Neural Network Models for Internet Traffic Prediction
This paper presents a view of models used for Internet data (traffic) prediction using neural network applications. We look at the problem of traffic prediction in the presence of self-similarity. Self-similarity is an important characteristic of traffic in high-speed networks that cannot be captured by traditional traffic models. Our experiments inspect performance using multilayer perceptrons and radial basis function networks. Ill. 1, bibl. 4 (in English; summaries in English, Russian and Lithuanian).
Copyright terms are indicated in the Republic of Lithuania Law on Copyright and Related Rights, Articles 4-37.