The Project
Mission
FAQ
Background

Participants
Researchers
Institutions
Internal site

Communications
News Room
Papers
Project Retreat
     Presentations

100x100 Clean Slate Project

The Internet is one of the most successful technology achievements. In less than 30 years, the Internet has grown from a small experimental network that served as a playground for researchers to a global infrastructure that connects hundreds of millions of people. IP, the technical foundation of Internet, is widely regarded, by both the general and technical communities, to be the convergence technology layer for all communication infrastructures and services. To date, network researchers have focused on solutions that incrementally improve the Internet with the implicit assumption that radical new solutions are not needed or have no chance of ever being deployed.

This project takes the opposite approach. We ask: Given the benefit of hindsight and our current understanding of network requirements and technologies, if we were not bound by existing design decisions and would be able to design the network from first principles (a clean slate design), how should we do it?

The scope of the 100x100 Clean Slate Design Project is necessarily broad, as the design of a network hinges on issues ranging from network architecture and service definition through the design of backbone networks and access networks (both wired and wireless) to network management, security, economics, public policy and switch architecture. However, three themes run through all the project’s research:

• A clean-slate approach: we open up all design decisions for review --- this is a powerful research methodology that helps to crystallize the issues and, by focusing on a specific network that supports 100 Mbps of connectivity between all 100 Million American homes, creates understanding of a desirable future architecture that will help plan the trajectory of evolution towards it.
• Holistic design: we consider the network as a whole. For example, leveraging technology trends, we do a top-down decomposition of the network into large regional access networks interconnected by a small number of richly connected regional nodes. Also, we explicitly consider economics, dependability, and security issues while architecting the network.
• Leveraging network structure: we concurrently develop both structures for network topology and protocols that take advantage of these structures to achieve dependable, simple, and analyzable networks.