Nodes number estimation based on ML for multi-operator unlicensed band sharing to extend indoor connectivity

Baiyekusi, Oluwatobi and Lee, Haeyoung and Moessner, Klaus; (2023) Nodes number estimation based on ML for multi-operator unlicensed band sharing to extend indoor connectivity. In: 2023 IEEE Wireless Communications and Networking Conference (WCNC). IEEE, Piscataway, NJ.. ISBN 9781665491228 (https://doi.org/10.1109/wcnc55385.2023.10118807)

[thumbnail of Baiyekusi-etal-IEEE-WCNC-2023-Nodes-number-estimation-based-on-ML-for-multi-operator]
Preview
 Text. Filename: Baiyekusi_etal_IEEE_WCNC_2023_Nodes_number_estimation_based_on_ML_for_multi_operator.pdf
Accepted Author Manuscript
License: Strathprints license 1.0
Download (831kB)| Preview

Abstract

Due to ever-increasing data and resource-hungry applications, the need for new spectrum by mobile networks keeps increasing. Unlicensed spectrum is still expected to play a crucial part in meeting the capacity demand for future mobile networks. But if this will be a reality, fair coexistence attained via practical and efficient channel access procedures would be necessary. In designing such channel access schemes, awareness of the number of nodes contending for the channel resource will be required. This paper investigates a node number estimation approach using channel idle time and analysed via machine learning (ML) techniques. When multiple nodes access the same unlicensed channel, varying idle times can be associated with a statistical distribution. In this paper, a statistical distribution of the idle-time slots over the channel is used to characterise and analyse the channel contention based on the number of nodes. Three ML model-based approaches are evaluated and the results confirm the proposed solution’s viability but also reveal the best-performing ML technique of the three, for the task of node number estimations.

CORE (COnnecting REpositories)