Experiments of Network Throughput Measurement and Forecasting Using the Network Weather

Abstract

A tool able to predict the behavior of the network in a Global computing environment could help the users to obtain better performance. In this paper we study the accuracy of the Network Weather Service (NWS) networking features and specifically the TCP throughput measurement and prediction. We studied the NWS forecast stability and confidence level on different types of networking connectivity. To examine how the predicted values can be applied to "bulk" transfer, the prediction was compared with results of measurements achieved with the Iperf network monitoring tool. Iperf results are more accurate than the NWS ones but the tool is much more intrusive. We propose an improvement to use its predicting feature in an internet based global computing environment.