Telemetry Event Causality Detection for Automated Root Cause Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for outlier detection and causal analysis in telemetry metrics across disparate devices and networks rely heavily on domain-level expertise, lacking an automated machine-learning framework for efficient identification of root causes.
Innovation Solution
An event causality identification engine using an autoencoder/attention mechanism ensemble is employed to detect outlier telemetry events and identify causal relationships, linking events into chains for root cause analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated machine-learning framework is implemented, then productivity and efficiency of root cause analysis is improved, but device complexity increases due to integration of autoencoders and attention mechanisms
Solution Approach 1:
The patent introduces an intermediary system (the automated machine-learning framework comprising autoencoders and attention mechanisms) that mediates between raw telemetry data and root cause analysis outcomes. This intermediary automatically processes and analyzes telemetry metric pairs, identifying causal relationships without requiring direct human domain expertise intervention, thereby improving productivity while managing complexity through automation.
Solution Approach 2:
The machine-learning framework performs self-service by automatically training on telemetry data, identifying outlier events, and determining causality chains without external guidance. The autoencoders and attention mechanisms autonomously learn patterns and relationships from the data, enabling the system to serve its own analytical needs and reducing dependency on external domain expertise.
2Ease of operation
If automated detection is implemented, then ease of operation is improved, but loss of information increases due to potential automated errors
Solution Approach 1:
The patent implements feedback mechanisms where the attention mechanism evaluates internal layer values and adjusts its analysis based on the significance of identified causal relationships. The system continuously refines its causal inferences by evaluating scores and feedback from the autoencoder's reconstruction error, allowing it to correct potential automated errors and maintain high accuracy while providing ease of operation.
Solution Approach 2:
The patent replaces manual domain expertise analysis (mechanical human process) with automated machine-learning mechanisms. The autoencoders and attention mechanisms substitute human analytical operations, performing outlier detection and causal analysis automatically. This substitution maintains accuracy by using sophisticated algorithms that can detect patterns beyond human capability while providing ease of operation through full automation.
Data Source
AI summary
Identifying causal relationships between outlier telemetry events in telemetry metric data using machine learning ensembles of an autoencoder and an attention mechanism provides an automated framework for root cause analysis. Outlier telemetry events are detected across a cloud of telemetry events using unsupervised learning models. To establish a causal relationship between outlier telemetry events, autoencoder/attention mechanism ensembles are trained for pairs of telemetry metrics. When inputs of sequences of telemetry events of a first telemetry metric and a second telemetry metric to the ensemble have sufficiently high loss value, a causal relationship is inferred. Internal node values of the attention mechanism from the input identify specific time stamps for the first telemetry metric that have a causal relationship with the outlier telemetry event.