Automated Root Cause Analysis for Telecommunications Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network management systems face challenges in quickly and accurately identifying the root cause of service failures and signal degradation, especially in multi-vendor, multi-layer networks, due to the need for expert knowledge and complete data sets, which are often unavailable.
Innovation Solution
The implementation of automated Root Cause Analysis (RCA) methods that utilize Performance Monitoring data, alarms, network topology information, and configuration logs to detect service failures and signal degradation, even with incomplete data, through the use of Machine Learning algorithms and derived alarms, enabling diagnosis without requiring domain expertise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual Root Cause Analysis is performed by network operators using complete data sets and expert knowledge, then diagnostic accuracy is improved, but response time increases and expert availability is required
Solution Approach 1:
The system enables automated self-diagnosis of network failures through machine learning models that independently analyze performance monitoring data, alarms, and topology information to identify root causes without requiring human expert intervention. The automated RCA system processes data and generates diagnostic results autonomously, eliminating the need for operators to manually stitch paths and identify failures.
Solution Approach 2:
The patent replaces the manual mechanical process of expert analysis with an automated electronic system using machine learning algorithms. The system substitutes human operators' cognitive processes with computational models that automatically correlate data from multiple sources (PM data, alarms, topology) to determine root causes, thereby accelerating diagnosis while maintaining accuracy.
2Measurement precision
If manual troubleshooting procedures are used with complete data sets, then root cause identification accuracy is improved, but the complexity of the process increases and requires expert knowledge
Solution Approach 1:
The automated RCA system serves multiple functions within a single unified platform: it collects performance monitoring data, processes alarm information, analyzes network topology, identifies failures, and determines root causes. This multi-functional system eliminates the need for separate manual procedures for data collection, analysis, and diagnosis, simplifying the overall process while maintaining comprehensive analysis capabilities.
Solution Approach 2:
The system introduces an automated intermediary layer between raw network data and diagnostic conclusions. The machine learning models act as intermediaries that automatically process and correlate data from multiple sources, translating complex multi-vendor, multi-layer network data into actionable root cause identification without requiring operators to manually interpret the complexity.
3Productivity
If automated RCA methods are used with incomplete data, then response time is improved and expert intervention is reduced, but data completeness decreases
Solution Approach 1:
The system is designed to perform effective root cause analysis with partial data sets rather than requiring complete information. The machine learning models can process available performance monitoring data and alarms even when some data sources are incomplete or unavailable, generating diagnostic results based on the subset of available information rather than waiting for complete data collection.
Solution Approach 2:
The system performs preliminary automated analysis immediately when data becomes available, rather than waiting for complete data sets. By initiating the diagnostic process early with available information and continuously updating as more data arrives, the system achieves faster initial root cause identification while progressively refining accuracy as data completeness improves.
Data Source
AI summary
Systems and methods for analyzing the root cause of service failures and service degradation in a telecommunications network are provided. A method, according to one implementation, includes a step of receiving any of Performance Monitoring (PM) data, standard path alarms, service PM data, standard service alarms, network topology information, and configuration logs from equipment configured to provide services in a network. The method also includes a step of automatically detecting a root cause of a service failure or signal degradation from the available PM data, standard path alarms, service PM data, standard service alarms, network topology information, and configuration logs.