Q-Learning Based Content Placement Method for Dynamic Cloud Content Delivery Networks
How to reduce the content placement cost of cloud content delivery networks (CCDNs) is a hot topic in recent years. Traditional content placement methods mainly reduce the cost of content placement by constructing delivery trees, but they cannot adapt to the dynamic deployment of cloud proxy servers...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8717626/ |
id |
doaj-2a7cd7c2fef741d69fa72bc3d9f3eeeb |
---|---|
record_format |
Article |
spelling |
doaj-2a7cd7c2fef741d69fa72bc3d9f3eeeb2021-03-29T23:32:20ZengIEEEIEEE Access2169-35362019-01-017663846639410.1109/ACCESS.2019.29175648717626Q-Learning Based Content Placement Method for Dynamic Cloud Content Delivery NetworksYujie Liu0https://orcid.org/0000-0002-2372-8737Dianjie Lu1Guijuan Zhang2https://orcid.org/0000-0002-9545-8668Jie Tian3Weizhi Xu4College of Information Science and Engineering, Shandong Normal University, Jinan, ChinaCollege of Information Science and Engineering, Shandong Normal University, Jinan, ChinaCollege of Information Science and Engineering, Shandong Normal University, Jinan, ChinaCollege of Information Science and Engineering, Shandong Normal University, Jinan, ChinaCollege of Information Science and Engineering, Shandong Normal University, Jinan, ChinaHow to reduce the content placement cost of cloud content delivery networks (CCDNs) is a hot topic in recent years. Traditional content placement methods mainly reduce the cost of content placement by constructing delivery trees, but they cannot adapt to the dynamic deployment of cloud proxy servers in the CCDNs. In addition, the traditional content placement method only provides delivery paths according to local decision-making without considering global dynamics of the congestion in the CCDNs, which is also one of the main factors causing high cost of content placement. To solve these problems, we propose a content placement model based on Q-learning for the dynamic CCDNs, called Q-content placement model (Q-CPM). This Q-learning approach can lead to better routing decisions due to up-to-date and more reliable congestion values. Then, based on the Q-CPM model, an algorithm is proposed to construct the Q-adaptive delivery tree (Q-ADT). In this algorithm, local and nonlocal congestion information is propagated over network learning packets. Through this algorithm, the paths with low congestion cost will be selected and can adapt to the dynamic cloud delivery environment. The experimental results show that the method can adapt to the dynamic changes of the CCDNs flexibly and reduce the overall congestion cost of content placement effectively.https://ieeexplore.ieee.org/document/8717626/Content placementdynamic CCDNscongestion informationQ-learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yujie Liu Dianjie Lu Guijuan Zhang Jie Tian Weizhi Xu |
spellingShingle |
Yujie Liu Dianjie Lu Guijuan Zhang Jie Tian Weizhi Xu Q-Learning Based Content Placement Method for Dynamic Cloud Content Delivery Networks IEEE Access Content placement dynamic CCDNs congestion information Q-learning |
author_facet |
Yujie Liu Dianjie Lu Guijuan Zhang Jie Tian Weizhi Xu |
author_sort |
Yujie Liu |
title |
Q-Learning Based Content Placement Method for Dynamic Cloud Content Delivery Networks |
title_short |
Q-Learning Based Content Placement Method for Dynamic Cloud Content Delivery Networks |
title_full |
Q-Learning Based Content Placement Method for Dynamic Cloud Content Delivery Networks |
title_fullStr |
Q-Learning Based Content Placement Method for Dynamic Cloud Content Delivery Networks |
title_full_unstemmed |
Q-Learning Based Content Placement Method for Dynamic Cloud Content Delivery Networks |
title_sort |
q-learning based content placement method for dynamic cloud content delivery networks |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
How to reduce the content placement cost of cloud content delivery networks (CCDNs) is a hot topic in recent years. Traditional content placement methods mainly reduce the cost of content placement by constructing delivery trees, but they cannot adapt to the dynamic deployment of cloud proxy servers in the CCDNs. In addition, the traditional content placement method only provides delivery paths according to local decision-making without considering global dynamics of the congestion in the CCDNs, which is also one of the main factors causing high cost of content placement. To solve these problems, we propose a content placement model based on Q-learning for the dynamic CCDNs, called Q-content placement model (Q-CPM). This Q-learning approach can lead to better routing decisions due to up-to-date and more reliable congestion values. Then, based on the Q-CPM model, an algorithm is proposed to construct the Q-adaptive delivery tree (Q-ADT). In this algorithm, local and nonlocal congestion information is propagated over network learning packets. Through this algorithm, the paths with low congestion cost will be selected and can adapt to the dynamic cloud delivery environment. The experimental results show that the method can adapt to the dynamic changes of the CCDNs flexibly and reduce the overall congestion cost of content placement effectively. |
topic |
Content placement dynamic CCDNs congestion information Q-learning |
url |
https://ieeexplore.ieee.org/document/8717626/ |
work_keys_str_mv |
AT yujieliu qlearningbasedcontentplacementmethodfordynamiccloudcontentdeliverynetworks AT dianjielu qlearningbasedcontentplacementmethodfordynamiccloudcontentdeliverynetworks AT guijuanzhang qlearningbasedcontentplacementmethodfordynamiccloudcontentdeliverynetworks AT jietian qlearningbasedcontentplacementmethodfordynamiccloudcontentdeliverynetworks AT weizhixu qlearningbasedcontentplacementmethodfordynamiccloudcontentdeliverynetworks |
_version_ |
1724189284837097472 |