Experiments of Network Throughput Measurement and Forecasting Using the Network Weather

Authors:
Pascale Primet;Robert Harakaly;Franck Bonnassieux
Affiliations:
-;-;-
Venue:
CCGRID '02 Proceedings of the 2nd IEEE/ACM International Symposium on Cluster Computing and the Grid
Year:
2002

Citing 0
Cited 4

Experiences with predicting resource performance on-line in computational grid settings

ACM SIGMETRICS Performance Evaluation Review
Grid Network Monitoring in the European Datagrid Project

International Journal of High Performance Computing Applications
Fog in the network weather service: a case for novel approaches

Proceedings of the first international conference on Networks for grid applications
Strategies for planning large capillarity broadband networks based on ADSL2+ technology: a case of study for qos-aware triple play services

FMN'10 Proceedings of the Third international conference on Future Multimedia Networking

Quantified Score

Hi-index	0.00

Visualization

Abstract

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