Network Traffic Measurement via Component-Level Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computing systems face challenges in identifying contributors to network traffic, leading to inefficient traffic optimization due to insensitivity of existing monitors to component-level issues and high latency in querying large volumes of traffic data, which can result in customer dissatisfaction and resource overconsumption.
Innovation Solution
A network traffic computing system that aggregates data from on-router traffic, on-server traffic, and application logs, performs feature extraction, splits data by source and destination ports, and provides component-level traffic measurements to enable effective monitoring and control, reducing data size and resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If on-router traffic sampling systems are used to monitor network traffic, then traffic data can be collected, but the system cannot identify component-level traffic contributors due to lack of granularity
Solution Approach 1:
The patent segments network traffic data by application, component, and protocol layers, organizing raw traffic data into structured components that can be analyzed at different granularities. This segmentation enables component-level identification while managing complexity through hierarchical organization of traffic attributes.
Solution Approach 2:
The patent introduces an intermediary data processing layer that sits between raw traffic capture and analysis. This intermediary layer aggregates and structures traffic data from multiple sources (on-router sampling, on-server monitoring, flow logs) into a unified component-level view, resolving the contradiction between measurement precision and system complexity.
2Productivity
If large volumes of traffic data are collected for continuous optimization control, then traffic analysis can be performed, but query latency increases leading to slow response times
Solution Approach 1:
The patent performs preliminary aggregation and structuring of traffic data in advance, organizing data by component, application, and time intervals before queries are executed. This preliminary action creates pre-processed data structures that enable fast querying and reduce latency when optimization decisions need to be made.
Solution Approach 2:
The patent implements dynamic data retention policies where traffic data is aggregated at different time granularities (second-level, minute-level, hourly) based on the specific query needs. This dynamic approach allows the system to retrieve only the necessary data volume for each query, balancing comprehensive analysis with fast response times.
3Reliability
If comprehensive traffic monitoring is implemented across all components, then complete traffic visibility is achieved, but resource consumption on production servers increases
Solution Approach 1:
The patent merges multiple traffic data sources (on-router sampling data, on-server monitoring data, and flow log data) into a unified analysis framework. This merging allows comprehensive traffic visibility to be achieved by combining complementary data sources rather than implementing intensive monitoring on every component, reducing overall resource consumption while maintaining monitoring accuracy.
Solution Approach 2:
The patent applies partial monitoring strategies where not all traffic components are monitored at the same intensity. Instead, the system identifies key traffic contributors and focuses detailed analysis on those components, while using aggregated data for less critical traffic flows. This partial action approach maintains reliability for critical components while reducing resource consumption across the entire system.
Data Source
AI summary
A network traffic computing system obtains on-router traffic data, on-server traffic data and application log data. A data processing system extracts features from the data sources, splits the extracted features based upon destination and source ports and performs component-level aggregation of the features. The aggregated data is surfaced for monitoring and traffic control.