<abstract xmlns="http://www.w3.org/1999/xhtml"><p>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.</p></abstract>

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.

Application of Machine Learning Algorithms for Traffic Forecasting in Dynamic Optical Networks with Service Function Chains

Wrocław University of Science and Technology

Department of Systems and Computer Networks

Foundations of Computing and Decision Sciences

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Knowledge about future optical network traffic can be beneficial for network operators in terms of decreasing an operational cost due to efficient resource...

Application of Machine Learning Algorithms for Traffic Forecasting in Dynamic Optical Networks with Service Function Chains

Data publikacji: 18 wrz 2020

Zakres stron: 217 - 232

Otrzymano: 29 lut 2020

Przyjęty: 10 lip 2020

DOI: https://doi.org/10.2478/fcds-2020-0012

Słowa kluczowe
Dynamic Optical Networks, Traffic Prediction, Service Function Chaining, Machine Learning

© 2020 Daniel Szostak et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Application of Machine Learning Algorithms for Traffic Forecasting in Dynamic Optical Networks with Service Function Chains

Data publikacji: 18 wrz 2020

Zakres stron: 217 - 232

Otrzymano: 29 lut 2020

Przyjęty: 10 lip 2020

DOI: https://doi.org/10.2478/fcds-2020-0012

Słowa kluczoweDynamic Optical Networks, Traffic Prediction, Service Function Chaining, Machine Learning

© 2020 Daniel Szostak et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Słowa kluczowe
Dynamic Optical Networks, Traffic Prediction, Service Function Chaining, Machine Learning