Managed Entity Configuration Trees for Anomaly Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Managing advanced networks, such as those found in data centers, is challenging due to configurators unintentionally overwriting each other, leading to undesired configuration states on managed entities, which can disrupt network functionality and user experience.

Innovation Solution

Anomaly detection is achieved by generating configuration trees for each managed entity, annotating them with information on the configurator that modified each parameter, and calculating weighted edit distances between subtrees to identify anomalous configurations using a distance matrix, allowing for the identification of the configurator and managed entity affected by the anomaly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple configurators are allowed to configure a managed entity, then configurator versatility and network management flexibility are improved, but configuration stability and reliability deteriorate due to unintended overwrites

Engineering Contradiction:
Improveconfigurator versatilityVSAvoidconfiguration stability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system implements feedback by continuously monitoring configuration changes across multiple configurators and comparing them against a learned normal behavior model. When a configurator deviates from expected patterns, the system generates alerts to prevent unintended overwrites, thus maintaining configuration stability while allowing multiple configurators to operate

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system performs preliminary action by establishing a baseline model of normal configurator behavior before anomalies can occur. This model is built by analyzing historical configuration data and typical configurator patterns, enabling the system to proactively detect and prevent deviations before they cause configuration instability

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If multiple configurators modify managed entity settings, then network management adaptability is improved, but configuration accuracy deteriorates due to conflicting modifications

Engineering Contradiction:
Improvenetwork management adaptabilityVSAvoidconfiguration accuracy
Core Design Contradiction:
Adaptability or versatilityVSManufacturing precision

Solution Approach 1:

The system uses feedback mechanisms to monitor configuration changes in real-time, comparing actual configurator actions against the learned model of accurate configuration patterns. This enables the system to identify and alert on inaccurate modifications while preserving the ability of multiple configurators to make valid changes

Inventive Principle:
Principle #23Feedback

3Difficulty of detecting and measuring

If configuration changes are monitored across multiple configurators, then anomaly detection capability is improved, but system complexity increases

Engineering Contradiction:
Improveanomaly detection capabilityVSAvoidsystem complexity
Core Design Contradiction:
Difficulty of detecting and measuringVSDevice complexity

Solution Approach 1:

The system applies self-service by automatically learning and building the model of normal configurator behavior from historical data without requiring manual configuration or intervention. The system autonomously analyzes patterns, establishes baselines, and performs anomaly detection, reducing the operational complexity despite the enhanced monitoring capability

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4483264B1Managed entity configurator anomaly detection
Publication Date: 2025.09.17 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP4483264B1 patent drawingFigure 1
  • EP4483264B1 patent drawingFigure 2
  • EP4483264B1 patent drawingFigure 3

AI summary

Detecting an anomalous configurator of a plurality of managed entities. A plurality of configuration trees, each representing configuration parameters at a corresponding managed entity, include annotations that identify a configurator that configured each parameter. For a particular configurator, a plurality of subtrees is generated from the plurality of configuration trees. A set of weighted edit distances are calculated from the plurality of subtrees, each representing a degree of difference between a different pair of subtrees. A distance matrix is populated with the set of weighted edit distances, and the distance matrix is used to identify anomalous subtree(s) within the plurality of subtrees for the particular configurator. In embodiments, a configuration corresponding to an anomalous subtree considered to have been anomalously applied by the particular configurator. Data that identifies at least one managed entity associated with the anomalous subtree, and the particular configurator is stored.