Path Stability Metrics for SD-WAN Oscillation Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Software-defined wide area networks (SD-WANs) face challenges in predicting and managing path performance oscillations, which cause repetitive rerouting and impact application experience due to fluctuations in delay, jitter, and packet loss, leading to poor Quality of Experience (QoE) for online applications.
Innovation Solution
A device in the network detects path oscillations by analyzing telemetry data and determines a stability metric to quantify these oscillations, providing an indication to avoid routing traffic through unstable paths, using a predictive application aware routing engine that employs machine learning to anticipate and prevent SLA violations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If predictive routing mechanisms are used to detect and respond to path performance issues, then application SLA compliance is improved, but path performance oscillations cause repeated rerouting recommendations that degrade application experience
Solution Approach 1:
The system performs preliminary action by detecting path oscillations before they cause SLA violations and proactively stabilizing routing decisions. The oscillation detection mechanism identifies unstable paths in advance, allowing the routing engine to avoid selecting these paths, thereby preventing the cycle of repeated rerouting and maintaining application experience while ensuring SLA compliance.
2Reliability
If routing decisions are made frequently in response to path performance changes, then SLA violations are prevented, but application experience deteriorates due to repeated rerouting
Solution Approach 1:
The system implements feedback by continuously monitoring path performance metrics and using this information to adjust routing decisions. The oscillation detection mechanism provides feedback about path stability, allowing the routing engine to make informed decisions that balance SLA compliance with application experience. By feeding back oscillation information, the system avoids unnecessary rerouting while maintaining service quality.
3Stability of the object's composition
If path performance monitoring is performed continuously to detect oscillations, then routing stability is improved, but system complexity increases
Solution Approach 1:
The system extracts the oscillation detection function as a separate, specialized component that focuses solely on identifying unstable paths. By taking out the oscillation detection logic from the general routing decision-making process, the system can monitor path performance continuously without significantly increasing overall system complexity. This extracted function provides routing stability through dedicated oscillation analysis.
4Reliability
If machine learning techniques are used for predictive failure detection, then proactive routing is enabled, but path oscillations cause repeated routing changes that impact application experience
Solution Approach 1:
The system performs preliminary action by using machine learning to detect path oscillations before they trigger SLA violations. The oscillation detection mechanism identifies unstable paths in advance, allowing the predictive routing engine to avoid selecting these paths proactively. This preliminary detection prevents the harmful cycle of repeated rerouting while maintaining the benefits of predictive routing for reliable SLA compliance.
Data Source
AI summary
In one embodiment, a device obtains telemetry data for a path in a network that is used to convey traffic associated with an online application. The device identifies, based on the telemetry data, oscillations of the path between a first state in which the path provides acceptable user experience for the online application and a second state in which the path does not provide acceptable user experience for the online application. The device determines a stability metric that quantifies the oscillations of the path. The device provides an indication of the oscillations of the path, based in part on the stability metric.