One-Way Latency Estimation Using Post-Collection Skew Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing two-way latency tests in telecommunication networks, such as TWAMP, struggle to accurately estimate one-way latency values when local and remote clocks are not synchronized, leading to unreliable results due to clock skew or offset, which is particularly problematic in networks with asynchronous clocks.
Innovation Solution
A method is provided to identify and compensate for clock skew by monitoring network latency results, collecting minimum latency values over a time interval, estimating clock skew, and revising latency data using these minimum values to improve accuracy, reducing computational resources by performing calculations only after data collection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If two-way latency tests are performed without clock synchronization between local and remote nodes, then the tests can be deployed in networks with limited synchronization support, but the one-way latency values become unreliable due to clock skew
Solution Approach 1:
The patent introduces an intermediary computational process that uses round-trip latency measurements as a mediator to indirectly estimate clock skew. By sending test packets in both directions and measuring round-trip times, the system derives clock offset values without requiring direct clock synchronization, thus enabling one-way latency calculation in asynchronous networks
Solution Approach 2:
The patent replaces the mechanical/clock-based synchronization system with a computational estimation system. Instead of relying on physical clock synchronization mechanisms, the system uses mathematical calculations based on packet timing data to estimate and compensate for clock skew, substituting hardware-dependent synchronization with software-based computation
2Measurement precision
If clock skew compensation is performed continuously during data collection, then latency measurement accuracy is maintained, but computational resources are consumed during the measurement interval
Solution Approach 1:
The patent performs preliminary data collection during the measurement interval without continuous computation. All packet timing data is collected and stored first, then clock skew estimation and compensation are performed in a single batch operation after data collection completes, reducing computational load during the critical measurement phase
Solution Approach 2:
The patent skips continuous computational processing during data collection and rushes through the compensation calculation in a single batch operation after data collection. This approach rushes the computational intensive work to a single moment rather than distributing it continuously, reducing ongoing resource consumption
Data Source
AI summary
A method for determining whether clock skew may exist between a sending node and a remote node during two-way network testing (using protocols such as TWAMP), and a computational method for revising measured latency data to compensate for clock differences.The method for compensating for clock skew comprises monitoring the network latency between two nodes during a defined time interval. When clock skew is detected, a flag is set, and, after the time interval has completed, clock skew S is estimated using the minimum latency values for the interval. The recorded latency values for the interval are then revised using the calculated clock skew S, and one-way latency results reported.The improved accuracy can be achieved with only on a few computations after the data have been collected. This a posteriori approach saves on computational resources, which can be at a premium for network testing equipment.