Quality Enhanced Multimedia Content Delivery for Mobile Cloud with Deep Reinforcement Learning
The importance of multimedia streaming using mobile devices has increased considerably. The dynamic adaptive streaming over HTTP is an efficient scheme for bitrate adaptation in which video is segmented and stored in different quality levels. The multimedia streaming with limited bandwidth and varyi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi-Wiley
2019-01-01
|
Series: | Wireless Communications and Mobile Computing |
Online Access: | http://dx.doi.org/10.1155/2019/5038758 |
id |
doaj-c28e3590c0784464884b1333120db088 |
---|---|
record_format |
Article |
spelling |
doaj-c28e3590c0784464884b1333120db0882020-11-25T01:55:21ZengHindawi-WileyWireless Communications and Mobile Computing1530-86691530-86772019-01-01201910.1155/2019/50387585038758Quality Enhanced Multimedia Content Delivery for Mobile Cloud with Deep Reinforcement LearningMuhammad Saleem0Yasir Saleem1H. M. Shahzad Asif2M. Saleem Mian3Department of Computer Science and Engineering, University of Engineering and Technology, Lahore 54890, PakistanDepartment of Computer Science and Engineering, University of Engineering and Technology, Lahore 54890, PakistanDepartment of Computer Science and Engineering, University of Engineering and Technology, Lahore 54890, PakistanFaculty of Electrical Engineering, University of Engineering and Technology, Lahore 54890, PakistanThe importance of multimedia streaming using mobile devices has increased considerably. The dynamic adaptive streaming over HTTP is an efficient scheme for bitrate adaptation in which video is segmented and stored in different quality levels. The multimedia streaming with limited bandwidth and varying network environment for mobile users affects the user quality of experience. We have proposed an adaptive rate control using enhanced Double Deep Q-Learning approach to improve multimedia content delivery by switching quality level according to the network, device, and environment conditions. The proposed algorithm is thoroughly evaluated against state-of-the-art heuristic and learning-based algorithms. The performance metrics such as PSNR, SSIM, quality of experience, rebuffering frequency, and quality variations are evaluated. The results are obtained using real network traces which shows that the proposed algorithm outperforms the other schemes in all considered quality metrics. The proposed algorithm provides faster convergence to the optimal solution as compared to other algorithms considered in our work.http://dx.doi.org/10.1155/2019/5038758 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Muhammad Saleem Yasir Saleem H. M. Shahzad Asif M. Saleem Mian |
spellingShingle |
Muhammad Saleem Yasir Saleem H. M. Shahzad Asif M. Saleem Mian Quality Enhanced Multimedia Content Delivery for Mobile Cloud with Deep Reinforcement Learning Wireless Communications and Mobile Computing |
author_facet |
Muhammad Saleem Yasir Saleem H. M. Shahzad Asif M. Saleem Mian |
author_sort |
Muhammad Saleem |
title |
Quality Enhanced Multimedia Content Delivery for Mobile Cloud with Deep Reinforcement Learning |
title_short |
Quality Enhanced Multimedia Content Delivery for Mobile Cloud with Deep Reinforcement Learning |
title_full |
Quality Enhanced Multimedia Content Delivery for Mobile Cloud with Deep Reinforcement Learning |
title_fullStr |
Quality Enhanced Multimedia Content Delivery for Mobile Cloud with Deep Reinforcement Learning |
title_full_unstemmed |
Quality Enhanced Multimedia Content Delivery for Mobile Cloud with Deep Reinforcement Learning |
title_sort |
quality enhanced multimedia content delivery for mobile cloud with deep reinforcement learning |
publisher |
Hindawi-Wiley |
series |
Wireless Communications and Mobile Computing |
issn |
1530-8669 1530-8677 |
publishDate |
2019-01-01 |
description |
The importance of multimedia streaming using mobile devices has increased considerably. The dynamic adaptive streaming over HTTP is an efficient scheme for bitrate adaptation in which video is segmented and stored in different quality levels. The multimedia streaming with limited bandwidth and varying network environment for mobile users affects the user quality of experience. We have proposed an adaptive rate control using enhanced Double Deep Q-Learning approach to improve multimedia content delivery by switching quality level according to the network, device, and environment conditions. The proposed algorithm is thoroughly evaluated against state-of-the-art heuristic and learning-based algorithms. The performance metrics such as PSNR, SSIM, quality of experience, rebuffering frequency, and quality variations are evaluated. The results are obtained using real network traces which shows that the proposed algorithm outperforms the other schemes in all considered quality metrics. The proposed algorithm provides faster convergence to the optimal solution as compared to other algorithms considered in our work. |
url |
http://dx.doi.org/10.1155/2019/5038758 |
work_keys_str_mv |
AT muhammadsaleem qualityenhancedmultimediacontentdeliveryformobilecloudwithdeepreinforcementlearning AT yasirsaleem qualityenhancedmultimediacontentdeliveryformobilecloudwithdeepreinforcementlearning AT hmshahzadasif qualityenhancedmultimediacontentdeliveryformobilecloudwithdeepreinforcementlearning AT msaleemmian qualityenhancedmultimediacontentdeliveryformobilecloudwithdeepreinforcementlearning |
_version_ |
1724983719789330432 |