Office QoE Location Forecasting from Network and Environmental Telemetry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network systems fail to accurately predict and optimize user application quality of experience (QoE) in office environments due to reliance on service level agreement (SLA) thresholds, which do not account for complex impairments and environmental factors affecting endpoint clients, leading to unnecessary rerouting that can degrade user experience.
Innovation Solution
A device that combines network telemetry with environmental telemetry to forecast future QoE metrics, providing recommendations for users to navigate to optimal locations for application access, leveraging machine learning and predictive routing to anticipate and mitigate SLA violations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If SLA thresholds are used to predict QoE, then network impairment detection is simplified, but complex environmental impairments go unnoticed leading to inaccurate QoE prediction
Solution Approach 1:
The patent combines network telemetry data with environmental telemetry data from multiple sources (occupancy sensors, noise sensors, temperature sensors, humidity sensors) to create a comprehensive QoE prediction model. This merging of data sources allows the system to detect both network impairments and environmental factors that affect user experience, resolving the contradiction between simplified detection and accurate prediction.
Solution Approach 2:
The system creates a universal prediction model that handles multiple types of impairments through a single platform. The machine learning model processes diverse input data including network metrics and environmental factors, providing multi-functional QoE assessment that works across different office environments and application types, thereby improving both simplicity and accuracy simultaneously.
2Reliability
If network traffic is rerouted proactively based on SLA predictions, then SLA violations are prevented, but unnecessary rerouting occurs degrading user experience
Solution Approach 1:
The system implements feedback mechanisms by continuously monitoring actual QoE metrics and comparing them with predicted values. This feedback loop allows the machine learning model to refine its predictions and reduce false positives, ensuring that rerouting decisions are based on accurate QoE assessments rather than inaccurate SLA threshold predictions, thus preventing unnecessary rerouting while maintaining SLA compliance.
Solution Approach 2:
The patent changes the prediction parameters from simple SLA thresholds to comprehensive QoE metrics that incorporate environmental factors. This parameter transformation enables more nuanced routing decisions that consider the actual user experience impact, allowing the system to maintain reliability while avoiding unnecessary rerouting that would degrade user experience.
3Measurement precision
If environmental factors are monitored to improve QoE prediction, then prediction accuracy increases, but system complexity and data processing requirements increase
Solution Approach 1:
The system employs machine learning models that automatically process and analyze the collected environmental and network telemetry data without requiring manual intervention. The models self-adjust and refine their predictions based on the input data, reducing the operational complexity despite the increased data processing requirements. This allows the system to handle complex environmental monitoring while maintaining manageable system operations.
Data Source
AI summary
In one embodiment, a device obtains network telemetry and environmental telemetry associated with a physical environment. The device forecasts, based on the network telemetry and environmental telemetry, future values of the network telemetry and environmental telemetry. The device predicts, based on the future values, quality of experience metrics for an online application for different locations within the physical environment. The device provides, based on the quality of experience metrics, a recommendation to a user interface that recommends a user of the online application navigate to a particular location from among the different locations to access the online application at a future point in time.