Application of active queue management for real-time adaptive video streaming.

Area of Science:

• Computer Science
• Network Engineering
• Multimedia Systems

Background:

• Live video streaming, crucial for global internet traffic, is highly sensitive to network impairments like delay, jitter, and packet loss.
• Dynamic Adaptive Streaming over HTTP (DASH) is the dominant technology for adapting video quality to network conditions, but live streaming's low-latency requirements preclude large buffers.
• Active Queue Management (AQM) offers a solution for router congestion control, prompting traffic sources to adjust transmission rates.

Purpose of the Study:

• To evaluate the performance of contemporary AQM strategies in the context of real-time adaptive video streaming.
• To introduce and validate a novel AQM algorithm designed to enhance the user-perceived video quality in live streaming scenarios.

Main Methods:

• Performance evaluation of existing AQM algorithms for live adaptive video streaming.
• Development and implementation of a new AQM algorithm.
• Comparative analysis of the proposed AQM algorithm against established methods using key performance metrics.

Main Results:

• The proposed AQM algorithm demonstrates superior performance compared to existing AQM strategies.
• Significant improvements in video quality, measured by average peak signal-to-noise ratio, were observed with the new algorithm.
• The algorithm maintained fairness among concurrent network flows while enhancing video quality.

Conclusions:

• The developed AQM algorithm effectively addresses congestion in live streaming networks.
• This approach enhances the quality of experience for users by improving video quality without compromising network fairness.