NeTS-FIND Collaborative Research: Enabling Future Internet innovations through Transit wire (eFIT)

点击翻译按钮获取中文摘要

The eFIT (Enabling Future Internet innovations through Transit wire) project aims to enable future innovations by ensuring strong universal connectivity at the architectural level. Innovations are enabled by the abundant and affordable computing resources provided by Moore's Law, and universal connectivity provided by the Internet. Computing resources are likely to become more plentiful and affordable, but the universal connectivity provided by the Internet is facing major challenges, as demonstrated by the prevalent use of network address translation (NAT) and accelerated growth of the global routing table. The current Internet architecture provides end-to-end connectivity by putting both user networks and Internet service providers (ISPs) in the same address and routing spaces. User networks and ISPs have different purposes, distinct characteristics, and are moving in almost opposite technological directions. However the inter-dependency between network users and ISPs imposed by the existing architecture creates a major roadblock to future Internet innovations.When a system grows larger in size by orders of magnitude, a change in form becomes necessary. The eFIT design enables innovation by first focusing on universal connectivity. eFIT places user networks and provider networks in different address and routing spaces, removing the inter-dependency between the two worlds. With eFIT, users can simply treat the Internet transit core as a transit wire with strong universal connectivity, while providers are insulated from the various problems caused by explosive growth in user networks. Therefore both users and providers will be able to innovate freely on their own without any architectural constraints.Broader Impact: This new architecture design will have a broad impact on the research community, service providers, and Internet users. eFIT enables graduate students to explore new directions for fundamental problems such as security. Even more broadly, it will liberate Internet users from the current architectural constraints and encourage a new wave of application innovations.