Leveraging Infrastructure Monitoring for User Experience Forecasting in Container-based 5G Core

Full text
Author(s):	da Silva, Bruno Marques ; Rodrigues Moreira, Larissa F. ; Moreira, Rodrigo ; Silva, Flavio de Oliveira Total Authors: 4
Document type:	Journal article
Source:	2025 JOINT EUROPEAN CONFERENCE ON NETWORKS AND COMMUNICATIONS & 6G SUMMIT, EUCNC/6G SUMMIT; v. N/A, p. 6-pg., 2025-01-01.
Abstract
Integrating intelligence in mobile networks enhances resource management and ensures Service Level Agreements (SLAs) compliance. However, the complexity of subsystems and interactions in the network-slicing lifecycle poses challenges. Existing studies often rely on simulated datasets or monitoring systems, which face limitations in generalization, privacy, and real-time responsiveness due to data quality and complexity of the Machine Learning (ML) algorithm. Although advanced monitoring systems improve accuracy, their high computational cost necessitates low-overhead alternatives. This paper demonstrates that generic computing and network metrics in container-based 5G core can accurately reveal user experience in mobile networks, achieving a 10.5232% Mean Absolute Percentage Error (MAPE) with feature-based and sequence-based ML algorithms. (AU)

FAPESP's process:	18/23097-3 - SFI2: slicing future internet infrastructures
Grantee:	Tereza Cristina Melo de Brito Carvalho
Support Opportunities:	Research Projects - Thematic Grants