Intelligent unloading algorithm and system for video monitoring cloud edge collaboration
The invention discloses an intelligent unloading algorithm and system for video monitoring cloud edge collaboration, and the algorithm comprises the steps: classifying different types of video monitoring tasks according to the levels of time delay requirements, and considering the current CPU, GPU,...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
21.01.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses an intelligent unloading algorithm and system for video monitoring cloud edge collaboration, and the algorithm comprises the steps: classifying different types of video monitoring tasks according to the levels of time delay requirements, and considering the current CPU, GPU, memory, bandwidth and other state information of an edge server; comprehensively determining a video monitoring task unloading strategy according to the processing time of the video monitoring task at different server sides. According to the method, the video monitoring task can be intelligently unloaded to the edge server or the cloud server, the operation time of the video monitoring task is optimized, and normal operation of the edge server is ensured.
本发明公开了一种面向视频监控云边协同的智能卸载算法与系统,对不同类型的视频监控任务类型根据时延要求等级进行分类,考虑边缘服务器当前的CPU、GPU、内存、带宽等状态信息,以及视频监控任务在不同服务器端的处理时间综合决定视频监控任务卸载策略;本发明能智能把视频监控任务卸载到边缘服务器或云服务器,优化视频监控任务运行时间,保证边缘服务器正常运行。 |
---|---|
Bibliography: | Application Number: CN202111159596 |