QoE-Driven Predictive Networks for Application-Aware Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing predictive network systems rely on service level agreements (SLAs) as a proxy for quality of experience (QoE), failing to account for application-specific and user-specific factors, leading to reactive and inefficient network management.
Innovation Solution
Implement a quality of experience (QoE) model that predicts user satisfaction across network and application layers, augmenting predictive network systems to enact routing policies that align with actual user feedback and application telemetry, enabling proactive network adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If predictive network systems use SLA violations as a proxy for QoE, then network management can be automated and scaled, but the system fails to account for application-specific and user-specific factors leading to inaccurate predictions
Solution Approach 1:
The patent introduces an intermediary layer between network infrastructure metrics and application QoE. This intermediary is the QoE model that translates network conditions (latency, packet loss, jitter) into application-level QoE predictions by incorporating application-specific parameters and user feedback, thus resolving the accuracy issue while maintaining automation
Solution Approach 2:
The system changes the parameters used for prediction from purely network-layer SLA metrics to a composite set including application-layer parameters and user feedback indicators. This parameter transformation enables accurate QoE prediction while preserving automated network management capabilities
2Speed
If predictive network systems implement proactive routing based on SLA predictions, then network responsiveness improves, but the system cannot accurately predict true QoE without application and user context
Solution Approach 1:
The system performs preliminary QoE prediction using the enhanced model that incorporates application context and user feedback before making routing decisions. This preliminary accurate assessment enables proactive routing actions that are both timely and accurate, resolving the contradiction between speed and precision
Solution Approach 2:
The patent incorporates user feedback mechanisms that provide continuous feedback loops. This feedback enables the system to learn from actual user experience and refine its QoE predictions, improving both the accuracy of QoE estimation and the effectiveness of proactive routing responses
3Measurement precision
If the system collects and processes application telemetry and user feedback to improve QoE predictions, then prediction accuracy improves, but system complexity increases
Solution Approach 1:
The patent segments the QoE prediction system into distinct functional modules: network condition monitoring, application telemetry collection, user feedback processing, and QoE model inference. This segmentation allows each component to handle specific data types and processing tasks independently, managing complexity while improving prediction accuracy through specialized processing
Data Source
AI summary
In one embodiment, a device trains a quality of experience model to predict a quality of experience metric for an online application. The device augments a predictive network system previously deployed to a network to use the quality of experience model instead of a prediction model that predicts performance of a network path. The device obtains policy information indicative of whether the predictive network system enacted one or more routing policies in the network based on a prediction by the quality of experience model. The device ensures, based on the policy information, that the predictive network system that was augmented to use the quality of experience model enacted a routing policy that accurately matches traffic for the online application.