Cognitive Service-Driven Handover Optimization for 5G QoE
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current handover mechanisms in 5G networks are event-triggered and focus primarily on signal quality, which may not adequately address the diverse service requirements of 5G applications, leading to potential quality of experience (QoE) degradation and radio link failures.
Innovation Solution
The implementation of a cognitive service-driven handover optimization module (CSDHO) that utilizes machine learning (ML) and path-aware cognitive handover optimization (PACHO) techniques to learn optimal handover settings and evaluate handover success comprehensively, considering both radio and service-dependent QoE factors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If event-triggered handover mechanisms focusing on signal quality are used, then handover decisions are simple and fast, but quality of experience (QoE) degradation and radio link failures occur due to inadequate consideration of diverse service requirements
Solution Approach 1:
The handover mechanism transitions from static event-triggered decisions to dynamic ML-based predictions that adapt to changing service requirements and mobility patterns, improving QoE while managing complexity through incremental deployment
Solution Approach 2:
The system changes the decision parameters from simple signal quality metrics to comprehensive QoE metrics that incorporate service requirements, user mobility patterns, and network conditions, resolved through ML model predictions
2Reliability
If traditional handover optimization is used, then implementation is straightforward, but ping pong handovers and radio link failures occur due to lack of personalized settings
Solution Approach 1:
The system segments handover optimization into distinct ML models for different service types and mobility patterns, allowing personalized settings without overwhelming complexity through modular model deployment
Solution Approach 2:
The network node performs self-optimization through automated ML model training using collected handover data, reducing the need for manual configuration while improving handover success rates through personalized predictions
3Reliability
If service-specific handover settings are implemented, then QoE is improved, but signaling overhead and processing requirements increase
Solution Approach 1:
The system performs preliminary ML model training during idle periods using collected data, so that service-specific handover settings are ready for immediate deployment without real-time processing delays or excessive signaling
Solution Approach 2:
The system creates simplified copies of complex service requirements as ML model features and predictions, reducing signaling overhead by replacing detailed service parameter exchanges with compact model-based handover recommendations
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
Systems, methods, apparatuses, and computer program products for supporting cognitive service driven handover are provided. One method may include signaling at least one user equipment to start performing and logging quality of experience (QoE) related measurements, and transmitting a request for a report on handover performance to the at least one user equipment. The method may also include receiving the handover performance report, from the at least one user equipment, including at least one service identifier of a service running on the at least one user equipment and the quality of experience (QoE) related measurements.