The paper presents the concept of a rough fuzzy controller for traffic management in ATM networks. It is a very complex task due to the random nature of the traffic arrival parameters and the character of butst duration. We present the rough fuzzy controller, which contains the knowledge base described in linguistic terms. The relationship between decision rules and inference rules are interpreted from the rough set theory perspective. The presented approach may be treated as an alternative to artificial neural networks and fuzzy set theory.
展开▼