Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Prediction and exposure of delays from a base station perspective in 5G and beyond networks

Rao, Akhila ; Tärneberg, William LU ; Fitzgerald, Emma LU orcid ; Corneo, Lorenzo ; Zavodovski, Aleksandr ; Rai, Omkar ; Johansson, Sixten ; Berggren, Viktor ; Riaz, Hassam and Kilinc, Caner , et al. (2022) 2022 ACM SIGCOMM Workshop on 5G and Beyond Network Measurements, Modeling, and Use Cases, 5G-MeMU 2022, co-located with ACM SIGCOMM 2022 In 5G-MeMU 2022 - Proceedings of the ACM SIGCOMM 2022 Workshop on 5G and Beyond Network Measurements, Modeling, and Use Cases - Part of SIGCOMM 2022 p.8-14
Abstract

The inherent flexibility of 5G networks come with a high degree of configuration and management complexity. This makes the performance outcome for UEs, more than ever, dependent on intricate configurations and interplay between algorithms at various network components. In this paper, we take initial steps towards a performance exposure system at the base station using a data-driven approach for predicting performance violations in terms of RTT, as observed by the UE, in a 5G mmWave network. We present ML models to predict RTT using low-level and high-frequency base station metrics from a 5G mmWave testbed based on commercially available equipment. Predicting UE performance from a base station perspective, and exposing this knowledge, is... (More)

The inherent flexibility of 5G networks come with a high degree of configuration and management complexity. This makes the performance outcome for UEs, more than ever, dependent on intricate configurations and interplay between algorithms at various network components. In this paper, we take initial steps towards a performance exposure system at the base station using a data-driven approach for predicting performance violations in terms of RTT, as observed by the UE, in a 5G mmWave network. We present ML models to predict RTT using low-level and high-frequency base station metrics from a 5G mmWave testbed based on commercially available equipment. Predicting UE performance from a base station perspective, and exposing this knowledge, is valuable for applications to proactively address performance violations. We also compare several methods for feature reduction, which have a significant impact on monitoring load. We demonstrate our model's ability to identify RTT violations, paving the way for network providers towards an intelligent performance exposure system.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
5G, delay prediction, machine learning, measurements
host publication
5G-MeMU 2022 - Proceedings of the ACM SIGCOMM 2022 Workshop on 5G and Beyond Network Measurements, Modeling, and Use Cases - Part of SIGCOMM 2022
series title
5G-MeMU 2022 - Proceedings of the ACM SIGCOMM 2022 Workshop on 5G and Beyond Network Measurements, Modeling, and Use Cases - Part of SIGCOMM 2022
pages
7 pages
publisher
Association for Computing Machinery (ACM)
conference name
2022 ACM SIGCOMM Workshop on 5G and Beyond Network Measurements, Modeling, and Use Cases, 5G-MeMU 2022, co-located with ACM SIGCOMM 2022
conference location
Amsterdam, Netherlands
conference dates
2022-08-22
external identifiers
  • scopus:85138281433
ISBN
9781450393935
DOI
10.1145/3538394.3546039
language
English
LU publication?
yes
id
f4ec9e0c-e073-479c-b007-8028eb797dc6
date added to LUP
2022-12-02 12:14:52
date last changed
2023-11-21 06:24:05
@inproceedings{f4ec9e0c-e073-479c-b007-8028eb797dc6,
  abstract     = {{<p>The inherent flexibility of 5G networks come with a high degree of configuration and management complexity. This makes the performance outcome for UEs, more than ever, dependent on intricate configurations and interplay between algorithms at various network components. In this paper, we take initial steps towards a performance exposure system at the base station using a data-driven approach for predicting performance violations in terms of RTT, as observed by the UE, in a 5G mmWave network. We present ML models to predict RTT using low-level and high-frequency base station metrics from a 5G mmWave testbed based on commercially available equipment. Predicting UE performance from a base station perspective, and exposing this knowledge, is valuable for applications to proactively address performance violations. We also compare several methods for feature reduction, which have a significant impact on monitoring load. We demonstrate our model's ability to identify RTT violations, paving the way for network providers towards an intelligent performance exposure system.</p>}},
  author       = {{Rao, Akhila and Tärneberg, William and Fitzgerald, Emma and Corneo, Lorenzo and Zavodovski, Aleksandr and Rai, Omkar and Johansson, Sixten and Berggren, Viktor and Riaz, Hassam and Kilinc, Caner and Johnsson, Andreas}},
  booktitle    = {{5G-MeMU 2022 - Proceedings of the ACM SIGCOMM 2022 Workshop on 5G and Beyond Network Measurements, Modeling, and Use Cases - Part of SIGCOMM 2022}},
  isbn         = {{9781450393935}},
  keywords     = {{5G; delay prediction; machine learning; measurements}},
  language     = {{eng}},
  month        = {{08}},
  pages        = {{8--14}},
  publisher    = {{Association for Computing Machinery (ACM)}},
  series       = {{5G-MeMU 2022 - Proceedings of the ACM SIGCOMM 2022 Workshop on 5G and Beyond Network Measurements, Modeling, and Use Cases - Part of SIGCOMM 2022}},
  title        = {{Prediction and exposure of delays from a base station perspective in 5G and beyond networks}},
  url          = {{http://dx.doi.org/10.1145/3538394.3546039}},
  doi          = {{10.1145/3538394.3546039}},
  year         = {{2022}},
}