Network Analysis System Predicting Alarm Events

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

As networks, such as telecommunications networks, become larger and more complex, detecting errors and diagnosing faults becomes increasingly difficult, making it preferable to predict potential fault conditions before they occur rather than reacting to them after the fact.

Innovation Solution

A method involving the analysis of historical network performance data to create probability networks, which determine conditional probabilities of alarm events, allowing for the prediction of future alarm events and identification of root causes, using weighted nodes and edges representing network elements and their interaction probabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional network monitoring methods are used to detect faults after they occur, then the system can identify actual fault conditions, but the complexity of analyzing alarms in large and complex networks increases significantly

Engineering Contradiction:
Improvefault detection capabilityVSAvoidnetwork monitoring complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary analysis of historical alarm data to build probability networks that predict future alarm events before they occur. By analyzing patterns in historical data and calculating conditional probabilities, the system proactively identifies potential faults and their root causes, enabling preventive maintenance rather than reactive troubleshooting in complex networks

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces probability networks as an intermediary layer between raw alarm data and fault diagnosis. These networks serve as a mediator that processes and interprets alarm correlations, reducing the complexity of direct analysis by providing a structured probabilistic framework that simplifies the relationship between alarms and potential root causes

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If all alarm events are analyzed in detail, then accurate fault diagnosis can be achieved, but the time and computational resources required increase significantly

Engineering Contradiction:
Improvefault diagnosis accuracyVSAvoidalarm analysis time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system extracts and focuses only on the most relevant alarm events by calculating conditional probabilities and identifying root cause alarms. By filtering out less significant alarms and concentrating analysis on high-probability candidates, the system achieves accurate fault diagnosis while reducing the time and computational resources needed to analyze the complete alarm dataset

Inventive Principle:
Principle #2Taking out (Extraction)

3Reliability

If reactive fault response is used, then actual faults can be addressed, but network operational costs and lost revenue increase

Engineering Contradiction:
Improvefault response capabilityVSAvoidoperational cost
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The system performs preliminary prediction of future alarm events by analyzing historical patterns and calculating conditional probabilities. By identifying potential faults before they occur and determining their root causes in advance, the system enables proactive maintenance scheduling, reducing emergency repairs, minimizing network downtime, and lowering operational costs associated with reactive fault response

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2415209B1Network analysis system
Publication Date: 2018.02.28 BRITISH TELECOM PLC
  • EP2415209B1 patent drawingFigure 1
  • EP2415209B1 patent drawingFigure 2
  • EP2415209B1 patent drawingFigure 3

AI summary

The present invention provides a method of operating a network comprising the steps of: analysing a first datastore comprising data representing historical network performance; creating or more indices within the first datastore; creating one or more probability networks in accordance with one or more of the created indices; determining from the one or more probability networks a conditional probability associated with an alarm event; and' if the conditional probability determined is less than a threshold value, disregarding the associated alarm event; or if the conditional probability determined is greater than a threshold value, using the associated alarm event in conjunction with other historical network data to predict future alarm events.