Simplified layering and flexible bandwidth with TWIN

Abstract

This paper describes a novel network architecture with simplified layering, called Time-domain Wavelength Interleaved Networking (TWIN), that scales end-to-end bandwidth granularity exibly up to the wavelength capacity. In TWIN, all packet and complex processing functions are pushed to the network edge such that the network core only has to deal with an optical forwarding layer. Furthermore, by avoiding fast optical switching and optical buffering in the core through scheduling fast-tunable lasers and buffering packets at the edge, TWIN effectively makes the network act like a switch. We examine distributed network scheduling for this architecture and show its performance via analysis and simulation. We also explore other research issues that are unique in TWIN.