arrow
Return

Startup delay aware short video ordering: Problem, model, and a reinforcement learning based algorithm

delete2025-01-17
delete0
delete
OA
AI
Z
Zhipeng Gao
C
Chunxi Li
Y
Yongxiang Zhao *
张
张宝贤 (Baoxian Zhang)
李
李程 (Cheng Li)
DOI:10.1007/s12083-024-01898-2delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Short video applications have attracted billions of users on the Internet and can satisfy diverse users' fragmented spare time with content-rich and duration-short videos. To achieve fast playback at user side, existing short video systems typically enforce burst transmission of initial segment of each video when being requested for improved quality of user experiences. However, such a way of burst transmissions can cause unexpected large startup delays at user side. This is because users may frequently switch videos when sequentially watching a list of short videos recommended by the server side, which can cause excessive burst transmissions of initial segments of different short videos and thus quickly deplete the network transmission capacity. In this paper, we adopt token bucket to characterize the video transmission path between video server and each user, and accordingly study how to effectively reduce the startup delay of short videos by effectively arranging the viewing order of a video list at the server side. We formulate the optimal video ordering problem for minimizing the maximum video startup delay as a combinatorial optimization problem and prove its NP-hardness. We accordingly propose a Partially Shared Actor Critic reinforcement learning algorithm (PSAC) to learn optimized video ordering strategy. Numerical results based on a real dataset provided by a large-scale short video service provider demonstrate that the proposed PSAC algorithm can significantly reduce the video startup delay compared to baseline algorithms.
Keywords:
Short video systems
Startup delay
Video ordering
Token bucket
Reinforcement learning

Journal

Peer-to-Peer Networking and Applications cover
Peer-to-Peer Networking and Applications
IF:
2.6
Papers:
2.2K
Citations:
2.9K

Organization

U
university of chinese academy of sciences, cas
Scholars:
4.1W
Papers: 3.8W
Citations: 75
B
Beijing Jiaotong University
Scholars:
2.2W
Papers: 1.7W
Citations: 1.2W
C
chinese academy of sciences
Scholars:
56.7W
Papers: 45.0W
Citations: 704
researcher View more organizations
Cited Papers

Cited Papers

Compound heterozygous protein C deficiency resulting in the presence of only the beta-form of protein C in plasma
err1996-09-15
err0
errOAAI
errP Simioni; M Kalafatis; DS Millar; SC Henderson; S Luni; DN Cooper; A Girolami
errShare
errSave
Joint Transcoding- and Recommending-Based Video Caching at Network Edges
err2022-09-01
err6
PREAI
errLi, Chunxi; Zhao, Hongna; Zhao, Yongxiang; Zhang, Baoxian; Li, Cheng
errShare
errSave
DUASVS: A Mobile Data Saving Strategy in Short-Form Video Streaming
err2023-03-01
err10
PREAI
errZhang, Guanghui; Zhang, Jie; Liu, Ke; Guo, Jing; Lee, Jack Y. B.; Hu, Haibo; Aggarwal, Vaneet
errShare
errSave
Reinforcement learning for combinatorial optimization: A survey
err2021-10-01
err375
errOAAI
errMazyavkina, Nina; Sviridov, Sergey; Ivanov, Sergei; Burnaev, Evgeny
errShare
errSave
A Survey on Mobile Edge Computing: The Communication Perspective
err2017-01-01
err2.6K
errOAAI
errMao, Yuyi; You, Changsheng; Zhang, Jun; Huang, Kaibin; Letaief, Khaled B.
errShare
errSave
Modeling Effect of a γ-Secretase Inhibitor on Amyloid-β Dynamics Reveals Significant Role of an Amyloid Clearance Mechanism
err2010-04-22
err0
PREAI
errRaibatak Das; Robert B. Nachbar; Leah Edelstein-Keshet; Jeffrey S. Saltzman; Matthew C. Wiener; Ansuman Bagchi; James Bailey; Daniel Coombs; Adam J. Simon; Richard J. Hargreaves; Jacquelynn J. Cook
errShare
errSave
researcher View more