SD-WAN Tunnel Creation for Application Experience Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current SD-WAN technologies face challenges in optimizing application performance due to static routing decisions and the complexity of determining the best network topology and exit to the Internet, leading to suboptimal application experience and frequent SLA failures.
Innovation Solution
A predictive application-aware routing engine within an SDN controller that uses machine learning to analyze network and application telemetry, predicting application experience metrics and dynamically creating on-the-fly tunnels to reroute traffic and improve performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If static routing decisions are used in SD-WAN, then network complexity is reduced and ease of operation is improved, but application performance deteriorates and SLA failures increase
Solution Approach 1:
The patent implements dynamic tunnel creation that automatically adapts to changing application performance conditions. The system continuously monitors application experience metrics and creates or modifies tunnels in real-time based on predicted performance, transforming static routing into a dynamic system that responds to network conditions without requiring manual reconfiguration.
Solution Approach 2:
The system employs feedback mechanisms by monitoring application experience metrics and using this information to predict future performance. The controller uses this feedback loop to make intelligent routing decisions, creating tunnels that are predicted to improve application performance based on historical and real-time data about network conditions and application behavior.
2Device complexity
If traditional SD-WAN topologies (hub & spoke, full-mesh) are used, then network structure is simplified and ease of manufacture is improved, but routing optimality deteriorates and application performance suffers
Solution Approach 1:
The patent segments the network routing into application-specific tunnels rather than using monolithic topologies. Instead of forcing all traffic through hub & spoke or full-mesh structures, the system creates dedicated tunnels for specific applications between specific edge routers, allowing each application to have its own optimized path independent of other applications.
Solution Approach 2:
The system transitions from static predefined topologies to dynamic tunnel creation. The controller predicts which tunnels will improve application experience and creates them on-demand, allowing the network topology to adapt dynamically to application requirements rather than being constrained by fixed structural patterns.
3Reliability
If predictive analytics and dynamic tunnel creation are implemented, then application performance and reliability are improved, but device complexity and computational requirements increase
Solution Approach 1:
The system implements partial action by creating tunnels only for applications that are predicted to benefit from them, rather than provisioning all possible tunnels in advance. The controller analyzes application experience metrics and selectively creates tunnels where predicted performance improvement justifies the computational overhead, avoiding unnecessary complexity for applications that don't require optimization.
Solution Approach 2:
The system performs preliminary analysis by predicting application experience metrics before actually creating tunnels. The controller evaluates predicted performance improvements and makes routing decisions in advance based on these predictions, allowing the system to prepare optimal routing paths before traffic demands arise, reducing reactive complexity.
Data Source
AI summary
In one embodiment, a controller obtains data indicative of an application experience metric for an online application having application traffic conveyed via the network. The controller predicts the application experience metric that would result from a first edge router conveying its application traffic to the online application via a second edge router that is not currently connected to the first edge router via a tunnel, based on the obtained data. The controller makes a determination that the first edge router should route its application traffic to the online application via a tunnel between the first edge router and the second edge router, based on the predicted application experience metric. The controller causes a tunnel to be established in the network between the first edge router and the second edge router, whereby the first edge router routes its application traffic to the online application via the second edge router.