Echo Timing for Reliable Distributed Application Latency Measurement

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Distributed real-time applications suffer from high latency and jitter in communication connections, leading to potential failures, which existing methods fail to accurately measure without modifying the applications.

Innovation Solution

A method involving a terminal device sender transmitting data packets and separate measuring application ping packets at a rate at least double the data packet rate, calculating time intervals between transmitted and received echo packets to determine transmission stop and start times, and packet rates, without modifying the distributed real-time application.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a separate measuring application transmits ping packets to measure latency, then latency measurement capability is improved, but measurement precision deteriorates due to inability to accurately capture data packet transmission timing

Engineering Contradiction:
Improvelatency measurement accuracyVSAvoidtransmission timing information
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The measuring application uses the calculated time intervals from ping packets as feedback to determine data packet transmission timing. By monitoring how time intervals change (rapidly shorten or lengthen), the system infers transmission stop and start times without directly observing data packets, thus recovering lost timing information through indirect feedback measurement

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The ping packets serve as an intermediary to indirectly measure the timing of data packets. Instead of attempting to directly measure data packet transmission (which loses timing information), the system uses ping packets as a mediator whose time interval changes reflect the underlying data packet transmission events

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If ping packets are transmitted at a high rate to improve measurement accuracy, then measurement precision is improved, but network load increases

Engineering Contradiction:
Improvelatency measurement accuracyVSAvoidnetwork traffic volume
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The system changes the parameter of ping packet transmission rate dynamically. By setting the ping rate to at least double the data packet rate, the system achieves sufficient measurement precision while controlling the quantity of ping packets. This parameter optimization allows accurate timing determination through time interval analysis without generating excessive network traffic

Inventive Principle:
Principle #35Parameter changes

3Ease of operation

If existing latency measurement methods are used without modifying applications, then ease of operation is improved, but measurement precision deteriorates due to inability to accurately determine data packet transmission timing

Engineering Contradiction:
Improvemeasurement implementation simplicityVSAvoidtransmission timing accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system replaces direct mechanical observation of data packet transmission with an indirect measurement mechanism using ping packets. Instead of modifying the application to directly track data packet timing (mechanical approach), it substitutes a separate measuring application that uses time interval analysis of ping packets to infer transmission timing, maintaining ease of operation while improving precision

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12375383B2Reliable and accurate latency measurement
Publication Date: 2025.07.29 DEUTSCHE TELEKOM AG
  • US12375383B2 patent drawing
  • US12375383B2 patent drawing

AI summary

A method for measuring a latency of a connection includes a sender of a distributed application that transmits a plurality of data packets to a receiver of the distributed application via a connection. A measuring application transmits a plurality of packets to an application server, receives a plurality of echo packets from the application server, where each echo packet is caused by a transmitted packet, and calculates time intervals between transmitting a packet and receiving the caused echo packet. The measuring application determines a transmission stop time of a transmitted data packet as a time point when the calculated time intervals rapidly shorten, and/or a transmission start time of a transmitted data packet as a time point when the calculated time intervals rapidly lengthen, and/or a packet rate of the transmitted data packets by counting the transmission start times or the transmission stop times during a second.