Using Network Application Behavior to Predict Performance

Chunling Ma

ISBN 10: 3639059603 / ISBN 13: 9783639059601

Published by VDM Verlag Dr. Müller, 2009

About this Item

nach der Bestellung gedruckt Neuware - Printed after ordering - Today's continuously growing Internet requires usersand network applications to have knowledge of networkmetrics.This knowledge is critical for decisionmaking during the usage of network applications.Thisthesis studies application related networkmetrics.The major approach in this work is to examinethe traffic between a simulated user.We use thehistorical data collected from previous usage ofnetwork applications to make predictions for futureusage of those applications.Prediction mechanismsrequire us to make parameter choices so that certainweights can be placed on historical data versuscurrent data.We study these different choices and usethe values from our best experimental results.Fromthese studies we conclude that our data prediction isquite accurate and remains stable over a range ofparameter choices.The use of shared routing pathsbetween users and network applications are exploredin the performance prediction of applications.Thenetwork applications studied are also varied,including web, streaming, DNS.We see whether sharinginformation obtained from different applications canbe used to make predictions of application performance.

Seller Inventory # 9783639059601

Bibliographic Details

• Title: Using Network Application Behavior to Predict Performance
• Publisher: VDM Verlag Dr. Müller
• Publication Date: 2009
• Language: English
• ISBN 10: 3639059603
• ISBN 13: 9783639059601
• Binding: Taschenbuch
• Condition: Neu
• Dimensions: 22W x 15H x 0.8D centimeters 22 centimeters width by 15 centimeters height by 0.8 centimeters depth
• Weight: 225 grams

About this title

Synopsis

Today's continuously growing Internet requires users and network applications to have knowledge of network metrics.This knowledge is critical for decision making during the usage of network applications.This thesis studies application related network metrics.The major approach in this work is to examine the traffic between a simulated user.We use the historical data collected from previous usage of network applications to make predictions for future usage of those applications.Prediction mechanisms require us to make parameter choices so that certain weights can be placed on historical data versus current data.We study these different choices and use the values from our best experimental results.From these studies we conclude that our data prediction is quite accurate and remains stable over a range of parameter choices.The use of shared routing paths between users and network applications are explored in the performance prediction of applications.The network applications studied are also varied, including web, streaming, DNS.We see whether sharing information obtained from different applications can be used to make predictions of application performance.

About the Author

Chunling Ma obtained her master's degree in computer science at Worcester Polytechnic Institute in Worcester,Massachusetts of the United States.She earned her bachelor's degree in computer science at Shenyang Institute of Technology in Shenyang, China.She is currently working as a storage performance engineer at EMC, a world leading storage company