Application-Centric Network Measurement Infrastructure
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network optimization techniques face challenges in distinguishing and optimizing traffic flows for specific applications due to the use of shared protocols, such as HTTP and HTTPS, and the increasing complexity of service level agreements (SLAs) in enterprise networks, leading to inefficient network performance and potential SLA violations.
Innovation Solution
A predictive and dynamic application-centric network measurement infrastructure that uses machine learning techniques to analyze traffic patterns, simulate application traffic, and adjust probing schedules to ensure SLAs are met, incorporating a traffic sensing process, probe crafting, probe timing, and probe routing to generate application-aware and application-centric probes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional network measurement techniques are used, then network monitoring is performed, but traffic flows cannot be distinguished for specific applications due to shared protocols
Solution Approach 1:
The patent segments network traffic measurement by application type, creating separate measurement paths for different applications (e.g., video conferencing, voice, web browsing). Each application-specific measurement path uses tailored probe packets designed to match that application's traffic characteristics, enabling precise distinction and measurement of otherwise indistinguishable HTTP/HTTPS flows.
Solution Approach 2:
The system performs preliminary actions by proactively generating application-specific probe packets before actual application traffic occurs. These probes are crafted in advance to simulate specific application traffic patterns, allowing the network to pre-establish measurement baselines and detect performance issues before they impact real user experience.
2Reliability
If network probing is performed continuously, then network performance is monitored, but network resources are consumed and performance may be degraded
Solution Approach 1:
The patent implements periodic action by sending probes at strategically determined intervals rather than continuously. The probe timing is dynamically adjusted based on network conditions, application requirements, and SLA parameters, sending probes only when necessary to detect performance degradation while minimizing resource consumption and interference with normal traffic.
Solution Approach 2:
The system dynamically adapts probe characteristics including packet size, interval, and routing based on real-time network conditions and application requirements. This dynamic adjustment allows the measurement infrastructure to optimize between reliability (detecting SLA violations) and productivity (minimizing probe impact on network throughput).
3Measurement precision
If application-specific probes are crafted, then measurement accuracy is improved, but probe generation complexity increases
Solution Approach 1:
The patent uses copying by creating simplified probe packets that replicate the essential characteristics of actual application traffic without requiring full copies. Each application-specific probe copies only the necessary traffic features (packet size, timing patterns, protocol headers) needed to measure that application's performance, reducing probe generation complexity while maintaining measurement accuracy.
4Reliability
If multiple SLAs are managed, then service quality is ensured, but network management complexity increases
Solution Approach 1:
The patent implements universality by creating a multi-functional measurement infrastructure that handles multiple SLAs through a unified application-centric framework. The same probe generation and analysis mechanism serves all applications and SLAs, with automatic adaptation to different requirements, reducing management complexity while ensuring comprehensive SLA compliance across diverse services.
Data Source
AI summary
In one embodiment, a device in a network receives data indicative of traffic characteristics of traffic associated with a particular application. The device identifies one or more paths in the network via which the traffic associated with the particular application was sent, based on the traffic characteristics. The device determines a probing schedule based on the traffic characteristics. The probing schedule simulates the traffic associated with the particular application. The device sends probes along the one or more identified paths according to the determined probing schedule.