A fuzzy logic based approach to multipriority control in ATM networks

Abstract

The priority control function in ATM networks allows users to generate traffic flows with different priorities by using the Cell Loss Priority (CLP) bit. The implementation of this function, however, represents a hard task as the network has to guarantee the Quality of Service (QoS) of the higher priority traffic regardless of the presence of low-priority traffic and, at the same time, to reach an efficient use of network resources. The conventional schemes proposed so far suffer from some limitations either in performance (threshold mechanisms) or in feasible implementation (push-out scheme). We propose a queue management strategy based on fuzzy logic, which combines high performance, guaranteeing the QoS requirements and increasing the throughput, with a low implementation cost. In the paper, we assess the fuzzy mechanism by considering several traffic scenarios ranging from bursty traffic to MPEG video traffic. The presented results show that our mechanism is robust and outperforms conventional mechanisms.