Abstract
The advent of 5G induced complex circumstances for operators to manage the network operations. The traditional manual configuration approaches to configure networks are inadequate to handle the vastly distributed infrastructure, diverse services with flexible requirements, and dynamic changes. To this end, intent-based networking (IBN) paves the way toward automatic handling of network service orchestration. It governs the network operations using the high-level, human-understandable, simplified interpretation of requirements. Administrators only determine what is required and don’t require configuring how to achieve the goals. In addition to the abstraction of hectic configuration requirements, it follows two-way intelligence-driven closed-loop operations to handle dynamic changes and assurance of services automatically. This work empowers automated 5G service orchestration with guaranteed quality of service (QoS) on vastly distributed multi-domain infrastructure through IBN and deep learning. It implements the long-short term memory (LSTM) model for virtual network function, achieving 0.1213 RMSE for resource prediction and management. It explored the RouteNet model with 0.025 RMSE for service path and routing control to optimize the key performance indicators. This results in machine learning (ML)-driven optimized resource scaling and the best path routing.
Original language | English |
---|---|
Article number | 833 |
Journal | Journal of Supercomputing |
Volume | 81 |
Issue number | 7 |
DOIs | |
State | Published - May 2025 |
Bibliographical note
Publisher Copyright:© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.
Keywords
- 5G/6G
- Intent-based networking
- Machine learning for network intelligence
- Network orchestration and management
- Software-defined networking
ASJC Scopus subject areas
- Theoretical Computer Science
- Software
- Information Systems
- Hardware and Architecture