Making 5G Networks Reliable for Next-generation Applications using AI
- Day - Time: 27 May 2024, h.11:00
- Place: Area della Ricerca CNR di Pisa - Room: C-29
Speakers
- Israat Haque (Dalhousie University, Halifax, Canada)
Referent
Abstract
The emergence of 5G technology marks a significant milestone in developing telecommunication networks, enabling exciting new applications such as augmented reality and self-driving vehicles. However, these improvements bring an increased management complexity and a special concern in dealing with failures, as the applications 5G intends to support heavily rely on high network performance and low latency. Thus, automatic self-healing solutions have become effective in dealing with this requirement, allowing a learning-based system to automatically detect anomalies and perform Root Cause Analysis (RCA).
This talk will present two learning-based systems: GenTrap and Simba. GenTrap is a novel generalized prediction framework that employs Transformer as the temporal feature extractor and incorporates Graph Neural Network (GNN) spatial context capture. GenTrap can be integrated into any existing prediction model for better performance and generalizability. Simba also leverages GNN and Transformer and develops a root cause analyzer in 5G Radio Access Networks (RANs). The performance evaluation confirms the effectiveness of both systems; e.g., GenTrap offers an F1 score of 0.93. The models can be extended to incorporate explainability and robustness as part of the future extension.