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
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;
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
DOI :
10.1109/CMC.2010.108