Network Congestion Analyzer Using Packet Data Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for analyzing congestion in low latency networks are inefficient due to the large storage requirements and unwieldy query times caused by high traffic rates, which can reach 10 Gbps, resulting in excessive data storage needs and slow analysis.

Innovation Solution

A congestion analyzer system that employs a sniffer tool to capture packet information and store it in a database with defined tables for flow, congestion, and packet data, allowing for efficient monitoring and analysis of network traffic, including packet size, arrival time, and latency, while using lightweight storage and user-defined congestion thresholds.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If packet dump is captured at high traffic rate (10 Gbps), then complete network traffic data is obtained for analysis, but storage requirements become excessive (108 TB per day) and query times become unwieldy

Engineering Contradiction:

Improvecongestion analysis accuracyVSAvoiddata storage volume

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential congestion-related information from packet data (timestamps, packet lengths, inter-arrival times) rather than storing complete packet dumps. This selective extraction reduces storage requirements from 108 TB per day to manageable sizes while preserving the ability to detect and analyze congestion events.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of storing all packet data and then querying for congestion analysis, the system inverts the approach by pre-processing packet data to extract only congestion-relevant metrics and storing these processed results. This allows fast query times without requiring storage of the original large-volume packet dumps.

Inventive Principle:

Principle #13The other way round (Inversion)

2Measurement precision

If complete packet dump is stored for congestion analysis, then comprehensive traffic data is available, but query times become excessively long due to the large amount of data

Engineering Contradiction:

Improvecongestion detection capabilityVSAvoidquery time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary processing of packet data by pre-calculating congestion-relevant metrics (inter-arrival times, packet lengths, timestamps) and storing these processed results in structured tables. When congestion analysis is needed, the system queries these pre-processed results rather than analyzing raw packet dumps, dramatically reducing query times.

Inventive Principle:

Principle #10Preliminary action

3Loss of information

If all packet data is captured and stored, then complete network traffic information is retained, but storage space is wasted due to the huge amounts of data generated

Engineering Contradiction:

Improvenetwork traffic information completenessVSAvoidstorage space

Core Design Contradiction:

Loss of informationVSQuantity of substance

Solution Approach 1:

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system changes the parameters being stored from complete packet data to condensed congestion metrics (inter-arrival times, packet lengths, timestamps). This parameter transformation maintains the essential information needed for congestion analysis while dramatically reducing the volume of stored data.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS10182011B2System and method to analyze congestion in low latency network

Publication Date: 2019.01.15 CISCO TECHNOLOGY INC

AI summary

Intelligent packet analysis may be provided to determine congestion problems and lead to fast solutions in low latency networks. Specifically, a congestion analyzer system may allow a user to monitor congestion on a network while using lightweight storage. A sniffer tool may be employed to capture all packets and store associated packet information into a database.