ML Handover Parameter Prediction for Fewer Radio Link Failures

The system enables self-service by automatically optimizing handover parameters through machine learning models. The network system autonomously selects optimal parameters, trains models using historical data, and applies predictions without manual intervention, transforming the manual configuration process into a self-optimizing system that improves handover success rates while maintaining operational simplicity

The patent replaces the mechanical manual configuration system with an intelligent machine learning-based system. Instead of manual parameter setting and adjustment, the system uses trained models to automatically select and optimize handover parameters, substituting human-operated mechanical processes with automated computational intelligence to improve reliability without increasing operational complexity

The system applies preliminary action by pre-training machine learning models using historical network data and terminal device information before actual handover operations. The model training and parameter optimization are performed in advance, creating a ready-to-use predictive system that can quickly provide optimal parameters during real-time handovers without intensive computational resources during the critical handover moment

The patent implements partial action by focusing computational resources on training the model with selected historical data subsets and using the trained model for predictions rather than continuously optimizing all parameters in real-time. This approach achieves sufficient handover optimization while avoiding excessive computational energy consumption by applying the model efficiently during actual handover operations