AoI and Throughput Optimization for Hybrid Traffic in Cellular Uplink Using Reinforcement Learning

Chien Cheng Wu; Zheng Hua Tan; Cedomir Stefanovic

doi:10.1109/VTC2022-Spring54318.2022.9861011

AoI and Throughput Optimization for Hybrid Traffic in Cellular Uplink Using Reinforcement Learning

Chien Cheng Wu, Zheng Hua Tan, Cedomir Stefanovic

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

Abstract

The fast growth of time-sensitive applications calls for the optimization of radio access network (RAN) scheduling. We consider the problem of RAN scheduling of a mix of periodic and burst traffic and design a reinforcement learning method for the age of information and throughput optimization. The periodic traffic is generated with a fixed frequency and the burst traffic is generated by the Poisson Pareto Burst Process. We firstly formulate the scheduling problem as a non-linear integer programming problem. Then, we focus on the reinforcement learning method modeling and solve it via the Proximal Policy Optimization algorithm. Our evaluations show that the suggested reinforcement algorithm outperforms the classical algorithms without any prior knowledge of the arriving traffic.

Original language	English
Title of host publication	2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings
Publisher	IEEE
Publication date	2022
Article number	9861011
ISBN (Electronic)	9781665482431
DOIs	https://doi.org/10.1109/VTC2022-Spring54318.2022.9861011
Publication status	Published - 2022
Event	95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring - Helsinki, Finland Duration: 19 Jun 2022 → 22 Jun 2022

Conference

Conference	95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring
Country/Territory	Finland
City	Helsinki
Period	19/06/2022 → 22/06/2022
Sponsor	Huawei Technologies Co., Ltd., Nokia Siemens Networks, pix moving, Samsung, Technology Innovation Institute (TII)

Series	IEEE Vehicular Technology Conference
Volume	2022-June
ISSN	1550-2252

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Age of Information
Burst Traffic
Periodic Traffic
Proximal Policy Optimization
Reinforcement Learning
Time-sensitive communications

Access to Document

10.1109/VTC2022-Spring54318.2022.9861011

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{232281b606734b8e98748779425b0152,

title = "AoI and Throughput Optimization for Hybrid Traffic in Cellular Uplink Using Reinforcement Learning",

abstract = "The fast growth of time-sensitive applications calls for the optimization of radio access network (RAN) scheduling. We consider the problem of RAN scheduling of a mix of periodic and burst traffic and design a reinforcement learning method for the age of information and throughput optimization. The periodic traffic is generated with a fixed frequency and the burst traffic is generated by the Poisson Pareto Burst Process. We firstly formulate the scheduling problem as a non-linear integer programming problem. Then, we focus on the reinforcement learning method modeling and solve it via the Proximal Policy Optimization algorithm. Our evaluations show that the suggested reinforcement algorithm outperforms the classical algorithms without any prior knowledge of the arriving traffic.",

keywords = "Age of Information, Burst Traffic, Periodic Traffic, Proximal Policy Optimization, Reinforcement Learning, Time-sensitive communications",

author = "Wu, {Chien Cheng} and Tan, {Zheng Hua} and Cedomir Stefanovic",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring ; Conference date: 19-06-2022 Through 22-06-2022",

year = "2022",

doi = "10.1109/VTC2022-Spring54318.2022.9861011",

language = "English",

series = "IEEE Vehicular Technology Conference",

publisher = "IEEE",

booktitle = "2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings",

address = "United States",

}

Wu, CC, Tan, ZH & Stefanovic, C 2022, AoI and Throughput Optimization for Hybrid Traffic in Cellular Uplink Using Reinforcement Learning. in 2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings., 9861011, IEEE, IEEE Vehicular Technology Conference, vol. 2022-June, 95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring, Helsinki, Finland, 19/06/2022. https://doi.org/10.1109/VTC2022-Spring54318.2022.9861011

AoI and Throughput Optimization for Hybrid Traffic in Cellular Uplink Using Reinforcement Learning. / Wu, Chien Cheng; Tan, Zheng Hua ; Stefanovic, Cedomir.
2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings. IEEE, 2022. 9861011 (IEEE Vehicular Technology Conference, Vol. 2022-June).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - AoI and Throughput Optimization for Hybrid Traffic in Cellular Uplink Using Reinforcement Learning

AU - Wu, Chien Cheng

AU - Tan, Zheng Hua

AU - Stefanovic, Cedomir

PY - 2022

Y1 - 2022

N2 - The fast growth of time-sensitive applications calls for the optimization of radio access network (RAN) scheduling. We consider the problem of RAN scheduling of a mix of periodic and burst traffic and design a reinforcement learning method for the age of information and throughput optimization. The periodic traffic is generated with a fixed frequency and the burst traffic is generated by the Poisson Pareto Burst Process. We firstly formulate the scheduling problem as a non-linear integer programming problem. Then, we focus on the reinforcement learning method modeling and solve it via the Proximal Policy Optimization algorithm. Our evaluations show that the suggested reinforcement algorithm outperforms the classical algorithms without any prior knowledge of the arriving traffic.

AB - The fast growth of time-sensitive applications calls for the optimization of radio access network (RAN) scheduling. We consider the problem of RAN scheduling of a mix of periodic and burst traffic and design a reinforcement learning method for the age of information and throughput optimization. The periodic traffic is generated with a fixed frequency and the burst traffic is generated by the Poisson Pareto Burst Process. We firstly formulate the scheduling problem as a non-linear integer programming problem. Then, we focus on the reinforcement learning method modeling and solve it via the Proximal Policy Optimization algorithm. Our evaluations show that the suggested reinforcement algorithm outperforms the classical algorithms without any prior knowledge of the arriving traffic.

KW - Age of Information

KW - Burst Traffic

KW - Periodic Traffic

KW - Proximal Policy Optimization

KW - Reinforcement Learning

KW - Time-sensitive communications

UR - http://www.scopus.com/inward/record.url?scp=85137797120&partnerID=8YFLogxK

U2 - 10.1109/VTC2022-Spring54318.2022.9861011

DO - 10.1109/VTC2022-Spring54318.2022.9861011

M3 - Article in proceeding

AN - SCOPUS:85137797120

T3 - IEEE Vehicular Technology Conference

BT - 2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings

PB - IEEE

T2 - 95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring

Y2 - 19 June 2022 through 22 June 2022

ER -

AoI and Throughput Optimization for Hybrid Traffic in Cellular Uplink Using Reinforcement Learning

Abstract

Conference

Bibliographical note

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this