesis of packet and circuit switching?

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.

Overspill routing in optical networks: a true hybrid optical network design

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

Optimization models for application migration to support mobile thin clients

Thin clients are lightweight devices from which all hardware, not related to input and output, is removed. Applications are executed on remote servers that render the graphical output and send it back to the client. As the reaction on user events can appear on the screen only after a two-way path delay, thin client computing can suffer from a high latency that degrades the user experience. We therefore propose that the application follows the user through the network by migrating to a server near enough to the user. In this paper, a theoretical model and heuristics are presented to efficiently select servers for mobile users, in order to minimize the number of migrations and the corresponding application downtime. A sample scenario is presented, which clearly exposes the trade-off between the number of migrations and the average client-server latency. We then detail a theoretical model to determine the optimal allocation of applications to servers, in order to minimize the number of handovers. This model is based on the knowledge of the exact user movements and is only useful in an off-line setting. As this is impossible in real-time, several heuristics are presented. Their performance is compared and validated against the theoretical model.

Controlling LSPs in an ORION network

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.

Dimensioning aWide-Area Thin-Client Computing Network Supporting Mobile Users

Battery life-time is a big concern for mobile users. Their devices can save energy when the applications are executed on a remote server, since they only have to display the output on the screen. This method of moving away the calculation logic from the end-user to a server, is the principle on which thin-clients are based. To extend the use of thin-clients to mobile users, the application should be executed on a server, close enough to the user at any time, to guarantee a good responsiveness, i.e. low delay. This paper presents a model to determine the optimal application server locations in a given network topology to support mobile users of thin-clients. Two heuristics are presented to reduce calculation time