New Data Transfer Model Increases Network Traffic Loss Dramatically
The traffic model used in networks affects how well they perform for different types of internet services. The size of files transferred can be small or large, with an average size of 10Kbytes. The study looked at how changing the shape parameter in two arrival models, Poisson and Pareto, affects the average queue size and loss. In the Pareto model, increasing the shape parameter leads to a significant increase in loss, while the impact is smaller in the Poisson model.