Online Learning and Placement Algorithms for Efficient Delivery of User Generated Contents in Telco-CDNs
(2019) In IEEE Transactions on Network and Service Management 17(1). p.637-651- Abstract
- User generated content (UGC) makes up a significant portion of Internet traffic. As opposed to other content, UGC has so far been left outside over-the-top providing network operators content distribution networks (telco-CDN) due to the difficulty in determining optimised placement of such content. The side effect of this is that UGC content is not placed close to end users and therefore occupy unnecessary network resources. The difficulty in determining optimal placement of UGC stems from the different geographical and dynamic behaviour of the content generators, and a further complication is that with UGC, it is necessary to place content in real-time which this has an impact on performance optimality. Even though CDNs have been widely... (More)
- User generated content (UGC) makes up a significant portion of Internet traffic. As opposed to other content, UGC has so far been left outside over-the-top providing network operators content distribution networks (telco-CDN) due to the difficulty in determining optimised placement of such content. The side effect of this is that UGC content is not placed close to end users and therefore occupy unnecessary network resources. The difficulty in determining optimal placement of UGC stems from the different geographical and dynamic behaviour of the content generators, and a further complication is that with UGC, it is necessary to place content in real-time which this has an impact on performance optimality. Even though CDNs have been widely studied in the literature, little attention has been given to the challenging case of UGC placement. In this paper, we propose an on-line placement algorithm and compare its performance with the off-line counterpart based on integer programming, both under the assumption that the popularity of content is known to the algorithms. In order to determine the popularity, we present an on-line learning model to predict spatial patterns in content requests. Furthermore, we couple the model with an algorithm for learning the early popularity of content, i.e. shortly after the content becomes known. We show that together, these approaches enable service providers to effectively place UGC and minimise the cost of serving UGC in their networks. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3da7e8ae-4bfa-4984-ac80-50b99d94cacc
- author
- Safavi, Mohammadhassan LU ; Bastani, Saeed LU and Landfeldt, Björn LU
- organization
- publishing date
- 2019-12-23
- type
- Contribution to journal
- publication status
- published
- subject
- in
- IEEE Transactions on Network and Service Management
- volume
- 17
- issue
- 1
- pages
- 637 - 651
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- scopus:85082039074
- ISSN
- 1932-4537
- DOI
- 10.1109/TNSM.2019.2961560
- language
- English
- LU publication?
- yes
- id
- 3da7e8ae-4bfa-4984-ac80-50b99d94cacc
- date added to LUP
- 2019-12-19 11:35:28
- date last changed
- 2022-04-18 19:43:59
@article{3da7e8ae-4bfa-4984-ac80-50b99d94cacc, abstract = {{User generated content (UGC) makes up a significant portion of Internet traffic. As opposed to other content, UGC has so far been left outside over-the-top providing network operators content distribution networks (telco-CDN) due to the difficulty in determining optimised placement of such content. The side effect of this is that UGC content is not placed close to end users and therefore occupy unnecessary network resources. The difficulty in determining optimal placement of UGC stems from the different geographical and dynamic behaviour of the content generators, and a further complication is that with UGC, it is necessary to place content in real-time which this has an impact on performance optimality. Even though CDNs have been widely studied in the literature, little attention has been given to the challenging case of UGC placement. In this paper, we propose an on-line placement algorithm and compare its performance with the off-line counterpart based on integer programming, both under the assumption that the popularity of content is known to the algorithms. In order to determine the popularity, we present an on-line learning model to predict spatial patterns in content requests. Furthermore, we couple the model with an algorithm for learning the early popularity of content, i.e. shortly after the content becomes known. We show that together, these approaches enable service providers to effectively place UGC and minimise the cost of serving UGC in their networks.}}, author = {{Safavi, Mohammadhassan and Bastani, Saeed and Landfeldt, Björn}}, issn = {{1932-4537}}, language = {{eng}}, month = {{12}}, number = {{1}}, pages = {{637--651}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, series = {{IEEE Transactions on Network and Service Management}}, title = {{Online Learning and Placement Algorithms for Efficient Delivery of User Generated Contents in Telco-CDNs}}, url = {{http://dx.doi.org/10.1109/TNSM.2019.2961560}}, doi = {{10.1109/TNSM.2019.2961560}}, volume = {{17}}, year = {{2019}}, }