Buffered Video Streaming With AI Bandwidth Timing Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video transmission systems face network congestion issues due to large video data volumes, which can affect other users' communications, especially in mobile communication networks.
Innovation Solution
A video transmission apparatus that temporarily stores video data and adjusts transmission timing based on network bandwidth availability, using artificial intelligence and machine learning to predict free bandwidth, and performs image processing to reduce data volume.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If video data is transmitted continuously without delay, then real-time display quality is maintained, but network congestion occurs and other users' communications are affected
Solution Approach 1:
The system performs preliminary actions by temporarily storing video data in a buffer before transmission, and uses machine learning to predict optimal transmission timing in advance. This allows the system to prepare transmission schedules proactively rather than reactively, balancing real-time requirements with network conditions.
Solution Approach 2:
The system implements periodic transmission by dividing video data into segments and transmitting them at scheduled intervals based on predicted network bandwidth availability. Instead of continuous transmission, video data is transmitted in periodic batches when network conditions are favorable, reducing congestion while maintaining acceptable display quality.
2Object-affected harmful factors
If video data transmission bandwidth is reduced to avoid congestion, then network load decreases, but original content quality deteriorates
Solution Approach 1:
The system performs preliminary actions by temporarily storing video data in a buffer before transmission, and uses machine learning to predict optimal transmission timing in advance. This allows the system to prepare transmission schedules proactively rather than reactively, balancing real-time requirements with network conditions.
Solution Approach 2:
The system dynamically changes transmission parameters including bandwidth allocation, resolution, and frame rate based on predicted network conditions. When network bandwidth is limited, the system adjusts these parameters to maintain acceptable quality while adapting to available capacity, and uses temporal buffering to smooth out quality variations.
3Object-affected harmful factors
If video data is buffered and transmission timing is adjusted, then network congestion is reduced, but transmission delay increases
Solution Approach 1:
The system performs preliminary actions by temporarily storing video data in a buffer before transmission, and uses machine learning to predict optimal transmission timing in advance. This allows the system to prepare transmission schedules proactively rather than reactively, balancing real-time requirements with network conditions.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring actual network performance and comparing it with predicted values. The machine learning model is updated with actual transmission results and network conditions, allowing the system to learn from past performance and improve future transmission timing predictions, thereby reducing unnecessary delays.
4Measurement precision
If machine learning models are trained with historical network data, then transmission timing prediction accuracy improves, but system complexity increases
Solution Approach 1:
The system implements self-service by automatically collecting historical network data, training machine learning models, and updating prediction algorithms without requiring manual intervention. The system autonomously manages the complexity of model training and optimization, reducing the burden on operators while maintaining high prediction accuracy through continuous learning.
Data Source
AI summary
A video transmission apparatus, including: a video data obtaining unit which obtains video data; a video data storing unit which stores the video data obtained by the video data obtaining unit; a reduced video generating unit which generates reduced video of which a data volume is reduced by performing image processing on the video data obtained by the video data obtaining unit; a streaming transmitting unit which transmits the reduced video to a transmission destination by streaming; and a video data transmitting unit which transmits the video data stored in the video data storing unit to a preservation destination of the video data in response to a predetermined condition being satisfied, is provided.