A fuzzy expert system for usage parameter control in ATM networks

In ATM networks usage parameter control is required in order to ensure that each source conforms to its negotiated parameters. However, traditional methods, such as leaky bucket and window mechanisms, revealed themselves to be inefficient in coping with the conflicting requirements of the ideal policing. We propose a fuzzy expert system for usage parameter control. The control strategy is described through a set of fuzzy inferences which emulate the knowledge base that is typical of human expertize. The simulation results shown in the paper demonstrate that our fuzzy policer outperforms conventional policing mechanisms.