Skip to main content

User and resource allocation in latency constrained Xhaul via reinforcement learning

Chughtai, Mohsan Niaz, Noor, Shabnam, Laurinavicius, Ignas, Assimakopoulos, Philippos, Gomes, Nathan J., Zhu, Huiling, Wang, Jiangzhou, Zheng, Xi, Yan, Qi (2023) User and resource allocation in latency constrained Xhaul via reinforcement learning. Journal of Optical Communications and Networking, 15 (4). pp. 219-228. ISSN 1943-0620. E-ISSN 1943-0639. (doi:10.1364/JOCN.485029) (Access to this publication is currently restricted. You may be able to access a copy if URLs are provided) (KAR id:100780)

PDF Author's Accepted Manuscript
Language: English

Restricted to Repository staff only until 29 March 2024.
Contact us about this Publication
[thumbnail of M.N.Chughtai - User and resource allocation in latency constrained Xhaul - AAM.pdf]
Official URL:
https://doi.org/10.1364/JOCN.485029

Abstract

The Flexible Ethernet (FlexE) is envisioned for the provisioning of different services and hard slicing of the Xhaul in 5G and beyond networks. For efficient bandwidth utilization in the Xhaul, traffic prediction for slot allocation in FlexE calendars is required. Further, if coordinated multipoint (CoMP) is used, the allocation of users to remote units (RUs) with an Xhaul path of lower latency to the distributed unit/central unit will increase the achievable user bit rate. In this paper, the use of multi-agent deep reinforcement learning (DRL) for optimal slot allocations in a FlexE-enabled Xhaul, for traffic generated through CoMP, and for offloading users among different RUs is explored. In simulation results, the DRL agent can learn to predict input traffic patterns and allocate slots with the necessary granularity of 5 Gbps in the FlexE calendar. The resulting gains are expressed in terms of the reduction of mean over-allocation of slots in the FlexE calendar in comparison to the prediction obtained from an autoregressive integrated moving average (ARIMA) model. Simulations indicate that DRL outperforms ARIMA-based prediction by up to 11.6%

Item Type: Article
DOI/Identification number: 10.1364/JOCN.485029
Subjects: Q Science > QA Mathematics (inc Computing science)
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts
Funders: Huawei Technologies (United Kingdom) (https://ror.org/056gzgs71)
Depositing User: Mohsan Chughtai
Date Deposited: 06 Apr 2023 08:26 UTC
Last Modified: 11 Apr 2023 13:28 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/100780 (The current URI for this page, for reference purposes)

University of Kent Author Information

Chughtai, Mohsan Niaz.

Creator's ORCID:
CReDIT Contributor Roles:

Noor, Shabnam.

Creator's ORCID: https://orcid.org/0000-0001-8258-8466
CReDIT Contributor Roles:

Laurinavicius, Ignas.

Creator's ORCID:
CReDIT Contributor Roles:

Assimakopoulos, Philippos.

Creator's ORCID: https://orcid.org/0000-0002-2550-1317
CReDIT Contributor Roles:

Gomes, Nathan J..

Creator's ORCID: https://orcid.org/0000-0003-3763-3699
CReDIT Contributor Roles:

Zhu, Huiling.

Creator's ORCID: https://orcid.org/0000-0003-3021-5013
CReDIT Contributor Roles:

Wang, Jiangzhou.

Creator's ORCID: https://orcid.org/0000-0003-0881-3594
CReDIT Contributor Roles:
  • Depositors only (login required):

Total unique views for this document in KAR since July 2020. For more details click on the image.