Network Bandwidth Usage Forecast in Content Delivery Networks

Aykut Teker; Ahmet Haydar Ornek; Berk Canberk

doi:10.1109/CoBCom49975.2020.9174180

Network Bandwidth Usage Forecast in Content Delivery Networks

Aykut Teker, Ahmet Haydar Ornek, Berk Canberk

Şişli/İ

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Operational burden of a Content Delivery Network that is a vast overlay network on top of current Internet Architecture can be alleviated by forecasting Content Delivery Network bandwidths. The purpose of this paper is to forecast network bandwidth usage for Content Delivery Networks' Points of Presence. In this paper we compare Seasonal Auto-Regressive Integrated Moving Averages and Artificial Neural Networks that can be used for predicting and minimizing operational costs of Content Delivery Networks via resource allocation, server allotment and local ISP bandwidth contract costs. We directly forecast end-user to Content Delivery Network bandwidth, so it can directly be used to lower end-user latencies. In this paper; we first conduct Self-Similarity Analysis and then utilize Seasonal Auto-Regressive Integrated Moving Averages and Artificial Neural Networks to predict bandwidth usage with 6.338% error.

Original language	English
Title of host publication	CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728174921
DOIs	https://doi.org/10.1109/CoBCom49975.2020.9174180
Publication status	Published - Jul 2020
Externally published	Yes
Event	3rd International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications, CoBCom 2020 - Graz, Austria Duration: 7 Jul 2020 → 9 Jul 2020

Publication series

Name	CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings

Conference

Conference	3rd International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications, CoBCom 2020
Country/Territory	Austria
City	Graz
Period	7/07/20 → 9/07/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

artificial neural networks
content delivery networks
seasonal auto-regressive integrated moving averages
traffic modelling

Access to Document

10.1109/CoBCom49975.2020.9174180

Cite this

Teker, A., Ornek, A. H., & Canberk, B. (2020). Network Bandwidth Usage Forecast in Content Delivery Networks. In CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings Article 9174180 (CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CoBCom49975.2020.9174180

Teker, Aykut ; Ornek, Ahmet Haydar ; Canberk, Berk. / Network Bandwidth Usage Forecast in Content Delivery Networks. CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. (CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings).

@inproceedings{211931acf51f412792fbd8f072a11cc4,

title = "Network Bandwidth Usage Forecast in Content Delivery Networks",

abstract = "Operational burden of a Content Delivery Network that is a vast overlay network on top of current Internet Architecture can be alleviated by forecasting Content Delivery Network bandwidths. The purpose of this paper is to forecast network bandwidth usage for Content Delivery Networks' Points of Presence. In this paper we compare Seasonal Auto-Regressive Integrated Moving Averages and Artificial Neural Networks that can be used for predicting and minimizing operational costs of Content Delivery Networks via resource allocation, server allotment and local ISP bandwidth contract costs. We directly forecast end-user to Content Delivery Network bandwidth, so it can directly be used to lower end-user latencies. In this paper; we first conduct Self-Similarity Analysis and then utilize Seasonal Auto-Regressive Integrated Moving Averages and Artificial Neural Networks to predict bandwidth usage with 6.338% error.",

keywords = "artificial neural networks, content delivery networks, seasonal auto-regressive integrated moving averages, traffic modelling",

author = "Aykut Teker and Ornek, {Ahmet Haydar} and Berk Canberk",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 3rd International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications, CoBCom 2020 ; Conference date: 07-07-2020 Through 09-07-2020",

year = "2020",

month = jul,

doi = "10.1109/CoBCom49975.2020.9174180",

language = "English",

series = "CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings",

address = "United States",

}

Teker, A, Ornek, AH & Canberk, B 2020, Network Bandwidth Usage Forecast in Content Delivery Networks. in CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings., 9174180, CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings, Institute of Electrical and Electronics Engineers Inc., 3rd International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications, CoBCom 2020, Graz, Austria, 7/07/20. https://doi.org/10.1109/CoBCom49975.2020.9174180

Network Bandwidth Usage Forecast in Content Delivery Networks. / Teker, Aykut; Ornek, Ahmet Haydar; Canberk, Berk.
CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9174180 (CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Network Bandwidth Usage Forecast in Content Delivery Networks

AU - Teker, Aykut

AU - Ornek, Ahmet Haydar

AU - Canberk, Berk

PY - 2020/7

Y1 - 2020/7

N2 - Operational burden of a Content Delivery Network that is a vast overlay network on top of current Internet Architecture can be alleviated by forecasting Content Delivery Network bandwidths. The purpose of this paper is to forecast network bandwidth usage for Content Delivery Networks' Points of Presence. In this paper we compare Seasonal Auto-Regressive Integrated Moving Averages and Artificial Neural Networks that can be used for predicting and minimizing operational costs of Content Delivery Networks via resource allocation, server allotment and local ISP bandwidth contract costs. We directly forecast end-user to Content Delivery Network bandwidth, so it can directly be used to lower end-user latencies. In this paper; we first conduct Self-Similarity Analysis and then utilize Seasonal Auto-Regressive Integrated Moving Averages and Artificial Neural Networks to predict bandwidth usage with 6.338% error.

AB - Operational burden of a Content Delivery Network that is a vast overlay network on top of current Internet Architecture can be alleviated by forecasting Content Delivery Network bandwidths. The purpose of this paper is to forecast network bandwidth usage for Content Delivery Networks' Points of Presence. In this paper we compare Seasonal Auto-Regressive Integrated Moving Averages and Artificial Neural Networks that can be used for predicting and minimizing operational costs of Content Delivery Networks via resource allocation, server allotment and local ISP bandwidth contract costs. We directly forecast end-user to Content Delivery Network bandwidth, so it can directly be used to lower end-user latencies. In this paper; we first conduct Self-Similarity Analysis and then utilize Seasonal Auto-Regressive Integrated Moving Averages and Artificial Neural Networks to predict bandwidth usage with 6.338% error.

KW - artificial neural networks

KW - content delivery networks

KW - seasonal auto-regressive integrated moving averages

KW - traffic modelling

UR - http://www.scopus.com/inward/record.url?scp=85092298024&partnerID=8YFLogxK

U2 - 10.1109/CoBCom49975.2020.9174180

DO - 10.1109/CoBCom49975.2020.9174180

M3 - Conference contribution

AN - SCOPUS:85092298024

T3 - CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings

BT - CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications, CoBCom 2020

Y2 - 7 July 2020 through 9 July 2020

ER -

Teker A, Ornek AH, Canberk B. Network Bandwidth Usage Forecast in Content Delivery Networks. In CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9174180. (CoBCom 2020 - International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications - Proceedings). doi: 10.1109/CoBCom49975.2020.9174180

Network Bandwidth Usage Forecast in Content Delivery Networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this