IEICE TRANSACTIONS on Information
PDAA3C: An A3C-Based Multi-Path Data Scheduling Algorithm
Summary :
In this letter, a path dynamics assessment asynchronous advantage actor-critic scheduling algorithm (PDAA3C) is proposed to solve the MPTCP scheduling problem by using deep reinforcement learning Actor-Critic framework. The algorithm picks out the optimal transmitting path faster by multi-core asynchronous updating and also guarantee the network fairness. Compared with the existing algorithms, the proposed algorithm achieves 8.6% throughput gain over RLDS algorithm, and approaches the theoretic upper bound in the NS3 simulation.
- Publication
- IEICE TRANSACTIONS on Information Vol.E105-D No.12 pp.2127-2130
- Publication Date
- 2022/12/01
- Publicized
- 2022/09/13
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2022EDL8052
- Type of Manuscript
- LETTER
- Category
- Fundamentals of Information Systems
Authors
Teng LIANG
Zhejiang Sci-Tech University
Ao ZHAN
Zhejiang Sci-Tech University
Chengyu WU
Zhejiang Sci-Tech University
Zhengqiang WANG
Chongqing University of Posts and Telecommunication
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Teng LIANG, Ao ZHAN, Chengyu WU, Zhengqiang WANG, "PDAA3C: An A3C-Based Multi-Path Data Scheduling Algorithm" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 12, pp. 2127-2130, December 2022, doi: 10.1587/transinf.2022EDL8052.
Abstract: In this letter, a path dynamics assessment asynchronous advantage actor-critic scheduling algorithm (PDAA3C) is proposed to solve the MPTCP scheduling problem by using deep reinforcement learning Actor-Critic framework. The algorithm picks out the optimal transmitting path faster by multi-core asynchronous updating and also guarantee the network fairness. Compared with the existing algorithms, the proposed algorithm achieves 8.6% throughput gain over RLDS algorithm, and approaches the theoretic upper bound in the NS3 simulation.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDL8052/_p
Copy
@ARTICLE{e105-d_12_2127,
author={Teng LIANG, Ao ZHAN, Chengyu WU, Zhengqiang WANG, },
journal={IEICE TRANSACTIONS on Information},
title={PDAA3C: An A3C-Based Multi-Path Data Scheduling Algorithm},
year={2022},
volume={E105-D},
number={12},
pages={2127-2130},
abstract={In this letter, a path dynamics assessment asynchronous advantage actor-critic scheduling algorithm (PDAA3C) is proposed to solve the MPTCP scheduling problem by using deep reinforcement learning Actor-Critic framework. The algorithm picks out the optimal transmitting path faster by multi-core asynchronous updating and also guarantee the network fairness. Compared with the existing algorithms, the proposed algorithm achieves 8.6% throughput gain over RLDS algorithm, and approaches the theoretic upper bound in the NS3 simulation.},
keywords={},
doi={10.1587/transinf.2022EDL8052},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - PDAA3C: An A3C-Based Multi-Path Data Scheduling Algorithm
T2 - IEICE TRANSACTIONS on Information
SP - 2127
EP - 2130
AU - Teng LIANG
AU - Ao ZHAN
AU - Chengyu WU
AU - Zhengqiang WANG
PY - 2022
DO - 10.1587/transinf.2022EDL8052
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2022
AB - In this letter, a path dynamics assessment asynchronous advantage actor-critic scheduling algorithm (PDAA3C) is proposed to solve the MPTCP scheduling problem by using deep reinforcement learning Actor-Critic framework. The algorithm picks out the optimal transmitting path faster by multi-core asynchronous updating and also guarantee the network fairness. Compared with the existing algorithms, the proposed algorithm achieves 8.6% throughput gain over RLDS algorithm, and approaches the theoretic upper bound in the NS3 simulation.
ER -
English
