AI-Based KPI Prediction Methods in Future 6G Networks: A Survey
AI-Based KPI Prediction Methods in Future 6G Networks: A Survey
Authors: Niloofar Mehrnia, Gourav Prateek Sharma, Samie Mostafavi, Andreas Johnsson, Sinem Çöleri, Carlo Fischione, James Gross Date: 2026-06-01 Paper ID: openalex:2606.01972
Summary
This paper presents a systematic review of data-driven KPI prediction methods essential for the transition to 6G networks. It introduces a structured multi-dimensional taxonomy to categorize various predictive approaches, ranging from statistical models to deep and reinforcement learning, based on their application to specific network performance metrics. The survey also evaluates practical deployment challenges such as scalability, privacy, and sustainability while outlining a roadmap for future research in predictive network automation.
Key Contributions
- Provides a comprehensive, systematic review of AI-driven KPI prediction methods specifically tailored for 6G network requirements.
- Introduces a multi-dimensional taxonomy for classifying KPI prediction approaches across KPI types, protocol layers, horizons, and model families.
- Identifies critical open research directions including the development of new KPI definitions and the requirement for probabilistic and explainable AI-native network automation.
Links
Metadata & Links
- url
- https://arxiv.org/abs/2606.01972
- paper_id
- 2606.01972
- paper_source
- openalex
- domain
- nlp
- tags
-
- architectures
-
- datasets
-
- concept_slugs
-
- dataset_slugs
-
- skill
- TimeSeriesSkill
- created_at
- 2026-06-04T06:35:18Z