Steady-State Throughput Measurement via Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining end-to-end link speed in computer networks are prone to distortion due to flow control mechanisms and lower layer protocols, leading to inaccurate measurements of steady-state throughput, which can result in inefficient data transfer and failure to adapt to network congestion.
Innovation Solution
A method and apparatus that determine sustainable average data throughput rates by timing data delivery during steady-state conditions, accounting for potential distortion effects from flow control or similar protocols, and isolating the transfer of data segments when the network is at or near its sustainable capacity, allowing for precise measurement and adaptation to congestion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If timing methods are used to determine end-to-end throughput, then throughput measurement is achieved, but measurement precision deteriorates due to distortion from flow control mechanisms and lower layer protocols
Solution Approach 1:
The patent segments the data transfer process into distinct phases: connection establishment phase, steady-state phase, and termination phase. By isolating and measuring only the steady-state phase, the method eliminates distortion from connection establishment dynamics and flow control mechanisms, thereby improving measurement precision and reliability
Solution Approach 2:
The patent implements preliminary actions by sending probe packets before actual data transfer to establish steady-state conditions. This preliminary probing allows the system to wait for flow control mechanisms to stabilize before beginning measurements, ensuring that subsequent throughput measurements are not distorted by transient effects
2Adaptability or versatility
If data transfer adaptation to network conditions is implemented, then adaptability improves, but device complexity increases due to additional measurement and control mechanisms
Solution Approach 1:
The patent implements feedback mechanisms where throughput measurements taken during steady-state conditions are used to dynamically adjust data transfer rates. The system continuously monitors network conditions and adapts transmission parameters based on measured performance, improving adaptability while maintaining manageable complexity through standardized feedback loops
Solution Approach 2:
The system performs self-service by automatically measuring its own throughput performance and using this information to adjust its data transfer behavior. The embedded measurement mechanisms enable the system to self-diagnose network conditions and self-adjust transmission parameters without external intervention, improving adaptability while avoiding the complexity of external control systems
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Sustainable average data throughput rates for data transfer between a sender and a receiver are determined for a network in a steady-state condition. Delivery performance for data transferred in non-steady-state conditions is disregarded in determining sustainable average data throughput rates. The rates may be used to adapt file delivery to network conditions.