Bandwidth Estimation Device Service Segmentation Accuracy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current band estimation methods in communication networks lack accuracy due to the collective analysis of diverse services, leading to inaccuracies in determining the necessary bandwidth, especially with varying user traffic patterns and service demands.

Innovation Solution

A band estimation device and method that classify traffic information by service and utilize contract band information to estimate necessary bandwidth for each service, employing machine learning and periodicity analysis to improve accuracy and facilitate facility expansion decisions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If traffic information is collectively analyzed without distinguishing various services, then the analysis process is simplified, but the accuracy of necessary band estimation deteriorates

Engineering Contradiction:

Improveanalysis process complexityVSAvoidnecessary band estimation accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments traffic information by service type, dividing the collective traffic analysis into distinct service categories. The classification unit separates traffic into different service groups, and the estimation unit calculates necessary bands for each service separately, thereby improving estimation accuracy while maintaining manageable complexity through structured segmentation

Inventive Principle:

Principle #1Segmentation

2Adaptability or versatility

If services with different elements are collectively analyzed, then the overall traffic overview is obtained, but the estimation accuracy for each service deteriorates

Engineering Contradiction:

Improvetraffic analysis coverageVSAvoidservice-specific estimation accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent implements segmentation by service type, where the classification unit divides traffic information into distinct service categories based on service elements. This allows the system to maintain comprehensive coverage of all services while performing separate, accurate estimations for each service type, resolving the contradiction between overall coverage and service-specific precision

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by tailoring the estimation process to each service type's specific characteristics. The estimation unit performs customized band estimation for each service category based on its unique traffic patterns and requirements, thereby achieving high accuracy for each service while maintaining versatility across diverse service types

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS20240259858A1Bandwidth prediction device, bandwidth prediction method, and program

Publication Date: 2024.08.01 NIPPON TELEGRAPH & TELEPHONE CORP

AI summary

A band estimation device (10) according to the present disclosure includes: a classification unit (11) that acquires traffic information regarding traffic from a communication device (20) and classifies the acquired traffic information for each service; and an estimation unit (14) that estimates a necessary band for each service on the basis of the traffic information for each service and contract band information regarding a contract band of each of a plurality of users.