Using fuzzy rules for network behavior identification: application for differentiated services in an Ethernet network

The Quality of Service (QoS) offered by a network is based on criteria such as delay, jitter and message loss. QoS management is crucial to ensure that the network respects the communication constraints defined by the application requirements. The network must dynamically manage QoS according to the evolution of network usage. To control QoS, the network implements mechanisms to schedule and regulate traffic. The main issue is identifying the relationship between these mechanisms and their effects on QoS values. The objective of this paper is to propose a method, based on fuzzy logic, for identifying this relationship and reusing it to dynamically control QoS. This study only focuses on the impact of the Weighted Round Robin (WRR) scheduler on the delay in a switched Ethernet network. The fuzzy controller is implemented in a network simulation tool (Riverbed Modeler) to efficiently manage the delay in the network.