Deep Reinforcement Learning Based Joint Allocation Scheme in a TWDM-PON-Based mMIMO Fronthaul Network

In next-generation centralized or cloud radio access networks (C-RANs), time and wavelength division multiplexed passive optical network (TWDM-PON) has been well recognized as a promising candidate to build the mobile fronthaul. Considering the stringent bandwidth efficiency, latency, and cost requi...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuansen Cheng, Yingjie Shao, Shifeng Ding, Chun-Kit Chan
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10499798/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849415906423209984
author Yuansen Cheng
Yingjie Shao
Shifeng Ding
Chun-Kit Chan
author_facet Yuansen Cheng
Yingjie Shao
Shifeng Ding
Chun-Kit Chan
author_sort Yuansen Cheng
collection DOAJ
description In next-generation centralized or cloud radio access networks (C-RANs), time and wavelength division multiplexed passive optical network (TWDM-PON) has been well recognized as a promising candidate to build the mobile fronthaul. Considering the stringent bandwidth efficiency, latency, and cost requirements in C-RAN, an efficient bandwidth and wavelength allocation scheme is highly desirable for TWDM-PON-based fronthaul. Especially for the massive multiple input multiple outputs (mMIMO) enabled beamforming scenario, the additional radio resource is required to be jointly allocated with bandwidth and wavelength resources in TWDM-PON. In this paper, we formulate the joint allocation problem into an integer linear programming mathematical model and propose a deep reinforcement learning (RL)-based joint allocation scheme with an energy-efficient architecture for the TWDM-PON-based mMIMO fronthaul network. The proposed scheme couples the heuristic radio resource allocation algorithm with the RL-based wavelength allocation model to optimize the fronthaul bandwidth, radio resource, and wavelength utilization efficiencies jointly in the downstream direction. Simulation results show that the proposed scheme achieves a high bandwidth efficiency and high radio resource block utilization simultaneously across different traffic loads and, meanwhile, reduces the wavelength usage compared with the benchmark.
format Article
id doaj-art-50c2e7f008e448f9a9290c0f1109bece
institution Kabale University
issn 1943-0655
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-50c2e7f008e448f9a9290c0f1109bece2025-08-20T03:33:21ZengIEEEIEEE Photonics Journal1943-06552024-01-0116311110.1109/JPHOT.2024.338857110499798Deep Reinforcement Learning Based Joint Allocation Scheme in a TWDM-PON-Based mMIMO Fronthaul NetworkYuansen Cheng0https://orcid.org/0000-0001-8684-8894Yingjie Shao1https://orcid.org/0000-0003-2308-5943Shifeng Ding2https://orcid.org/0000-0003-2810-2212Chun-Kit Chan3https://orcid.org/0000-0002-7046-5335Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong SAR, ChinaCentre for Applied Photonics, Fraunhofer U.K. Research Ltd., Glasgow, U.K.Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong SAR, ChinaDepartment of Information Engineering, The Chinese University of Hong Kong, Hong Kong SAR, ChinaIn next-generation centralized or cloud radio access networks (C-RANs), time and wavelength division multiplexed passive optical network (TWDM-PON) has been well recognized as a promising candidate to build the mobile fronthaul. Considering the stringent bandwidth efficiency, latency, and cost requirements in C-RAN, an efficient bandwidth and wavelength allocation scheme is highly desirable for TWDM-PON-based fronthaul. Especially for the massive multiple input multiple outputs (mMIMO) enabled beamforming scenario, the additional radio resource is required to be jointly allocated with bandwidth and wavelength resources in TWDM-PON. In this paper, we formulate the joint allocation problem into an integer linear programming mathematical model and propose a deep reinforcement learning (RL)-based joint allocation scheme with an energy-efficient architecture for the TWDM-PON-based mMIMO fronthaul network. The proposed scheme couples the heuristic radio resource allocation algorithm with the RL-based wavelength allocation model to optimize the fronthaul bandwidth, radio resource, and wavelength utilization efficiencies jointly in the downstream direction. Simulation results show that the proposed scheme achieves a high bandwidth efficiency and high radio resource block utilization simultaneously across different traffic loads and, meanwhile, reduces the wavelength usage compared with the benchmark.https://ieeexplore.ieee.org/document/10499798/BeamformingC-RANpointer networkresource allocationreinforcement learningTWDM-PON
spellingShingle Yuansen Cheng
Yingjie Shao
Shifeng Ding
Chun-Kit Chan
Deep Reinforcement Learning Based Joint Allocation Scheme in a TWDM-PON-Based mMIMO Fronthaul Network
IEEE Photonics Journal
Beamforming
C-RAN
pointer network
resource allocation
reinforcement learning
TWDM-PON
title Deep Reinforcement Learning Based Joint Allocation Scheme in a TWDM-PON-Based mMIMO Fronthaul Network
title_full Deep Reinforcement Learning Based Joint Allocation Scheme in a TWDM-PON-Based mMIMO Fronthaul Network
title_fullStr Deep Reinforcement Learning Based Joint Allocation Scheme in a TWDM-PON-Based mMIMO Fronthaul Network
title_full_unstemmed Deep Reinforcement Learning Based Joint Allocation Scheme in a TWDM-PON-Based mMIMO Fronthaul Network
title_short Deep Reinforcement Learning Based Joint Allocation Scheme in a TWDM-PON-Based mMIMO Fronthaul Network
title_sort deep reinforcement learning based joint allocation scheme in a twdm pon based mmimo fronthaul network
topic Beamforming
C-RAN
pointer network
resource allocation
reinforcement learning
TWDM-PON
url https://ieeexplore.ieee.org/document/10499798/
work_keys_str_mv AT yuansencheng deepreinforcementlearningbasedjointallocationschemeinatwdmponbasedmmimofronthaulnetwork
AT yingjieshao deepreinforcementlearningbasedjointallocationschemeinatwdmponbasedmmimofronthaulnetwork
AT shifengding deepreinforcementlearningbasedjointallocationschemeinatwdmponbasedmmimofronthaulnetwork
AT chunkitchan deepreinforcementlearningbasedjointallocationschemeinatwdmponbasedmmimofronthaulnetwork