Collaborative Research: NeTS-FIND: Postcards from the Edge: A Cache-and-Forward Architecture for the Future Internet

University Of Massachusetts Amherst, Amherst MA

Investigators

Abstract

Proposal Number: 0626959 PI: Roy Yates Institution: Rutgers University Proposal Number: 0626874 PI: James Kurose Institution: University of Massachusetts Title: Collaborative NeTS-FIND: Postcards from the Edge: A Cache-and-Forward Architecture for the Future Internet Abstract This project develops a cache-and-forward network architecture that exploits the decreasing cost and increasing capacity of storage devices to provide unified and efficient transport services to end hosts that may be wired or wireless; static, mobile, and/or intermittently disconnected; and either resource rich or poor. Fundamental to this architecture is a transport layer service that operates in a hop-by-hop store-and-forward manner with large files. To realize this architecture, this project designs, implements and evaluates a new network architecture that incorporates the following elements: (1) reliable hop-by-hop transport of large files; (2) push-pull architecture for opportunistic delivery of files both to and from the wired network; (3) enhanced naming to provide location information for mobile terminals; and (4) distributed caching of popular content to make peer-to-peer file sharing a first-class service and to enable efficient reliable multicast. The experimental evaluation phase of the project, based on extensive use of PlanetLab, the ORBIT radio grid testbed and real world environments supported by future experimental systems, examines network performance trade-offs for various potential protocol design choices and usage/traffic scenarios. The technical merit of this project is in the complementary mix of architectural design, the development of macroscopic models quantifying the performance benefits of architectural components, and a prototype implementation and experimental validation of key architectural innovations. The broader impact of this project is its contribution towards the definition and selection of one or more protocol architectures for the future Internet, leading to new services and applications of value to both scientific and commercial end users.