Network Traffic Demand Estimation via Passive Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network monitoring systems fail to accurately measure end-to-end packet loss in large computer networks, as active monitoring under-samples real traffic and passive monitoring lacks comprehensive data for determining end-to-end path loss.
Innovation Solution
A method that passively collects packet transmission and drop rates from network devices to estimate end-to-end traffic demand and loss by forming and solving simultaneous equations, generating traffic and loss matrices that account for packet loss at each device, using a gravity model and optimization techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If active monitoring is used to measure packet loss, then end-to-end path loss can be measured, but the measurement accuracy is poor due to under-sampling of real traffic
Solution Approach 1:
The patent uses passive monitoring to create a copy of actual network traffic data, analyzing real packet flows without injecting probe packets. This copying approach allows accurate measurement of end-to-end packet loss by observing actual traffic patterns rather than relying on low-rate probe packets, thereby resolving the contradiction between measurement accuracy and sampling quantity.
2Measurement precision
If passive monitoring is used to collect transmission statistics, then accurate device-level loss rate can be obtained, but end-to-end path loss cannot be determined
Solution Approach 1:
The patent merges device-level passive monitoring data from multiple network devices along a path with active monitoring path information. By combining the accurate device-level loss rates with the path topology data, the system reconstructs end-to-end path loss measurements, thereby resolving the contradiction between obtaining accurate device-level data and determining complete end-to-end path loss.
Solution Approach 2:
The patent introduces an intermediary computational model that acts as a bridge between device-level monitoring data and end-to-end path loss determination. This intermediary process uses the passive monitoring statistics from individual devices, combined with path information, to calculate and infer the overall end-to-end packet loss, thus recovering the lost information without requiring direct end-to-end measurement.
3Productivity
If existing traffic matrix determination methods are used, then traffic volume can be estimated, but packet loss is not accounted for leading to erroneous results
Solution Approach 1:
The patent changes the parameters used in traffic matrix determination by incorporating packet loss rates as an additional variable. Instead of using only transmission volume data, the method integrates loss rate parameters from passive monitoring into the traffic matrix calculation, thereby accounting for packet loss and improving the accuracy of traffic volume estimation without sacrificing computational efficiency.
Data Source
AI summary
Packet transmission rate and packet drop rate for discrete network devices in a network are used to estimate end-to-end traffic demand and loss in the network. Data regarding the packet transmission rate and drop rate are passively collected for each network device and transmitted to a network monitoring unit. The network monitoring unit compiles the data and generates a series of simultaneous equations that represent traffic demand and loss between the discrete network devices along the paths connecting respective source-destination pairs. By determining an optimal solution to the simultaneous equations, an estimate of end-to-end traffic loss and corresponding traffic demand, which takes into account packet loss at each network device, can be generated for each source-destination pair. The optimal solution can be formed as a traffic matrix, which aggregates source-to-destination traffic demands, and a loss matrix, which aggregates source-to-destination traffic losses.