Machine Learning Empowered Content Delivery: Status, Challenges, and Opportunities

Zhihui Lu; Keke Gai; Qiang Duan; Kim Kwang Raymond Choo; Junnan Li; Jie Wu; Yajing Xu

doi:10.1109/MNET.011.2000141

Machine Learning Empowered Content Delivery: Status, Challenges, and Opportunities

Zhihui Lu, Keke Gai, Qiang Duan, Kim Kwang Raymond Choo, Junnan Li, Jie Wu, Yajing Xu

Division of Engineering and Science (Abington)

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

Trends such as increasing mobile device ownership and faster and more affordable internet speed have contributed to significant demands in media-based services on mobile devices. There has been an emphasis on content delivery networks to support media-based services. However, achieving high-performance content delivery in large-scale dynamic network environments is still operationally challenging, especially when we have to consider the diverse application requirements. One emerging research trend is to explore the use of machine learning techniques to enhance content delivery quality. in this article, we review and discuss existing state of the art machine learning-based approaches on enhancing content delivery performance. Discussions in this article will benefit readers and help identify future research agendas and opportunities.

Original language	English (US)
Article number	9220172
Pages (from-to)	228-234
Number of pages	7
Journal	IEEE Network
Volume	34
Issue number	6
DOIs	https://doi.org/10.1109/MNET.011.2000141
State	Published - Nov 1 2020

All Science Journal Classification (ASJC) codes

Software
Information Systems
Hardware and Architecture
Computer Networks and Communications

Access to Document

10.1109/MNET.011.2000141

Cite this

@article{2f96eb95244b49cda04aa6852166cfce,

title = "Machine Learning Empowered Content Delivery: Status, Challenges, and Opportunities",

abstract = "Trends such as increasing mobile device ownership and faster and more affordable internet speed have contributed to significant demands in media-based services on mobile devices. There has been an emphasis on content delivery networks to support media-based services. However, achieving high-performance content delivery in large-scale dynamic network environments is still operationally challenging, especially when we have to consider the diverse application requirements. One emerging research trend is to explore the use of machine learning techniques to enhance content delivery quality. in this article, we review and discuss existing state of the art machine learning-based approaches on enhancing content delivery performance. Discussions in this article will benefit readers and help identify future research agendas and opportunities. ",

author = "Zhihui Lu and Keke Gai and Qiang Duan and Choo, {Kim Kwang Raymond} and Junnan Li and Jie Wu and Yajing Xu",

note = "Funding Information: Acknowledgment The work of this article is supported by the National Key Research and Development Program of China (2019YFB1405000); the National Natural Science Foundation of China under Grant No. 61873309, No. 61972034, No. 61572137, and No. 61728202; the Shanghai Science and Technology Innovation Action Plan Project under Grant No.19510710500, No. 18510732000, and No.18510760200; the Natural Science Foundation of Beijing Municipality (Grant No. 20D20116); and the Natural Science Foundation of Shandong Province (Grant No. ZR2019ZD10). This work is also partially supported by the project: PCL Future Greater Bay Area Network Facilities for Large Scale Experiments and Applications LZC 0019. Publisher Copyright: {\textcopyright} 1986-2012 IEEE.",

year = "2020",

month = nov,

day = "1",

doi = "10.1109/MNET.011.2000141",

language = "English (US)",

volume = "34",

pages = "228--234",

journal = "IEEE Network",

issn = "0890-8044",

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

number = "6",

}

TY - JOUR

T1 - Machine Learning Empowered Content Delivery

T2 - Status, Challenges, and Opportunities

AU - Lu, Zhihui

AU - Gai, Keke

AU - Duan, Qiang

AU - Choo, Kim Kwang Raymond

AU - Li, Junnan

AU - Wu, Jie

AU - Xu, Yajing

N1 - Funding Information: Acknowledgment The work of this article is supported by the National Key Research and Development Program of China (2019YFB1405000); the National Natural Science Foundation of China under Grant No. 61873309, No. 61972034, No. 61572137, and No. 61728202; the Shanghai Science and Technology Innovation Action Plan Project under Grant No.19510710500, No. 18510732000, and No.18510760200; the Natural Science Foundation of Beijing Municipality (Grant No. 20D20116); and the Natural Science Foundation of Shandong Province (Grant No. ZR2019ZD10). This work is also partially supported by the project: PCL Future Greater Bay Area Network Facilities for Large Scale Experiments and Applications LZC 0019. Publisher Copyright: © 1986-2012 IEEE.

PY - 2020/11/1

Y1 - 2020/11/1

N2 - Trends such as increasing mobile device ownership and faster and more affordable internet speed have contributed to significant demands in media-based services on mobile devices. There has been an emphasis on content delivery networks to support media-based services. However, achieving high-performance content delivery in large-scale dynamic network environments is still operationally challenging, especially when we have to consider the diverse application requirements. One emerging research trend is to explore the use of machine learning techniques to enhance content delivery quality. in this article, we review and discuss existing state of the art machine learning-based approaches on enhancing content delivery performance. Discussions in this article will benefit readers and help identify future research agendas and opportunities.

AB - Trends such as increasing mobile device ownership and faster and more affordable internet speed have contributed to significant demands in media-based services on mobile devices. There has been an emphasis on content delivery networks to support media-based services. However, achieving high-performance content delivery in large-scale dynamic network environments is still operationally challenging, especially when we have to consider the diverse application requirements. One emerging research trend is to explore the use of machine learning techniques to enhance content delivery quality. in this article, we review and discuss existing state of the art machine learning-based approaches on enhancing content delivery performance. Discussions in this article will benefit readers and help identify future research agendas and opportunities.

UR - http://www.scopus.com/inward/record.url?scp=85092930210&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85092930210&partnerID=8YFLogxK

U2 - 10.1109/MNET.011.2000141

DO - 10.1109/MNET.011.2000141

M3 - Article

AN - SCOPUS:85092930210

SN - 0890-8044

VL - 34

SP - 228

EP - 234

JO - IEEE Network

JF - IEEE Network

IS - 6

M1 - 9220172

ER -

Machine Learning Empowered Content Delivery: Status, Challenges, and Opportunities

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this