The Next Generation of Internetworking

This paper describes a research effort concerned with the design of the next generation of internet architecture, which has been necessitated by two emerging trends. First, there will be at least a few orders of magnitude increase in data rates of communication networks in the next few years. For example, researchers are already prototyping networks with data rates of up to a few hundred Mbps, and are planning networks with data rates up to a few Gbps. Second, researchers from all disciplines of science, engineering, and humanities plan to use the communication infrastructure to access widely distributed resources in order to solve bigger and more complex problems. These trends provide new challenges and opportunities to researchers in the communication field. One such challenge is the design of what we call the very high speed internet (VHSI) abstraction which can help efficiently support guaranteed levels of performance for a variety of applications, and can cope with the ever increasing diversity of underlying networks with rapidly growing user population and needs. Our strategy towards achieving this ambitious goal comprises the following: • Design, specification, and prototype implementation of novel multipoint congram-oriented service that can work well with connection-oriented and datagram high speed networks, can provide variable grade service on a need basis to its applications, and can provide adequate reconfigurability to deal with survivability requirements due to network failures. • Design and implementation of gateway architecture than can support data rates of a few hundred Mbps, can interface with diverse networks, and can implement the congram-oriented service without becoming a performance bottleneck. • Development of analytical and simulation models to evaluate important tradeoffs associated with the design of a congram-oriented protocol, the resource management on diverse networks, and the design of new gateway architectures