Version 1
: Received: 16 July 2024 / Approved: 16 July 2024 / Online: 16 July 2024 (11:56:48 CEST)
How to cite:
Efunogbon, A.; Efunogbon, T.; Liu, E.; Qiu, R. Optimal 5G Network Sub Slicing Orchestration in a Fully Virtualised Smart Company Using Machine Learning. Preprints2024, 2024071320. https://doi.org/10.20944/preprints202407.1320.v1
Efunogbon, A.; Efunogbon, T.; Liu, E.; Qiu, R. Optimal 5G Network Sub Slicing Orchestration in a Fully Virtualised Smart Company Using Machine Learning. Preprints 2024, 2024071320. https://doi.org/10.20944/preprints202407.1320.v1
Efunogbon, A.; Efunogbon, T.; Liu, E.; Qiu, R. Optimal 5G Network Sub Slicing Orchestration in a Fully Virtualised Smart Company Using Machine Learning. Preprints2024, 2024071320. https://doi.org/10.20944/preprints202407.1320.v1
APA Style
Efunogbon, A., Efunogbon, T., Liu, E., & Qiu, R. (2024). Optimal 5G Network Sub Slicing Orchestration in a Fully Virtualised Smart Company Using Machine Learning. Preprints. https://doi.org/10.20944/preprints202407.1320.v1
Chicago/Turabian Style
Efunogbon, A., Enjie Liu and Renxi Qiu. 2024 "Optimal 5G Network Sub Slicing Orchestration in a Fully Virtualised Smart Company Using Machine Learning" Preprints. https://doi.org/10.20944/preprints202407.1320.v1
Abstract
Network Slicing serves as an enabler for the new fifth generation (5G) of mobile networks era as it enhances connectivity and diverse network slice requirements across various user devices. Optimally orchestrating these 5G network slices to meet the varying demands of applications with diverse quality of service (QoS) requirements and stringent high performance metric remains a challenge today [1]. In this paper, a smart and novel machine learning (ML)-based framework, which dynamically sub-slice in real time and optimally orchestrate a 5G network slice is proposed. Our proposed framework incorporates series of supervised machine learning algorithms with the use of LazyPredict module to find and suggest the best-fit model and make intelligent decisions for the specific network data environment being monitored in real time or analysed with historical dataset. Additionally, the framework employs reinforcement-learning techniques to predict future network traffic data pattern thereby optimally allocating network resources and orchestrating alternative best fit bespoke network slice. This alternative network sub-slice is orchestrated as required to reduce the risk of denial of service and improve user experience. This ultimately forms the proposed new vertical Enterprise Network as a Service: Company Network as a Service (CNaaS) in this study. The proposed approach is extensively evaluated through simulations using python with MATLAB and Simulink. This identified the important features and performance metrics for the 5G network data and demonstrated the efficiency and improvement in key metrics such as latency, throughput, jitter, packet loss rate, and available network resource utilisation compared to conventional methods [1]. The results highlight the importance of leveraging the right machine-learning algorithm for each unique network as the demand requirements changes. The proposed Enhanced Sub-Slice (eSS) module with embedded series of machine learning algorithms using the Lazypredict shows that one size does not fit all and demonstrates the significance of leveraging advanced ML techniques and ML pipelines in the context of 5G network slice management and orchestration.
Computer Science and Mathematics, Computer Networks and Communications
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
