Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction
Rapid growth of network traffic causes the need for the development of new network technologies. Artificial intelligence provides suitable tools to improve currently used network optimization methods. In this paper, we propose a procedure for network traffic prediction. Based on optical networks’ (a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/13/1578 |
| _version_ | 1797528203688935424 |
|---|---|
| author | Daniel Szostak Adam Włodarczyk Krzysztof Walkowiak |
| author_facet | Daniel Szostak Adam Włodarczyk Krzysztof Walkowiak |
| author_sort | Daniel Szostak |
| collection | DOAJ |
| description | Rapid growth of network traffic causes the need for the development of new network technologies. Artificial intelligence provides suitable tools to improve currently used network optimization methods. In this paper, we propose a procedure for network traffic prediction. Based on optical networks’ (and other network technologies) characteristics, we focus on the prediction of fixed bitrate levels called traffic levels. We develop and evaluate two approaches based on different supervised machine learning (ML) methods—classification and regression. We examine four different ML models with various selected features. The tested datasets are based on real traffic patterns provided by the Seattle Internet Exchange Point (SIX). Obtained results are analyzed using a new quality metric, which allows researchers to find the best forecasting algorithm in terms of network resources usage and operational costs. Our research shows that regression provides better results than classification in case of all analyzed datasets. Additionally, the final choice of the most appropriate ML algorithm and model should depend on the network operator expectations. |
| first_indexed | 2024-03-10T09:54:50Z |
| format | Article |
| id | doaj.art-7e3d78f4572548869335f5a7b5784b4a |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T09:54:50Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-7e3d78f4572548869335f5a7b5784b4a2023-11-22T02:26:34ZengMDPI AGElectronics2079-92922021-06-011013157810.3390/electronics10131578Machine Learning Classification and Regression Approaches for Optical Network Traffic PredictionDaniel Szostak0Adam Włodarczyk1Krzysztof Walkowiak2Faculty of Electronics, Wrocław University of Science and Technology, Wybrzeże Wyspiańskiego 27, 50-370 Wrocław, PolandFaculty of Electronics, Wrocław University of Science and Technology, Wybrzeże Wyspiańskiego 27, 50-370 Wrocław, PolandFaculty of Electronics, Wrocław University of Science and Technology, Wybrzeże Wyspiańskiego 27, 50-370 Wrocław, PolandRapid growth of network traffic causes the need for the development of new network technologies. Artificial intelligence provides suitable tools to improve currently used network optimization methods. In this paper, we propose a procedure for network traffic prediction. Based on optical networks’ (and other network technologies) characteristics, we focus on the prediction of fixed bitrate levels called traffic levels. We develop and evaluate two approaches based on different supervised machine learning (ML) methods—classification and regression. We examine four different ML models with various selected features. The tested datasets are based on real traffic patterns provided by the Seattle Internet Exchange Point (SIX). Obtained results are analyzed using a new quality metric, which allows researchers to find the best forecasting algorithm in terms of network resources usage and operational costs. Our research shows that regression provides better results than classification in case of all analyzed datasets. Additionally, the final choice of the most appropriate ML algorithm and model should depend on the network operator expectations.https://www.mdpi.com/2079-9292/10/13/1578optical networkstraffic forecastingmachine learningclassificationregression |
| spellingShingle | Daniel Szostak Adam Włodarczyk Krzysztof Walkowiak Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction Electronics optical networks traffic forecasting machine learning classification regression |
| title | Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction |
| title_full | Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction |
| title_fullStr | Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction |
| title_full_unstemmed | Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction |
| title_short | Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction |
| title_sort | machine learning classification and regression approaches for optical network traffic prediction |
| topic | optical networks traffic forecasting machine learning classification regression |
| url | https://www.mdpi.com/2079-9292/10/13/1578 |
| work_keys_str_mv | AT danielszostak machinelearningclassificationandregressionapproachesforopticalnetworktrafficprediction AT adamwłodarczyk machinelearningclassificationandregressionapproachesforopticalnetworktrafficprediction AT krzysztofwalkowiak machinelearningclassificationandregressionapproachesforopticalnetworktrafficprediction |