Network Alarm Management via Machine Learning Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current network management systems are inadequate in ensuring enhanced availability, reliability, and efficiency, particularly in preventing and quickly recovering from network failures, which is critical for society-critical applications like autonomous driving and real-time healthcare.

Innovation Solution

A method and system for managing alarms in networks by identifying attributes such as persistence time, alarm grouping, and predictions, using iterative algorithms and machine learning techniques to determine optimal persistence times, group alarms, and predict alarm occurrences, thereby optimizing resource use and reducing downtime.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional network management systems are used, then device complexity is reduced, but network reliability and availability deteriorate due to inadequate failure prevention and recovery

Engineering Contradiction:

Improvenetwork reliabilityVSAvoidmanagement system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by predicting network alarms before they occur using machine learning models. The alarm prediction module analyzes historical alarm data and network parameters to forecast potential failures, enabling proactive maintenance and prevention of network downtime before it affects critical applications.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring network performance parameters, comparing actual alarm occurrences with predictions, and using this feedback to refine and update the machine learning models. This closed-loop approach improves prediction accuracy over time and enhances network reliability through adaptive learning.

Inventive Principle:

Principle #23Feedback

2Reliability

If more comprehensive alarm monitoring is implemented, then network reliability improves, but loss of time increases due to alarm analysis and processing

Engineering Contradiction:

Improvenetwork availabilityVSAvoiddowntime

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary alarm prediction to identify potential issues before they cause actual network failures. By forecasting alarms in advance, the system enables proactive response and mitigation actions, reducing the actual downtime when failures occur while maintaining comprehensive monitoring coverage.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements self-service capabilities through automated alarm prediction and analysis using machine learning models. The intelligent alarm management system automatically processes and analyzes alarm data without requiring constant human intervention, reducing the time loss associated with manual alarm analysis while maintaining high network availability.

Inventive Principle:

Principle #25Self-service

3Productivity

If manual alarm analysis is used, then device complexity is minimized, but productivity decreases due to slower response to network issues

Engineering Contradiction:

Improveresponse efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system implements self-service through automated machine learning models that independently analyze alarm data, identify patterns, and generate predictions without human intervention. This automation dramatically improves response efficiency to network issues while the system manages its own complexity through standardized algorithms and processes.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces manual mechanical analysis processes with electronic machine learning-based prediction systems. The ML models automatically process large volumes of network data and alarm information, substituting human analysts with intelligent algorithms that provide faster, more consistent, and scalable analysis capabilities.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Productivity

If resource allocation is optimized, then network efficiency improves, but loss of information increases due to filtering out potential alarms

Engineering Contradiction:

Improvenetwork efficiencyVSAvoidalarm information

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The system replaces manual resource allocation decisions with intelligent machine learning-based prediction and prioritization. The ML models analyze multiple factors simultaneously to determine which alarms require immediate attention and how to allocate network resources efficiently, improving overall network efficiency without losing critical alarm information through automated, data-driven decision-making.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11258659B2Management and control for IP and fixed networking

Publication Date: 2022.02.22 NOKIA SOLUTIONS & NETWORKS OY

AI summary

A method for managing alarms in a network includes identifying a first set of alarms based on data in a knowledge base, determining at least one attribute for each alarm in the first set of alarms, generating a model based on the at least one attribute, and applying the model to manage alarms in the network. The at least one attribute includes at least one of a persistence time for one or more alarms in the first set of alarms, an alarm group derived from the first set of alarms, and predictions for alarms in the first set of alarms. The model may be adaptively updated to track changing network conditions relating to the alarms.