Predictive Routing Policy Trust Adjustment in SD-WAN
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In software-defined wide area networks (SD-WANs), reactive failure detection leads to traffic disruption until a secondary tunnel is activated, and dynamic policy creation with machine learning can become unmanageable, inconsistent, and unstable due to multiple policies with varying activation times.
Innovation Solution
A device determines the superiority of a predictive routing policy generated by a predictive routing engine over existing policies, adjusts the trust level, and activates a second predictive policy based on this trust, using machine learning to optimize routing decisions and reduce SLA failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If reactive failure detection is used, then network stability is maintained, but traffic disruption occurs during failures
Solution Approach 1:
The system performs preliminary actions by predicting potential network failures before they occur using machine learning models that analyze historical data and patterns. This allows the network to proactively switch to backup tunnels or adjust routing policies in advance, preventing traffic disruption rather than reacting after failure detection.
2Productivity
If multiple dynamic routing policies are created using machine learning, then routing optimization is improved, but system manageability deteriorates
Solution Approach 1:
The system merges multiple dynamic routing policies into a unified framework where policies are automatically generated, prioritized, and managed by a central controller. The machine learning models continuously learn from network behavior to optimize routing decisions while the system consolidates policy management to maintain simplicity and scalability.
Solution Approach 2:
The system implements feedback mechanisms where routing policies are continuously monitored and evaluated based on their performance. Machine learning models analyze the outcomes of policy applications and adjust future predictions and recommendations accordingly, creating a closed-loop system that optimizes routing while automatically managing policy complexity through data-driven insights.
Data Source
AI summary
In one embodiment, a device makes a determination that a first predictive routing policy generated by a predictive routing engine for a network would have performed better than a preexisting routing policy that is active in the network. The device adjusts, based on the determination, a level of trust associated with the predictive routing engine. The device obtains information regarding a second predictive routing policy generated by the predictive routing engine for the network. The device activates the second predictive routing policy in the network, based on the level of trust associated with the predictive routing engine.