Dynamic Smoothing Envelope for Noisy Network Path Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Noisy network metrics such as delay, jitter, and packet loss, which vary significantly over short durations, pose challenges for predictive routing models in software-defined wide area networks (SD-WANs), leading to poor performance in predicting service level agreement (SLA) violations and user experience degradation.
Innovation Solution
The implementation of dynamic smoothing envelopes applied to timeseries of path metrics to denoise the data and predict potential SLA violations, allowing for proactive rerouting decisions, with the duration of the smoothing envelope dynamically determined based on early signs of degradation to optimize prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If machine learning techniques are used to predict SLA violations based on path metrics, then proactive routing decisions can be made, but the noisy and varying nature of the metrics leads to poor prediction accuracy
Solution Approach 1:
The patent applies smoothing envelopes to path metrics before feeding them to the prediction model. This preliminary processing step stabilizes the noisy metrics by filtering out short-term variations, allowing the machine learning model to work with more reliable input data and improve prediction accuracy for SLA violations
Solution Approach 2:
The smoothing envelope acts as an intermediary between the raw path metrics and the prediction model. It mediates the relationship by transforming the noisy original metrics into smoothed versions that better represent the underlying trends, thereby improving the prediction model's ability to detect future SLA violations
2Reliability
If smoothing envelopes are applied to path metrics, then prediction accuracy improves, but the complexity of the system increases
Solution Approach 1:
The patent changes the parameter of the path metrics by applying different smoothing envelope durations. Instead of using raw metrics directly, the system transforms them by smoothing with varying time windows, which improves prediction accuracy while keeping the overall system architecture relatively simple through parameter adjustment rather than structural complexity
Data Source
AI summary
In one embodiment, a device generates a plurality of smoothed timeseries by applying smoothing envelopes of different durations to a timeseries of a path metric for a path in a network that is used to convey traffic of an online application. The device uses the plurality of smoothed timeseries and the timeseries of the path metric to make predictions as to whether the path will provide an unacceptable user experience in the online application. The device selects a smoothing envelope of a particular duration, by comparing performance metrics for the predictions. The device uses a timeseries of the path metric smoothed using the smoothing envelope of the particular duration to make predictive routing decisions in the network for the traffic of the online application.