Flow-level prediction of 100 random topologies and flows based on statistical methods.

What is it about?

Modeling extreme latencies in communication net-works can contribute information to network planning and flow admission under service level agreements. Extreme Value Theory is such an approach that utilizes real-world measurement data. It is often applied without verifying the resulting model predictions on larger datasets. Here we show that such models can provide accurate predictions over larger datasets while being applied to 100 random network topologies and configurations. We found that applying derived models with a bounded tail to a twentyfold time period results in a prediction accuracy of 75% for extreme latency exceedances. Furthermore, we show that tail latency quantiles can be predicted on a flow level with median absolute percentage errors ranging from 0.7% to 16.8%. Therefore, we consider this approach to be useful for dimensioning networks under latency-constrained service level agreements.

Featured Image

Why is it important?

Able to predict the tail-latency behavior of flows over time enables to use a small amount of measurement data and length of measurements to predict the behavior over a longer time. This allows operators to use the prediction to plan their SLOs and provide benefit to customers.

Perspectives