Passive Network RTT Measurement via Packet Delta Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current passive monitoring techniques for network RTP delay are limited in measuring Round Trip Time (RTT) as they require active probing, clock synchronization, or packet tagging, which are complex and not applicable in all scenarios, especially for uni-directional RTP flows.
Innovation Solution
A method that calculates RTT by identifying and correlating packet deltas between network elements without requiring active packet generation, clock synchronization, or packet tagging, using a collector device to determine RTT from passive monitoring records provided by network elements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If active probing techniques (such as IPSLA and Mediatrace) are used to measure RTT delay, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent enables RTT measurement by having network elements autonomously calculate time differences between receiving packets in opposite directions and export these measurements automatically. The system serves itself by utilizing existing traffic flows and built-in packet timing capabilities, eliminating the need for external active probing mechanisms.
Solution Approach 2:
The patent introduces a collector as an intermediary that receives time difference measurements from network elements and computes the RTT delay. This mediator approach allows passive measurement without requiring complex active probing at each network element, simplifying the overall system while maintaining measurement precision.
2Measurement precision
If packet tagging and metadata are used for RTT measurement, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
Network elements automatically calculate and export time difference measurements using their inherent packet reception timing capabilities. No manual packet tagging or metadata injection is required, as the system utilizes existing packet timing information already available at each network element.
Solution Approach 2:
Instead of tagging packets with metadata to track RTT, the patent inverts the approach by having network elements calculate time differences based on when they receive packets and export these measurements. This eliminates the need for packet modification while achieving the same measurement goal.
3Measurement precision
If one-way delay with clock synchronization is used, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent utilizes the inherent packet timing capabilities of network elements to calculate time differences between receiving packets in opposite directions. Each network element independently performs the measurement using its own clock, eliminating the need for complex clock synchronization protocols between elements.
Solution Approach 2:
The patent extracts only the necessary timing information (packet reception times) from network elements and exports these measurements to a collector. By taking out only the essential time difference data rather than requiring full clock synchronization, the system achieves measurement precision without the complexity of synchronization mechanisms.
4Measurement precision
If active probing techniques are used, then RTT measurement capability is improved, but adaptability deteriorates
Solution Approach 1:
The patent enables RTT measurement to be applied universally across all traffic flows by having network elements calculate time differences for any packets they receive in opposite directions. The system is not limited to specific flow types or protocols, as it utilizes the general packet forwarding function already performed by all network elements.
Solution Approach 2:
Network elements autonomously perform RTT measurement for all traffic flows passing through them using their existing packet processing capabilities. This self-service approach eliminates the need for flow-specific active probing configurations, making the system adaptable to diverse traffic types without additional complexity.
Data Source
AI summary
A method is described and in one embodiment includes receiving at a first network element of a communications network a first packet corresponding to a first traffic flow from a first end user device to a second end user device at a time T1; receiving at the first network element a second packet corresponding to a second traffic flow from the second end user device to the first end user device at a time T2; calculating by the first network element a difference α1 between the time T1 and the time T2; creating at the first network element a first record including the calculated difference Δ1; and providing the first record to a network collector device, wherein the network collector device compares the first record with a second record received from a second network element to determine a Round Trip Time (“RTT”) delay for the communications network.