Congestion Window Adjustment via Round Trip Time Monitoring

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current TCP congestion control mechanisms, such as TCP New Reno, cannot guarantee the delivery of content within a specified time interval due to their reactive nature, leading to fluctuations in transmission rate and packet loss, which affects network throughput and buffer fill.

Innovation Solution

A method and apparatus that dynamically adjust the congestion window size based on measured round trip times, setting it to a higher value when round trip times are low and a lower value when they are high, to maintain optimal transmission rates and reduce packet loss, thereby ensuring timely delivery of content segments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Stability of the object's composition

If TCP uses reactive congestion control (reducing transmission rate after packet loss), then network stability is improved, but delivery time guarantee deteriorates

Engineering Contradiction:

Improvenetwork stabilityVSAvoiddelivery time guarantee

Core Design Contradiction:

Stability of the object's compositionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by proactively reducing the congestion window size before packet loss occurs. Instead of waiting for packet loss to trigger congestion control (reactive approach), the system monitors buffer fill levels and round trip time trends, and preemptively adjusts the transmission rate to prevent buffer overflow and packet loss, thereby ensuring timely content delivery while maintaining network stability

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements dynamics by continuously adapting the congestion window size based on real-time network conditions. The system dynamically adjusts the congestion window based on buffer fill levels, round trip time variations, and delivery deadlines, allowing the transmission rate to flexibly respond to changing network states rather than following a fixed additive-increase-multiplicative-decrease pattern

Inventive Principle:

Principle #15Dynamics

2Productivity

If TCP increases congestion window size gradually, then network throughput is improved, but packet loss increases due to buffer overflow

Engineering Contradiction:

Improvenetwork throughputVSAvoidpacket loss

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent applies feedback by continuously monitoring network conditions including buffer fill levels, round trip time, and packet acknowledgment patterns. This feedback information is used to dynamically adjust the congestion window size, preventing buffer overflow by reducing transmission rate when buffers are approaching capacity, while maximizing throughput when network conditions are favorable

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system uses feedback about buffer fill levels and RTT trends to take preliminary action before packet loss occurs. By detecting early signs of congestion (increasing buffer fill, rising RTT), the system preemptively reduces the congestion window to prevent buffer overflow and packet loss, maintaining both high throughput and reliability

Inventive Principle:

Principle #10Preliminary action

3Reliability

If TCP reduces congestion window size rapidly after packet loss, then packet loss is reduced, but network throughput deteriorates

Engineering Contradiction:

Improvepacket loss reductionVSAvoidnetwork throughput

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent inverts the traditional congestion control logic by reducing the congestion window proactively before packet loss occurs, rather than reacting after packet loss. This inversion allows the system to maintain higher average throughput by avoiding the severe throughput reduction that occurs with traditional rapid window reduction after packet loss, while still effectively preventing packet loss through early congestion detection and response

Inventive Principle:

Principle #13The other way round (Inversion)

Data Source

PatentUS11438275B2Congestion response

Publication Date: 2022.09.06 BRITISH TELECOM PLC

AI summary

In examples of the present invention, during delivery of content, the round trip times for each delivered data packet are measured and the congestion window used for delivery is adjusted accordingly. The congestion window is set to a relatively high value when the round trip times are relatively low, and set to a relatively low value when the round trip times are relatively high.