Distributed Computing Services at the Internet Edge

Authors:Condry, Michael, Department of Computer ScienceUniversity of Virginia Weaver, Alfred, Department of Computer ScienceUniversity of Virginia

The Internet's current client/server architecture is not well suited to the increasingly complex data types and increasingly diverse media interfaces that characterize the World Wide Web. Each origin server (e. g., an estore) bears the burden of interfacing with all connecting devices (eg., PCs, PDAs, touch-screen kiosks, cell phones, e - book readers) and of satisfying user preferences (e. g., language of presentation) and capabilities (e. g., media speeds). We propose an alternative client/edge server/origin server architecture that distributes some of these services to the network edge in a way that is nevertheless flexible and extensible. Our proposed NetEdge server uses a rule engine to watch data crossing defined processing points, identify requests for service, and provide those services via callouts to specialized software. We predict that vendors will be motivated to create useful services (e. g., language translation, image recoding) because of the revenue stream that a truly useful service can generate.
Note: Abstract extracted from PDF file via OCR

All rights reserved (no additional license for public reuse)
Source Citation:

Condry, Michael, and Alfred Weaver. "Distributed Computing Services at the Internet Edge." University of Virginia Dept. of Computer Science Tech Report (2002).

University of Virginia, Department of Computer Science
Published Date: