Deep Reinforcement Learning-Based Policy for Baseband Function Placement and Routing of RAN in 5G and Beyond

Zhengguang Gao; Shuangyi Yan; Jiawei Zhang; Bingtao Han; Yongcheng Wang; Yuming Xiao; Dimitra Simeonidou; Yuefeng Ji

doi:10.1109/JLT.2021.3110788

Deep Reinforcement Learning-Based Policy for Baseband Function Placement and Routing of RAN in 5G and Beyond

Zhengguang Gao, Shuangyi Yan, Jiawei Zhang^*, Bingtao Han, Yongcheng Wang, Yuming Xiao, Dimitra Simeonidou, Yuefeng Ji

^*Corresponding author for this work

Research output: Contribution to journal › Article (Academic Journal) › peer-review

10 Citations (Scopus)

151 Downloads (Pure)

Abstract

In this paper, we propose a deep reinforcement learning (DRL)-based algorithm to generate policies of Baseband Function (BBF) placement and routing. In order to explore the performance of the proposed algorithm in practical systems, the online scenario with the completely random requests is used in the simulation considering C-RAN and NG-RAN architectures. Besides, an Integer Linear Programming (ILP) model is formulated to generate the optimal solution as the benchmark. The simulation results show that DRL-based algorithm converges in a short time, and its performance closes to the optimal benchmark obtained by ILP in terms of latency and bandwidth for the online scenarios. In addition, the performance of the generated policies based on DRL is compared with a classic heuristic algorithm, i.e., first-fit algorithm. The performance of DRL-based algorithm is superior to the first-fit algorithm from above two perspectives. The fast convergence and the near-optimal performance prove that the DRL-based algorithm is a promising approach for the BBF placement and routing of RAN in 5G and Beyond.

Original language	English
Number of pages	1
Journal	Journal of Lightwave Technology
Early online date	9 Sept 2021
DOIs	https://doi.org/10.1109/JLT.2021.3110788
Publication status	E-pub ahead of print - 9 Sept 2021

Bibliographical note

Publisher Copyright:
IEEE

Keywords

5G and Beyond
5G mobile communication
Bandwidth
Baseband
Baseband Function placement and routing
Benchmark testing
Computer architecture
Deep reinforcement learning
Heuristic algorithms
Routing

Access to Document

10.1109/JLT.2021.3110788

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via Optical Society of America at https://ieeexplore.ieee.org/document/9531497 . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 834 KB

Handle.net

Persistent link

5G-CLARITY: Beyond 5G multi-tenant private networks integrating Cellular, WiFi, and LiFi, Powered by ARtificial Intelligence and Intent Based PolicY
Simeonidou, D.
1/11/19 → 30/04/22
Project: Research, Parent

Cite this

@article{7f397d3c43034744ae2c86f72176723a,

title = "Deep Reinforcement Learning-Based Policy for Baseband Function Placement and Routing of RAN in 5G and Beyond",

abstract = "In this paper, we propose a deep reinforcement learning (DRL)-based algorithm to generate policies of Baseband Function (BBF) placement and routing. In order to explore the performance of the proposed algorithm in practical systems, the online scenario with the completely random requests is used in the simulation considering C-RAN and NG-RAN architectures. Besides, an Integer Linear Programming (ILP) model is formulated to generate the optimal solution as the benchmark. The simulation results show that DRL-based algorithm converges in a short time, and its performance closes to the optimal benchmark obtained by ILP in terms of latency and bandwidth for the online scenarios. In addition, the performance of the generated policies based on DRL is compared with a classic heuristic algorithm, i.e., first-fit algorithm. The performance of DRL-based algorithm is superior to the first-fit algorithm from above two perspectives. The fast convergence and the near-optimal performance prove that the DRL-based algorithm is a promising approach for the BBF placement and routing of RAN in 5G and Beyond.",

keywords = "5G and Beyond, 5G mobile communication, Bandwidth, Baseband, Baseband Function placement and routing, Benchmark testing, Computer architecture, Deep reinforcement learning, Heuristic algorithms, Routing",

author = "Zhengguang Gao and Shuangyi Yan and Jiawei Zhang and Bingtao Han and Yongcheng Wang and Yuming Xiao and Dimitra Simeonidou and Yuefeng Ji",

note = "Publisher Copyright: IEEE",

year = "2021",

month = sep,

day = "9",

doi = "10.1109/JLT.2021.3110788",

language = "English",

journal = "Journal of Lightwave Technology",

issn = "1558-2213",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

TY - JOUR

T1 - Deep Reinforcement Learning-Based Policy for Baseband Function Placement and Routing of RAN in 5G and Beyond

AU - Gao, Zhengguang

AU - Yan, Shuangyi

AU - Zhang, Jiawei

AU - Han, Bingtao

AU - Wang, Yongcheng

AU - Xiao, Yuming

AU - Simeonidou, Dimitra

AU - Ji, Yuefeng

N1 - Publisher Copyright: IEEE

PY - 2021/9/9

Y1 - 2021/9/9

N2 - In this paper, we propose a deep reinforcement learning (DRL)-based algorithm to generate policies of Baseband Function (BBF) placement and routing. In order to explore the performance of the proposed algorithm in practical systems, the online scenario with the completely random requests is used in the simulation considering C-RAN and NG-RAN architectures. Besides, an Integer Linear Programming (ILP) model is formulated to generate the optimal solution as the benchmark. The simulation results show that DRL-based algorithm converges in a short time, and its performance closes to the optimal benchmark obtained by ILP in terms of latency and bandwidth for the online scenarios. In addition, the performance of the generated policies based on DRL is compared with a classic heuristic algorithm, i.e., first-fit algorithm. The performance of DRL-based algorithm is superior to the first-fit algorithm from above two perspectives. The fast convergence and the near-optimal performance prove that the DRL-based algorithm is a promising approach for the BBF placement and routing of RAN in 5G and Beyond.

AB - In this paper, we propose a deep reinforcement learning (DRL)-based algorithm to generate policies of Baseband Function (BBF) placement and routing. In order to explore the performance of the proposed algorithm in practical systems, the online scenario with the completely random requests is used in the simulation considering C-RAN and NG-RAN architectures. Besides, an Integer Linear Programming (ILP) model is formulated to generate the optimal solution as the benchmark. The simulation results show that DRL-based algorithm converges in a short time, and its performance closes to the optimal benchmark obtained by ILP in terms of latency and bandwidth for the online scenarios. In addition, the performance of the generated policies based on DRL is compared with a classic heuristic algorithm, i.e., first-fit algorithm. The performance of DRL-based algorithm is superior to the first-fit algorithm from above two perspectives. The fast convergence and the near-optimal performance prove that the DRL-based algorithm is a promising approach for the BBF placement and routing of RAN in 5G and Beyond.

KW - 5G and Beyond

KW - 5G mobile communication

KW - Bandwidth

KW - Baseband

KW - Baseband Function placement and routing

KW - Benchmark testing

KW - Computer architecture

KW - Deep reinforcement learning

KW - Heuristic algorithms

KW - Routing

U2 - 10.1109/JLT.2021.3110788

DO - 10.1109/JLT.2021.3110788

M3 - Article (Academic Journal)

SN - 1558-2213

JO - Journal of Lightwave Technology

JF - Journal of Lightwave Technology

ER -

Deep Reinforcement Learning-Based Policy for Baseband Function Placement and Routing of RAN in 5G and Beyond

Abstract

Bibliographical note

Keywords

Access to Document

Handle.net

Fingerprint

Projects

5G-CLARITY: Beyond 5G multi-tenant private networks integrating Cellular, WiFi, and LiFi, Powered by ARtificial Intelligence and Intent Based PolicY

Cite this