Low Earth orbit satellite switching and recovery method based on generic congestion control algorithm.

Area of Science:

• Satellite Communication Systems
• Network Engineering
• Artificial Intelligence in Telecommunications

Background:

• Rapid advancements in low Earth orbit (LEO) satellite technology are expanding its role in mobile communication and data transmission.
• Challenges remain in optimizing user experience for video services and mitigating network congestion during link switching.

Purpose of the Study:

• To propose an enhanced congestion control algorithm for low Earth orbit (LEO) satellite switching recovery.
• To improve the reliability and efficiency of LEO satellite networks, particularly for video services.

Main Methods:

• Implementation of a neural network-based attitude control strategy.
• Development of a handover detection mechanism considering satellite service time.
• Integration of a rate recovery algorithm combining congestion control with time series prediction.

Main Results:

• Reduced communication interruption rate from 6.48% to 2.13%.
• Increased minimum throughput from 257 kbps to 2017 kbps.
• Decreased average recovery time from 3200 ms to 1800 ms, with a 71.6% reduction in false detection rate and 96.32% detection accuracy.

Conclusions:

• The proposed method effectively enhances switching and recovery performance in LEO satellite networks.
• The study provides crucial theoretical and technical support for stable and efficient satellite system operations.
• The method demonstrates robust real-time performance and significant improvements in key network metrics.