Predictive Radio Link Failure Reporting for QoE Protection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems lack a mechanism for user equipment (UE) to predict and report quality of experience (QoE) degradation or radio link failures in real-time, leading to degraded user experience and inefficient network resource management.
Innovation Solution
UEs are equipped with AI/ML models to predict QoE degradation and radio link failures, allowing them to proactively report predicted data rate, spectrum efficiency, or latency issues to the network, enabling the network to adjust scheduling parameters and prevent QoE degradation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If UEs wait for actual radio link failure to report to the network, then the reporting mechanism is simple, but the user experience is degraded due to late detection of quality issues
Solution Approach 1:
The UE performs preliminary actions by predicting future radio link failure or QoE degradation events before they actually occur. The device uses AI/ML models to analyze current radio conditions and predict future failures, then reports these predictions to the network in advance, allowing the network to take preventive actions before the actual degradation happens.
2Productivity
If the UE uses traditional reactive reporting after radio link failure, then the system complexity is low, but the network resource management efficiency is poor
Solution Approach 1:
The system implements a feedback mechanism where the UE continuously monitors radio link conditions, predicts potential failures using AI/ML models, and reports these predictions to the network. The network then uses this feedback information to proactively adjust scheduling parameters and resource allocation, creating a closed-loop system that improves resource management efficiency through informed decision-making.
Solution Approach 2:
The patent replaces traditional mechanical/reactive reporting mechanisms with AI/ML-based predictive systems. Instead of simply reporting after failure occurs, the UE employs machine learning models to predict future failures based on pattern recognition in radio condition data, substituting reactive mechanical systems with intelligent predictive systems.
3Reliability
If the network waits for actual failures before adjusting parameters, then the control mechanism is simple, but the user experience quality is degraded
Solution Approach 1:
The network takes preliminary action by receiving and acting on predictive failure reports from UEs before actual radio link failures occur. Upon receiving a prediction, the network proactively adjusts scheduling parameters, resource allocation, or other configuration settings to prevent the predicted failure from happening, thereby maintaining high user experience quality.
Data Source
AI summary
Methods, systems, and devices for wireless communications are described that provide for configuration of a user equipment (UE) to perform predictive radio failure identification, predictive estimation of Quality of Experience (QoE) degradation, predictive data rate estimation, or any combination thereof. The UE may report predictive radio failures and/or QoE degradation in advance of such an event. A network entity, based on the reported information, may proactively react to attempt to avoid radio failure, QoE degradation, or both, such as by changing one or more communications parameters with the UE. The UE may also indicate an estimated time or time deadline for the network to take action to prevent radio failure, QoE degradation, or both.