SaaS Routing Path Selection with Network and Application Telemetry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional path routing decisions in SD-WANs rely solely on network KPIs or outdated application QoE data, failing to accurately reflect the network-application relationship and leading to suboptimal path selection.
Innovation Solution
A method that combines current metrics with historical application status data, using confidence values to dynamically weight path selection, ensuring accurate and proactive routing by incorporating both KPIs and application telemetry.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If path routing decisions are made based solely on network KPIs (such as loss and latency from TCP probes), then the routing system is simple to operate, but the accuracy of path selection is insufficient because TCP probes do not accurately reflect actual application traffic status
Solution Approach 1:
The patent combines multiple data sources (network KPIs from TCP probes and application QoE data from SaaS providers) into a unified path selection framework. The edge device receives both network performance metrics and application-specific QoE metrics, then integrates them to make routing decisions, thereby improving measurement precision without excessive complexity increase
Solution Approach 2:
The system implements feedback mechanisms where QoE data from actual application traffic is collected and used to adjust routing decisions. The SaaS provider feeds back application performance metrics to the edge device, which then uses this feedback to optimize path selection, creating a closed-loop system that continuously improves accuracy
2Adaptability or versatility
If multiple paths are used for SaaS services, then service availability and adaptability are improved, but the variation in SLA and QoE increases leading to inconsistent user experience
Solution Approach 1:
The patent implements dynamic path selection where the edge device continuously monitors both network KPIs and application QoE metrics, then adapts routing decisions in real-time. The system dynamically weights and combines multiple data sources to select the optimal path for each application, ensuring consistent QoE while maintaining service availability through multiple path options
Solution Approach 2:
The system applies different selection criteria to different application traffic flows based on their specific QoE requirements. Each application's traffic is routed through paths optimized for its particular performance needs, ensuring that each flow receives appropriate service quality while the overall system maintains high availability
3Measurement precision
If TCP probes are used to determine network KPI values, then the implementation is simple, but the KPI values do not accurately reflect the status of actual application traffic due to different network treatment
Solution Approach 1:
The patent introduces QoE data from SaaS providers as an intermediary that bridges the gap between network KPIs and actual application performance. This intermediary data source provides application-specific metrics that accurately reflect how application traffic is actually treated by the network, complementing the general network KPIs from TCP probes
Data Source
AI summary
Techniques are provided herein for determining a routing path for application traffic based on historic application telemetry and current network telemetry. The techniques comprising determining current metrics for a set of potential paths between an edge device and an application endpoint associated with an application, generating, from the current metrics, a link score for individual paths in the set of potential paths, receiving application status data generated from historic telemetry data associated with the application and the set of potential paths, generating, from the application status data, an application score for individual paths in the set of potential paths, and determining, as a function of the link score and the application score for individual paths in the set of potential paths, a selected path to be used in communications between the edge device and the application endpoint.