Federated learning for performance prediction in multi-operator environments

Article


Lan, X., Taghia, J., Moradi, F., Khoshkholghi, A., Listo Zec, E., Mogren, O., Mahmoodi, T. and Johnsson, A. 2023. Federated learning for performance prediction in multi-operator environments. ITU Journal on Future and Evolving Technologies. 4 (1), pp. 166-177. https://doi.org/10.52953/PFYZ9165
TypeArticle
TitleFederated learning for performance prediction in multi-operator environments
AuthorsLan, X., Taghia, J., Moradi, F., Khoshkholghi, A., Listo Zec, E., Mogren, O., Mahmoodi, T. and Johnsson, A.
Abstract

Telecom vendors and operators deliver services with strict requirements on performance, over complex and sometimes partly shared network infrastructures. A key enabler for network and service management in such environments is knowledge sharing, and the use of data-driven models for performance prediction, forecasting, and troubleshooting. In this paper, we outline a multi-operator service metrics prediction framework using federated learning that allows privacy-preserved knowledge-sharing across operators for improved model performance, and also reduced requirements on data transfer within an operator network. Federated learning is compared against local and central learning strategies for multi-operator performance prediction, and it is shown to balance the requirements on data privacy, model performance, and the network overhead. Further, the paper provides insights on how data heterogeneity affects model performance, where the conclusion is that standard federated learning has certain robustness to data heterogeneity. Finally, we discuss the challenges related to training a federated learning model with a limited budget on the communication rounds. The evaluation is performed using a set of realistic publicly available data traces, that are adapted specifically for the purpose of studying multi-operator service performance prediction.

Middlesex University ThemeCreativity, Culture & Enterprise
LanguageEnglish
PublisherInternational Telecommunications Union
JournalITU Journal on Future and Evolving Technologies
ISSN2616-8375​​
Publication dates
Online10 Mar 2023
Publication process dates
Deposited02 Mar 2023
Accepted15 Feb 2023
Output statusPublished
Publisher's version
Accepted author manuscript
File Access Level
Restricted
Copyright Statement

© International Telecommunication Union, 2023
Some rights reserved. This work is available under the CC BY-NC-ND 3.0 IGO license: https://creativecommons.org/licenses/by-nc-nd/3.0/igo/.
More information regarding the license and suggested citation, additional permissions and disclaimers is available at: https://www.itu.int/en/journal/j-fet/Pages/default.aspx

Web address (URL)https://www.itu.int/pub/S-JNL-VOL4.ISSUE1-2023-A13
Digital Object Identifier (DOI)https://doi.org/10.52953/PFYZ9165
Related Output
Has metadatahttps://publons.com/wos-op/publon/59761241/
Permalink -

https://repository.mdx.ac.uk/item/8q4vy

Download files

  • 43
    total views
  • 4
    total downloads
  • 5
    views this month
  • 1
    downloads this month

Export as

Related outputs

Leveraging oversampling techniques in machine learning models for multi-class malware detection in smart home applications
Chowdhury, A., Isalm, M., Kaisar, S., Naha, R., Khoshkholghi, A., Aiash, M. and Khoda, M.E. Leveraging oversampling techniques in machine learning models for multi-class malware detection in smart home applications. IEEE 22nd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) .
Efficient design for smart environment using Raspberry Pi with Blockchain and IoT (BRIoT)
Ponugumati, S., Ali, K., Lasebae, A., Zahoor, Z., Kiyani, A., Khoshkholghi, A. and Maddu, L. 2023. Efficient design for smart environment using Raspberry Pi with Blockchain and IoT (BRIoT). CCGridW: 4th Workshop on Secure IoT, Edge and Cloud Systems (SioTEC) 2023. Bangalore, India 01 - 04 May 2023 IEEE. pp. 75-80 https://doi.org/10.1109/CCGridW59191.2023.00026
Information fusion-based cybersecurity threat detection for intelligent transportation system
Chowdhury, A., Naha, R., Kaisar, S., Khoshkholghi, A., Ali, K. and Galletta, A. 2023. Information fusion-based cybersecurity threat detection for intelligent transportation system. CCGridW: 4th Workshop on Secure IoT, Edge and Cloud Systems (SioTEC) 2023. Bangalore, India 01 - 04 May 2023 Bangalore, India IEEE. pp. 96-103 https://doi.org/10.1109/CCGridW59191.2023.00029
A novel scheduling algorithm for improved performance of multi-objective safety-critical wireless sensor networks using long short-term memory
Al-Nader, I., Lasebae, A., Raheem, R. and Khoshkholghi, A. 2023. A novel scheduling algorithm for improved performance of multi-objective safety-critical wireless sensor networks using long short-term memory. Electronics. 12 (23). https://doi.org/10.3390/electronics12234766
Performance and cryptographic evaluation of security protocols in distributed networks using applied pi calculus and Markov Chain
Edris, E., Aiash, M., Khoshkholghi, A., Naha, R., Chowdhury, A. and Loo, J. 2023. Performance and cryptographic evaluation of security protocols in distributed networks using applied pi calculus and Markov Chain. Internet of Things. 24. https://doi.org/10.1016/j.iot.2023.100913
IoT-based emergency vehicle services in intelligent transportation system
Chowdhury, A., Kaisar, S., Khoda, M., Naha, R., Khoshkholghi, A. and Aiash, M. 2023. IoT-based emergency vehicle services in intelligent transportation system. Sensors. 23 (11). https://doi.org/10.3390/s23115324