QoS Analytics Confidence Thresholds for Reliable 5G Notifications
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 5G communication systems lack efficient mechanisms for providing confidence thresholds in analytics requests or subscriptions, leading to inaccurate predictions and unnecessary resource consumption in QoS sustainability analytics.
Innovation Solution
Implementing confidence thresholds in conjunction with reporting thresholds to define conditions for prediction analytics events or notifications, allowing consumers to specify their individual needs based on the cost or impact of compensating actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If confidence thresholds are added to analytics requests, then prediction accuracy and notification reliability are improved, but device complexity and configuration requirements increase
Solution Approach 1:
The patent introduces confidence thresholds as a new parameter in analytics requests, allowing consumers to specify the minimum confidence level required for predictions to trigger notifications. This parameter change enables the system to filter out low-confidence predictions, improving notification reliability while maintaining the ability to configure only the necessary additional parameter.
2Loss of energy
If confidence thresholds are implemented, then false notifications are reduced and processing resources are conserved, but the complexity of evaluating prediction conditions increases
Solution Approach 1:
The confidence threshold is evaluated in advance before generating notifications, allowing the system to pre-filter predictions based on confidence levels. This preliminary evaluation prevents unnecessary notification generation and associated processing resources from being wasted on low-confidence predictions.
Solution Approach 2:
The patent extracts the confidence threshold evaluation as a separate condition that must be satisfied independently from the reporting threshold. By separating this evaluation criterion, the system can efficiently filter predictions based on confidence levels without complicating the core notification generation logic.
3Adaptability or versatility
If multiple threshold types (lower bound, higher bound, range) are supported, then adaptability to different QoS scenarios is improved, but device complexity and processing overhead increase
Solution Approach 1:
The patent implements a universal threshold evaluation framework that can handle multiple threshold types (lower bound, higher bound, and range) through a single unified mechanism. The system evaluates the prediction against the appropriate threshold type based on the configuration, providing adaptability to different QoS scenarios without requiring separate processing logic for each threshold type.
Data Source
AI summary
Certain example embodiments provide systems, methods, apparatuses, and computer program products for providing confidence thresholds in an analytics request or subscription. For example, certain embodiments may include a confidence threshold for each reporting threshold (e.g., quality of service (QoS) metric-specific reporting threshold) in an analytics request or subscription (e.g., a network data analytics function (NWDAF) QoS sustainability analytics request or subscription). The confidence threshold (lower bound) can be determined by the consumer application based on their individual needs, e.g., based on the cost or impact of the compensating actions on the predicted QoS sustainability notification. The confidence threshold, in combination with the reporting threshold, may define the conditions for analytics events and/or notifications (e.g., QoS sustainability prediction analytics events and the related notifications).