Fuzzy Traffic Smoothing: An Approach for Real-time Communication over Ethernet Networks

The paper presents an improvement on existing dynamic traffic smoothing techniques in two respects. Firstly, here the input parameters for the smoother are both the overall throughput and the number of collisions observed over an interval. Together, these two parameters represent a more complete indicator of the actual network workload. Secondly, here the smoothing action is dynamically gauged according to the actual workload by using a fuzzy controller. Experimental results in a real environment, comprising 11 workstations running the Linux OS and connected via a IOBASE-T Ethernet, are presented, together with a performance comparison with a dynamic smoother in the literature.