Abstract

Optical packet switching (OPS) is a promising technology for future networks. However, optical packet contention is a major problem in an OPS network. Resolution and avoidance are two schemes that can deal with the contention problem. A resolution scheme, as a reactive approach, resolves collisions, while an avoidance scheme, as a proactive approach, tries to reduce the number of potential collision events. Therefore, many contention controllers using neural networks have been proposed to control the output contention problem within a learning approach. In this article, we survey the contention resolution and avoidance schemes proposed for OPS networks. We also review some contention controller propositions using neural network techniques for solving the output contention problem in OPS.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call