DocumentCode
517364
Title
Study on Prediction Model for Buffer Memory Based on SVM
Author
Ling, Yongfa ; Gao, Yali
Author_Institution
Sch. of Electr. & Commun. Eng., Yunnan Univ. of Nat., Kunming, China
Volume
1
fYear
2010
fDate
12-14 April 2010
Firstpage
513
Lastpage
516
Abstract
The key to high performance network design is the ability to build model and make prediction for performance parameters. Configuration of buffer memory directly influences the delay and loss rate of network. Good match between buffer memory of network and network capacity will improve performance of network. Therefore, in this paper, Support Vector Machine (SVM) is used to predict the business flow data of network, and sample is trained for distribution rules of data beyond sample. Then, prediction model for queue buffer memory of network is designed. It is suggested by experimental data that the model is of high training efficiency and prediction accuracy.
Keywords
buffer storage; computer network performance evaluation; support vector machines; SVM; buffer memory configuration; buffer memory prediction model; high performance network design; network business flow data; network capacity; network delay; network loss rate; performance parameters; queue buffer memory; support vector machine; Accuracy; Computer networks; Design engineering; High performance computing; IP networks; Mobile communication; Mobile computing; Prediction algorithms; Predictive models; Support vector machines;
fLanguage
English
Publisher
ieee
Conference_Titel
Communications and Mobile Computing (CMC), 2010 International Conference on
Conference_Location
Shenzhen
Print_ISBN
978-1-4244-6327-5
Electronic_ISBN
978-1-4244-6328-2
Type
conf
DOI
10.1109/CMC.2010.108
Filename
5471424
Link To Document