Congestion Window Adjustment for Timely Media Delivery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Adaptive bitrate media delivery over networks faces unpredictable and variable delivery times due to TCP congestion response mechanisms, leading to buffering delays and playout stalling, which are mitigated by increasing latency through large buffering.
Innovation Solution
A method and apparatus that dynamically adjust the congestion window based on the initial and updated delivery rates, time remaining for segment delivery, and remaining data, ensuring timely delivery of media content segments by calculating an updated congestion window size using the formula CWND_target = CWND_initial * R_measured * D_remaining / ΔT_remaining, where CWND is the initial congestion window, R_measured is the actual delivery rate, D_remaining is the remaining data, and ΔT_remaining is the time left for delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If TCP congestion response mechanism is used to reduce transmission rate following packet loss, then network throughput of competing TCP traffic flows is protected, but delivery time of media content segments becomes variable and unpredictable
Solution Approach 1:
The patent implements dynamic adjustment of the congestion window size during segment delivery. Instead of using a fixed congestion response, the system continuously monitors delivery rate and packet loss, then adaptively modifies the congestion window to maintain predictable delivery times while still protecting network throughput through controlled rate adjustment
Solution Approach 2:
The system employs feedback mechanisms by measuring the actual delivery rate of media segments and using this information to adjust the congestion window size. This closed-loop control allows the system to respond to network conditions while maintaining predictable delivery times, resolving the contradiction between throughput protection and delivery time variability
2Reliability
If large buffering is used to minimize buffering delays and playout stalling, then media playout performance is improved, but end-to-end latency increases
Solution Approach 1:
The patent calculates and sets an initial congestion window size before segment delivery begins, based on expected network conditions and segment characteristics. This preliminary configuration allows the system to achieve predictable delivery times without requiring large buffers, thus maintaining low latency while ensuring reliable playout
Solution Approach 2:
The system dynamically changes the congestion window parameter during delivery based on measured delivery rates and packet loss conditions. This parameter adjustment allows the system to adapt to actual network conditions, achieving reliable media playout with minimal buffering and consequently low end-to-end latency
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In examples of the present invention, delivery of a segment of content is done using an initial congestion window, preferably chosen to give a delivery rate that ensures timely delivery of that segment. However, under high levels of packet loss, the delivery rate may not be sufficient. Hence, at any stage during delivery of a segment, the actual delivery rate is measured, and used, together with the previous congestion window size, the amount of content segment data still to be delivered, and the time left for delivery, to calculate an updated congestion window. The remainder of the segment is then delivered using this revised congestion window.