Management and Evaluation of the Performance of end-to-end 5G Inter/Intra Slicing using Machine Learning in a Sustainable Environment

Aug 5, 2026

Upload by Logic

3GPP defines network slicing as scalable resources that match user requirements, and the study integrates machine learning with inter/intra end-to-end slicing for efficient management and optimization. A prototype connects end users to multiple inter and intra slices based on demand, deploying slices through software-defined and virtualization technologies. End-to-end traffic is generated across multiple scenarios, analyzed using flow-behavior features, and processed with MATLAB classification to select models that reduce CPU and training time. Regression minimizes squared error to predict slice type across datasets, supporting sustainable future networks.

LanguageEnglish

CategoryTechnology

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Introduction

End-to-End slicing concepts and benefits

Virtual network creation with SDN and NFV

Related work and motivation

Methodology and Prototype Approach

Inter/intra-slice implementation and traffic scenarios

Traffic feature extraction and dataset element selection

Machine learning workflow for model selection and training

Performance Evaluation

Classification to manage and predict slices efficiently

Regression for slice-type prediction with minimum error

Conclusion

Sustainable environment considerations

This is a peer-reviewed, final published version of the following document and is licensed under Creative Commons: Attribution-Noncommercial 4.0 license: Mohammedali, Noor Abdalkarem, Kanakis, Triantafyllos, AlSherbaz, Ali ORCID: 0000-0002-0995-1262 and Agyeman, Michael Opoku (2023) Management and Evaluation of the Performance of end-to-end 5G Inter/Intra Slicing using Machine Learning in a Sustainable Environment . Journal of Communications Software and Systems, 19 (1) . pp . 91-102 . doi:10.24138/jcomss-2022-0163 Official URL: [http://dx.doi.org/10.24138/jcomss-2022-0163](http://dx.doi.org/10.24138/jcomss-2022-0163) [DOI: 10.24138/jcomss-2022-0163](DOI: 10.24138/jcomss-2022-0163) EPrint URI: [https://eprints.glos.ac.uk/id/eprint/12593](https://eprints.glos.ac.uk/id/eprint/12593) Disclaimer The University of Gloucestershire has obtained warranties from all depositors as to their title in the material deposited and as to their right to deposit such material. The University of Gloucestershire makes no representation or warranties of commercial utility, title, or fitness for a particular purpose or any other warranty, express or implied in respect of any material deposited. The University of Gloucestershire makes no representation that the use of the materials will not infringe any patent, copyright, trademark or other property or proprietary rights. The University of Gloucestershire accepts no liability for any infringement of intellectual property rights in any material deposited but will remove such material from public view pending investigation in the event of an allegation of any such infringement. PLEASE SCROLL DOWN FOR TEXT. Management and Evaluation of the Performance of end-to-end 5G Inter/Intra Slicing using Machine Learning in a Sustainable Environment Noor Abdalkarem Mohammedali, Student Member, IEEE, Triantafyllos Kanakis, Member, IEEE, Ali Al-Sherbaz, Member, IEEE, and Michael Opoku Agyeman, Senior Member, IEEE Abstract—The 3G Partnership Project (3GPP) defined network slicing as a set of resources that could be scaled up and down to cover users’ requirements. Machine learning and network slicing will be used together to manage and optimize resources efficiently. Sharing resources across multiple operators, such as towers, spectrum and infrastructure, can reduce the cost of 5G resources. In the proposed prototype, the end-user is connected to more than eight inter and intra-slices according to the demands. A set of slices is implemented over the 5G networks to provide an efficient service to the end-user using softwarization and virtualization technologies. Traffic is generated over multiple scenarios then End-to-End slicing traffic was analyzed after generating realtime traffic over the 5G networks. Also, all the features extracted from the traffic based on the flow behaviours and a set of elements selected from the datasets according to machine learning behaviours. Multiple machine learning algorithms are applied to our datasets using MATLAB classification application. After that, the best model is chosen to train and predict the slices using less CPU and training time to reduce the computational power in future networks and build a sustainable environment. Furthermore, the regression application predicts the slice type on the third dataset with the minimum squared error. Index Terms—5G, NFV, Network Slicing, Future Network, Inter-Slice, Machine Learning, Network Services, Intra-Slice, Resources Allocation, E2E. I. INTRODUCTION END-to-End slicing is a new technology that promises to provide flexibility, more sustainability, better performance and lower costs in mobile networks. Network slicing enables operators to create multiple virtual networks on a single physical network, allowing for more flexibility and customizability using Software-Defined Networks (SDN) and Network Function Virtualization (NFV) . In [1], the authors reviewed all the slicing issues and focused on emplo

FAQs

How does the document define network slicing and why is it important for 5G?

It describes network slicing as a set of resources that can be scaled to meet user requirements. The paper positions slicing as a way to provide flexibility, sustainability, improved performance, and lower costs in mobile networks.

What role do machine learning techniques play in managing end-to-end inter/intra slicing?

The workflow generates real-time traffic scenarios, extracts features from traffic flow behaviors, applies multiple machine learning algorithms in MATLAB classification, and selects the best model to train and predict slice assignments efficiently.

How is slice type predicted and what performance objective is used?

A regression application predicts the slice type on a third dataset using a minimum squared error objective, aiming to improve prediction accuracy while supporting efficient future network operation.

Aug 5, 2026

Upload by Logic