Geodesic
Reinforcement Learning - based Adaptation and Scheduling Methods for Multi-source DASH
Computer Science and Information Systems, Tome 20 (2023) no. 1.

Voir la notice de l'article provenant de la source Computer Science and Information Systems website

Dynamic adaptive streaming over HTTP (DASH) has been widely used in video streaming recently. In DASH, the client downloads video chunks in order from a server. The rate adaptation function at the video client enhances the user’s quality-of-experience (QoE) by choosing a suitable quality level for each video chunk to download based on the network condition. Today networks such as content delivery networks, edge caching networks, contentcentric networks, etc. usually replicate video contents on multiple cache nodes. We study video streaming from multiple sources in this work. In multi-source streaming, video chunks may arrive out of order due to different conditions of the network paths. Hence, to guarantee a high QoE, the video client needs not only rate adaptation, but also chunk scheduling. Reinforcement learning (RL) has emerged as the state-of-the-art control method in various fields in recent years. This paper proposes two algorithms for streaming from multiple sources: RL-based adaptation with greedy scheduling (RLAGS) and RL-based adaptation and scheduling (RLAS). We also build a simulation environment for training and evaluation. The efficiency of the proposed algorithms is proved via extensive simulations with real-trace data.
Keywords: multi-source streaming, reinforcement learning, proximal policy optimization, dynamic adaptation streaming over HTTP 
@article{CSIS_2023_20_1_a11,
     author = {Nghia T. Nguyen and Long Luu and Phuong L. Vo and Thi Thanh Sang Nguyen and Cuong T. Do and Ngoc-thanh Nguyen},
     title = {Reinforcement {Learning} - based {Adaptation} and {Scheduling} {Methods} for {Multi-source} {DASH}},
     journal = {Computer Science and Information Systems},
     publisher = {mathdoc},
     volume = {20},
     number = {1},
     year = {2023},
     url = {http://geodesic.mathdoc.fr/item/CSIS_2023_20_1_a11/}
}
TY  - JOUR
AU  - Nghia T. Nguyen
AU  - Long Luu
AU  - Phuong L. Vo
AU  - Thi Thanh Sang Nguyen
AU  - Cuong T. Do
AU  - Ngoc-thanh Nguyen
TI  - Reinforcement Learning - based Adaptation and Scheduling Methods for Multi-source DASH
JO  - Computer Science and Information Systems
PY  - 2023
VL  - 20
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/CSIS_2023_20_1_a11/
ID  - CSIS_2023_20_1_a11
ER  - 
%0 Journal Article
%A Nghia T. Nguyen
%A Long Luu
%A Phuong L. Vo
%A Thi Thanh Sang Nguyen
%A Cuong T. Do
%A Ngoc-thanh Nguyen
%T Reinforcement Learning - based Adaptation and Scheduling Methods for Multi-source DASH
%J Computer Science and Information Systems
%D 2023
%V 20
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/CSIS_2023_20_1_a11/
%F CSIS_2023_20_1_a11
Nghia T. Nguyen; Long Luu; Phuong L. Vo; Thi Thanh Sang Nguyen; Cuong T. Do; Ngoc-thanh Nguyen. Reinforcement Learning - based Adaptation and Scheduling Methods for Multi-source DASH. Computer Science and Information Systems, Tome 20 (2023) no. 1. http://geodesic.mathdoc.fr/item/CSIS_2023_20_1_a11/