Network Link Bandwidth Determination via Packet Loss Rate Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining the bandwidth of a communication link within a network is challenging due to the complexity of traffic management schemes and the difficulty in identifying bottleneck bandwidth, especially since many devices communicate in an end-to-end manner, making it opaque to devices outside of ISPs how many TCP connections are established over a link.
Innovation Solution
A method involving sending data packets at multiple transmission rates and measuring associated packet loss rates to determine the bandwidth of a link, allowing nodes to calculate bandwidth without knowing the total number of data streams supported by the link, using a function that relates transmission rate and packet loss rate.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traffic management schemes are implemented by ISPs to prioritise certain types of network traffic, then network traffic can be effectively managed and bandwidth allocated to different applications, but the schemes become complex and time consuming to implement
Solution Approach 1:
The patent enables network nodes (such as content servers) to autonomously determine the bandwidth of communication links they utilise by measuring packet loss rates at different transmission rates. This self-service approach eliminates the need for complex ISP-implemented traffic management schemes, as each node independently manages its own bandwidth allocation based on measured link characteristics rather than relying on external traffic management infrastructure.
2Ease of operation
If devices communicate in an end-to-end manner, then communication is simplified and devices can operate independently, but the location of bottleneck links becomes transparent to devices making it difficult to determine available bandwidth
Solution Approach 1:
The patent implements a feedback mechanism where network nodes measure packet loss rates at different transmission rates and use this feedback information to determine the bandwidth of communication links. By monitoring the relationship between transmission rate and packet loss rate, nodes can infer bottleneck link characteristics and available bandwidth without breaking end-to-end communication transparency. This feedback loop restores bandwidth information availability while preserving the simplicity of end-to-end communication.
3Productivity
If multiple data streams are transmitted over a communication link, then network capacity is utilised efficiently, but determining the bandwidth of the link becomes difficult without knowledge of the number of data streams
Solution Approach 1:
The patent changes the parameter being measured from direct bandwidth calculation (which requires knowledge of the number of data streams) to packet loss rate measurement at different transmission rates. By varying the transmission rate parameter and observing the corresponding packet loss rate, nodes can determine link bandwidth through the relationship between these parameters without needing to know how many data streams are sharing the link. This parameter transformation solves the measurement difficulty while maintaining efficient multi-stream transmission.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of determining the bandwidth of a link carrying a plurality of data streams between a plurality of sources and a plurality of destinations in a network, said method comprising: sending data packets from a first data stream over the link from one source to one destination at a first transmission rate, and measuring an associated first packet loss rate; sending further data packets from the first data stream over the link from the one source to the one destination at a second transmission rate, and measuring an associated second packet loss rate; and determining the bandwidth of the link in dependence on the first and second packet loss rates and the first and second transmission rates.