Application of Machine Learning Algorithms for Traffic Forecasting in Dynamic Optical Networks with Service Function Chains
| Autor: | Daniel Szostak, Krzysztof Walkowiak |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
dynamic optical networks
Service (systems architecture) Computer science business.industry media_common.quotation_subject Software development 020206 networking & telecommunications QA75.5-76.95 02 engineering and technology Machine learning computer.software_genre service function chaining machine learning 020210 optoelectronics & photonics Electronic computers. Computer science 0202 electrical engineering electronic engineering information engineering Artificial intelligence traffic prediction Function (engineering) business computer media_common |
| Zdroj: | Foundations of Computing and Decision Sciences, Vol 45, Iss 3, Pp 217-232 (2020) |
| ISSN: | 2300-3405 |
| DOI: | 10.2478/fcds-2020-0012 |
| Popis: | Knowledge about future optical network traffic can be beneficial for network operators in terms of decreasing an operational cost due to efficient resource management. Machine Learning (ML) algorithms can be employed for forecasting traffic with high accuracy. In this paper we describe a methodology for predicting traffic in a dynamic optical network with service function chains (SFC). We assume that SFC is based on the Network Function Virtualization (NFV) paradigm. Moreover, other type of traffic, i.e. regular traffic, can also occur in the network. As a proof of effectiveness of our methodology we present and discuss numerical results of experiments run on three benchmark networks. We examine six ML classifiers. Our research shows that it is possible to predict a future traffic in an optical network, where SFC can be distinguished. However, there is no one universal classifier that can be used for each network. Choice of an ML algorithm should be done based on a network traffic characteristics analysis. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|