ERAS: Efficient, Robust, Adaptive, and Scalable Service Composition in Overlay Networks

Jin, Jingwen; Nahrstedt, Klara

Permalink

https://hdl.handle.net/2142/11026 Copy

Description

Title

ERAS: Efficient, Robust, Adaptive, and Scalable Service Composition in Overlay Networks

Author(s)

• Jin, Jingwen
• Nahrstedt, Klara

Issue Date

2005-05

Keyword(s)

networking

Abstract

The importance of the component service model has been widely recognized in the Internet community due to its high flexibility in creating customized applications from primitive services in a plug-and-play manner. Deployment of such a service model in the wide area networks spawns a new type of routing problem - QoS service-added routing, that is far more complex than the traditional QoS routing problem, especially when multicast comes into play to save resources. We study this special routing problem in overlay networks, and provide an Efficient, Robust, Adaptive, and Scalable (ERAS) service composition framework that (1) optimizes composite services' runtime performance-related aspects (e.g., network bandwidths, path delay, machine resources), which is of great importance to wide-area applications, especially to those that are resource-consuming (e.g., multimedia applications); optimizes global resource usage in one-to-many application scenarios by means of multicast (service multicast and hybrid multicast), to eliminate redundancies in data delivery and service executions; (2) is robust against network failures; (3) adapts to network and membership dynamics; and (4) scales to large networks.

Type of Resource

text

Permalink

http://hdl.handle.net/2142/11026

Copyright and License Information

You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the University of Illinois at Urbana-Champaign Computer Science Department under terms that include this permission. All other rights are reserved by the author(s).

Owning Collections