AI-Enhanced Data Sampling for Network Traffic Reduction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Determining the optimal sampling rate for communication devices in communication networks is challenging, leading to high network traffic and resource overload due to typically high sampling rates.

Innovation Solution

A method involving fine-grain sampling followed by machine learning algorithm training to reduce sampling rates while maintaining accuracy, using coarse-grain sampling intervals and machine learning inference to produce accuracy-enhanced samples.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high sampling rates are used to ensure accurate samples, then measurement precision is improved, but network traffic and resource usage increase

Engineering Contradiction:
Improvesampling accuracyVSAvoidnetwork traffic
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent segments the sampling process into two distinct phases: fine-grain sampling at high rates for training purposes, and coarse-grain sampling at lower rates for operational use. This segmentation allows the system to capture detailed patterns during training while reducing resource consumption during normal operation, thereby resolving the contradiction between measurement precision and network traffic volume.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary fine-grain sampling and machine learning model training before transitioning to coarse-grain sampling. By pre-processing the data at high resolution to build an accurate predictive model, the system can subsequently operate at lower sampling rates while maintaining accuracy, thus reducing network traffic without sacrificing measurement precision.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If high sampling rates are used to ensure accurate samples, then measurement precision is improved, but communication and processing resources are overloaded

Engineering Contradiction:
Improvesampling accuracyVSAvoidprocessing resources
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the processing workload into two stages: intensive fine-grain sampling and model training performed preliminarily, followed by lightweight coarse-grain sampling using the trained model. This segmentation transfers the heavy processing burden to an initial training phase, allowing operational devices to function with reduced processing requirements while maintaining high measurement precision.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary fine-grain sampling and model training before deployment. By pre-computing the complex processing tasks during the training phase, the operational phase requires minimal processing resources, thus resolving the contradiction between measurement precision and device complexity.

Inventive Principle:
Principle #10Preliminary action

3Loss of energy

If coarse-grain sampling is used to reduce network traffic, then loss of energy is reduced, but measurement precision deteriorates

Engineering Contradiction:
Improvenetwork energy consumptionVSAvoidsampling accuracy
Core Design Contradiction:
Loss of energyVSMeasurement precision

Solution Approach 1:

The patent performs preliminary fine-grain sampling to train a machine learning model that captures the underlying patterns and relationships in the data. This preliminary high-precision sampling enables subsequent coarse-grain sampling to achieve accurate measurements by leveraging the learned patterns, thus reducing energy consumption without sacrificing measurement precision.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The machine learning model acts as an intermediary between fine-grain and coarse-grain sampling. It translates detailed fine-grain data into patterns that can be accurately reconstructed from sparse coarse-grain samples, enabling energy-efficient sampling while maintaining measurement precision through the mediating intelligence of the trained model.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4221131B1Artificial intelligent enhanced data sampling
Publication Date: 2025.01.22 HUAWEI TECH CO LTD
  • EP4221131B1 patent drawingFigure 1
  • EP4221131B1 patent drawingFigure 2
  • EP4221131B1 patent drawingFigure 3

AI summary

Monitoring an operational characteristic of a data communication device within a network includes sampling an operational characteristic of the data communication device at a fine-grain sample rate over a first sampling interval to produce fine-grain samples of the operational characteristic of the data communication device, training a machine learning algorithm using the fine-grain samples of the operational characteristic of the data communication device, the fine-grain sample rate, and a coarse-grain sample rate that is less than the fine-grain sample rate, sampling the operational characteristic of the data communication device at the coarse-grain sample rate over a second sampling interval to produce coarse-grain samples of the operational characteristic of the data communication device, and using the machine learning algorithm to process the coarse-grain samples of the operational characteristic of the data communication device to produce accuracy-enhanced samples of the operational characteristic of the data communication device.