Application Session Performance Compensation via Link Probing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network solutions lack the ability to selectively and efficiently reroute traffic experiencing performance degradation, particularly when a high-priority application session is under attack, due to the operational expense of current traffic engineering and quality of service mechanisms.
Innovation Solution
A link probing mechanism identifies the lowest performing application session and performs corrective actions such as rerouting packets to a different queue or network link, distinguishing between normal congestion and attack-induced degradation by analyzing performance and priority thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traffic engineering and quality of service mechanisms are used to handle overwhelmed router links, then network traffic can be managed and routed, but operational expense increases significantly due to added overhead
Solution Approach 1:
The system uses self-service by having the network automatically detect performance degradation through performance metrics collection and analysis, identify the lowest performing application sessions, and trigger corrective actions without requiring manual traffic engineering intervention. The router autonomously monitors its own links and application sessions, eliminating the need for complex external traffic engineering mechanisms.
Solution Approach 2:
The system changes parameters by monitoring performance metrics (such as packet loss, latency, bandwidth utilization) of application sessions and dynamically adjusting routing decisions based on these parameter changes. When performance degradation is detected, the system modifies the routing path for affected application sessions while leaving other sessions unchanged, thereby avoiding the need for comprehensive QoS mechanisms across all traffic.
2Ease of operation
If routing is performed by destination address only, then routing is simple and conventional, but there is no ability to selectively reroute traffic belonging to particular application sessions
Solution Approach 1:
The system segments traffic into individual application sessions, each with its own performance metrics and routing requirements. Instead of treating all traffic to a destination address uniformly, the system divides traffic into separate application session flows and monitors each independently. This allows selective identification and rerouting of only those application sessions experiencing performance degradation, while maintaining simple destination-based routing for the majority of traffic.
Solution Approach 2:
The system introduces dynamics by enabling routing paths to change based on real-time performance conditions of individual application sessions. While the base routing remains simple and destination-based, the system dynamically adjusts the routing path for specific application sessions when performance degradation is detected, creating a hybrid approach that combines routing simplicity with selective adaptability.
3Measurement precision
If all application sessions on a network link experience performance degradation, then normal congestion is occurring, but if a particular application session experiences the worst performance, then an attack is likely occurring on that session
Solution Approach 1:
The system applies partial action by focusing performance analysis and corrective actions only on the specific application session exhibiting the worst performance, rather than analyzing or modifying all application sessions equally. When performance degradation is detected, the system identifies the single lowest performing session and applies corrective routing only to that session, reducing the overhead of performance analysis while maintaining precise detection capabilities.
Data Source
AI summary
Disclosed is a method and apparatus for compensating for a performance degradation of an application session in a plurality of application sessions associated with a network link. The performance of each application session in the plurality of application sessions associated with the network link is determined. The performance of each application session in the plurality is then compared. From this comparison, a lowest performance application session in the plurality of application sessions is identified. Corrective action is performed on packets scheduled to be transmitted over the lowest performance application session.