Cell Capacity Saturation Forecasting Using Abnormal Pattern Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for forecasting cell capacity saturation in wireless communication systems are inaccurate due to their reliance on uniform rules, failing to account for abnormal patterns caused by specific events within cells.

Innovation Solution

The implementation of an AI module that detects and categorizes abnormal patterns in cell resource utilization data to forecast cell saturation, enabling informed decisions on deploying new cells based on increasing or decreasing patterns.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If uniform rules are used for forecasting cell capacity saturation, then the forecasting process is simple, but the accuracy of cell saturation forecast deteriorates due to inability to account for abnormal patterns

Engineering Contradiction:
Improveforecasting process complexityVSAvoidcell saturation forecast accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments the cell resource utilization data into different patterns (normal patterns and abnormal patterns) based on specific events. By dividing the data into distinct categories, the system can apply different forecasting approaches for each pattern type, thereby improving forecast accuracy while maintaining manageable complexity through systematic classification.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different forecasting rules and parameters depending on the local characteristics of each data pattern. For abnormal patterns caused by specific events, the system uses event-specific forecasting parameters, while for normal patterns, it uses standard parameters. This localized approach ensures that each pattern is forecasted with appropriate precision without requiring complete redesign of the entire forecasting system.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If AI module with abnormal pattern detection is implemented, then the cell saturation forecast accuracy is improved, but the device complexity increases

Engineering Contradiction:
Improvecell saturation forecast accuracyVSAvoidforecasting system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary classification of cell resource utilization data into different patterns before applying forecasting algorithms. By pre-identifying abnormal patterns and their associated events, the system prepares the data in advance for more accurate forecasting. This preliminary action reduces the complexity of the main forecasting process by organizing data into manageable categories beforehand.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary classification layer between data collection and forecasting that identifies and categorizes abnormal patterns. This intermediary component acts as a mediator that translates raw complex data into structured pattern categories, making the subsequent forecasting process more accurate and manageable without requiring the entire system to be overly complex.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If per-cell resource utilization monitoring is performed, then the management precision of base stations is improved, but the loss of time and computational resources increases

Engineering Contradiction:
Improvebase station management precisionVSAvoiddata processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts and focuses monitoring efforts on key performance indicators and specific abnormal patterns rather than analyzing all possible parameters continuously. By taking out only the most relevant data elements for forecasting purposes, the system maintains high management precision while reducing the time and computational resources required for processing.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies monitoring and analysis at appropriate levels of detail - using full precision only when abnormal patterns are detected, while using simplified monitoring for normal conditions. This partial action approach ensures that computational resources are concentrated where they provide the most value, balancing precision requirements with resource constraints.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3844995B1Method and apparatus for forecasting cell capacity saturation in wireless communication system
Publication Date: 2023.12.13 SAMSUNG ELECTRONICS CO LTD
  • EP3844995B1 patent drawingFigure 1a
  • EP3844995B1 patent drawingFigure 1b~2a
  • EP3844995B1 patent drawingFigure 2b

AI summary

The present disclosure relates to a pre-5th-Generation (5G) or 5G communication system to be provided for supporting higher data rates Beyond 4th-Generation (4G) communication system such as Long Term Evolution (LTE). A method and an apparatus for forecasting capacity saturations of cells in a wireless communication system based on per-cell resource utilizations and determining whether to deploy a new cell based on a forecast result are provided. The method includes acquiring first data related to a resource utilization of a cell from the cell, deducing a certain pattern corresponding to a predetermined time period from the first data, acquiring second data by converting the first data based on a shape of an abnormal pattern corresponding to the certain pattern among multiple preconfigured abnormal patterns, and forecasting whether the cell capacity is saturated based on the second data.