Base Station Fault Ranking Through Clustered Data Rate Forecasting

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing fault management systems in telecommunication networks fail to prioritize faults based on their impact on user performance, leading to inefficient resource allocation and potential service disruptions.

Innovation Solution

A method and system using machine learning models, including time series forecasting and clustering, to predict the impact of faults on user equipment data rates, enabling service-centric fault management by identifying and prioritizing faults based on their effect on user experience.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If equipment-centric fault detection is used, then fault identification capability is improved, but fault impact analysis and prioritization deteriorates

Engineering Contradiction:
Improvefault detection capabilityVSAvoidfault impact information
Core Design Contradiction:
Difficulty of detecting and measuringVSLoss of information

Solution Approach 1:

The patent segments the fault management process into two distinct phases: (1) equipment-centric fault detection using machine learning models to identify faulty base stations, and (2) service-centric impact analysis using clustering algorithms to group affected users and prioritize faults based on user experience degradation. This segmentation allows each phase to focus on its specific objective without compromising the other.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from a single-dimension equipment-centric approach to a multi-dimensional approach by introducing a service impact dimension. The system not only detects faults at the base station level but also analyzes and prioritizes them based on their impact on user services, adding a new dimension of service quality assessment to the traditional equipment monitoring dimension.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Ease of operation

If equal weightage is given to all faults, then fault management simplicity is improved, but network operation efficiency deteriorates

Engineering Contradiction:
Improvefault management simplicityVSAvoidnetwork operation efficiency
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The patent applies local quality by differentiating the treatment of faults based on their local impact characteristics. Instead of uniform treatment, the system clusters faults according to their impact on specific user groups and network segments, allowing operators to prioritize and respond differently to faults based on their localized service impact rather than treating all faults equally.

Inventive Principle:
Principle #3Local quality

3Measurement precision

If manual fault diagnosis is used, then diagnostic accuracy is improved, but scalability and complexity management deteriorates

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidnetwork complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements self-service by enabling the network to autonomously detect, analyze, and prioritize faults using machine learning models and clustering algorithms. The system automatically processes network data, identifies patterns, and ranks faults based on their impact without requiring manual intervention, thereby maintaining high diagnostic accuracy while improving scalability and reducing operational complexity.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4648465A1Method and system for network fault management by predicting average rate at faulty base station
Publication Date: 2025.11.12 TATA CONSULTANCY SERVICES LTD
  • EP4648465A1 patent drawingFigure 1
  • EP4648465A1 patent drawingFigure 2
  • EP4648465A1 patent drawingFigure 3

AI summary

This disclosure relates generally to a method and system for network fault management. Conventionally, faults are analyzed by setting rules based on network experts' experience, such as duration of faults or predefined categories of faults, to determine which faults need to be handled with higher priority. The present disclosure addresses these problems through a method of performing network fault management at a faulty base station using a timeseries forecasting model coupled with a clustering algorithm. The time series forecasting model considers a plurality of network parameters received from a plurality of base stations serving at least one user equipment (UE) and trains the model to predict an average data rate at the faulty BS. Further the model receives the network parameters for a cluster comprising the faulty BS and re-trains itself. Finally, the model prioritizes the faults based on decreased average data rate of the UE at the faulty BS.