RL-based adaptive live video streaming for academic event

Chuhua Xiang; Dan Yang

doi:10.1117/12.3009563

16 October 2023 RL-based adaptive live video streaming for academic event

Chuhua Xiang, Dan Yang

Proceedings Volume 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023); 128033V (2023) https://doi.org/10.1117/12.3009563
Event: 2023 5th International Conference on Artificial Intelligence and Computer Science (AICS 2023), 2023, Wuhan, China

Abstract

Under the Covid-19 epidemic’s influence, academic events must be conducted online through live broadcasts. Therefore, improving the live user quality experience is vital for academic activities. However, in most live streaming, users suffer from low quality, frequent buffering, and long delays. ABR algorithm is one of the economic methods to solve the above problems. This paper models the ABR problem through mathematical formalization and designs an ABR solution and framework called RL-LIVE based on reinforcement learning. Secondly, we published the training data set with features of academic activities and the platform required for training. Finally, after evaluation, the RL-based ABR algorithm has a performance improvement of 7.5%-23% in various scenarios.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Chuhua Xiang and Dan Yang "RL-based adaptive live video streaming for academic event", Proc. SPIE 12803, Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023), 128033V (16 October 2023); https://doi.org/10.1117/12.3009563

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available