TY - GEN
T1 - Prediction and exposure of delays from a base station perspective in 5G and beyond networks
AU - Rao, Akhila
AU - Tärneberg, William
AU - Fitzgerald, Emma
AU - Corneo, Lorenzo
AU - Zavodovski, Aleksandr
AU - Rai, Omkar
AU - Johansson, Sixten
AU - Berggren, Viktor
AU - Riaz, Hassam
AU - Kilinc, Caner
AU - Johnsson, Andreas
N1 - Funding Information:
This research has been supported by the Swedish Governmental Agency for Innovation Systems (VINNOVA) through the project Celtic IMMINENCE (C2020/2-2), the Swedish Foundation for Strategic Research (SSF) through the project Future Factories in the Cloud (GMT-14-0032) and the project Time Critical Clouds (RIT15-0075), and by the Federal Ministry of Education and Research of Germany in the programme of "Souverän. Digital. Vernetzt." joint project 6G-RIC, PIN 16KISK027. Finally, the project has also been supported by the European Union’s Horizon 2020 AIatEDGE (grant agreement No. 101015922).
Publisher Copyright:
© 2022 ACM.
PY - 2022/8/22
Y1 - 2022/8/22
N2 - 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.
AB - 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.
KW - 5G
KW - delay prediction
KW - machine learning
KW - measurements
UR - http://www.scopus.com/inward/record.url?scp=85138281433&partnerID=8YFLogxK
U2 - 10.1145/3538394.3546039
DO - 10.1145/3538394.3546039
M3 - Conference article in proceedings
AN - SCOPUS:85138281433
SP - 8
EP - 14
BT - 5G-MeMU 2022 - Proceedings of the ACM SIGCOMM 2022 Workshop on 5G and Beyond Network Measurements, Modeling, and Use Cases - Part of SIGCOMM 2022
PB - ACM
T2 - ACM SIGCOMM Workshop on 5G and Beyond Network Measurements, Modeling, and Use Cases
Y2 - 22 August 2022 through 22 August 2022
ER -