Cell Degradation Detection via Correlation Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for detecting cell degradation in wireless communications networks are plagued by high false positives, computational complexity, and require significant human intervention, making them inefficient and unreliable.

Innovation Solution

A method using a first network node to determine cell degradation by comparing observed performance values with generated degraded patterns through correlation analysis, focusing on similarities rather than dissimilarities, and employing a dynamic threshold to reduce false positives and computational load.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional threshold-based monitoring is used to detect cell degradation, then the detection mechanism is simple to implement, but it produces high false positives and cannot detect local degradations within normal ranges

Engineering Contradiction:
Improvedetection accuracyVSAvoiddetection algorithm complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent pre-generates multiple degraded patterns representing different types of cell degradations before actual detection occurs. These patterns are stored and used as reference templates during runtime, allowing the system to quickly compare observed values against known degradation signatures without complex real-time analysis

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent creates simplified copies of degraded cell states in the form of pattern templates. Instead of analyzing complex raw data in real-time, the system compares observed performance values against these pre-created pattern copies, significantly reducing computational complexity while maintaining detection accuracy

Inventive Principle:
Principle #26Copying

2Reliability

If adaptive algorithms with learning stages are used to reduce false positives, then detection accuracy improves, but computational complexity and processing time increase significantly

Engineering Contradiction:
Improvefalse positive reductionVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The learning and pattern generation process is performed in advance during system initialization or offline stages. The pre-generated degraded patterns capture the essential characteristics of various failure modes without requiring real-time computation, enabling fast detection during actual operation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent extracts only the essential features of degradation patterns that are necessary for detection, storing them in compact template form. This extraction eliminates unnecessary computational overhead while retaining the key characteristics needed for accurate degradation detection

Inventive Principle:
Principle #2Taking out (Extraction)

3Reliability

If multiple performance indicators are monitored to improve detection reliability, then more degradation types can be detected, but the number of thresholds to configure and false alarms increase

Engineering Contradiction:
Improvedetection coverageVSAvoidconfiguration effort
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent creates a universal detection framework where a single correlation-based mechanism can detect multiple types of cell degradations across different performance indicators. The pre-generated degraded patterns serve as multi-functional templates that can match various degradation scenarios without requiring separate configuration for each indicator

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system changes the approach from fixed threshold parameters to pattern-based correlation parameters. Instead of configuring multiple thresholds for different indicators, the system uses correlation coefficients against pre-generated patterns, automatically adapting to different degradation types without manual parameter adjustment

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3298817B1First network node, method therein, computer program and computer-readable medium comprising the computer program for determining whether a performance of a cell is degraded or not
Publication Date: 2018.12.12 TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
  • EP3298817B1 patent drawingFigure 1
  • EP3298817B1 patent drawingFigure 2
  • EP3298817B1 patent drawingFigure 3~4

AI summary

A method performed by a first network node (110) for determining whether a performance of a cell (130) associated with a second network node (120) is degraded or not. The first network node (110) and the second network node (120) operate in a wireless communications network (100). The first network node (110) obtains(201) a first set of values making up a pattern comprising a set of values indicative of a performance of the cell (130). The first network node (110) then determines(204) a first correlation between the obtained first set of values and a generated set of values. The generated set of values is indicative of a degraded performance of the cell (130). The first network node (110) then determines(206) whether the performance of the cell (130) is degraded or not based on the determined first correlation, with respect to a first threshold.