A method and apparatus for computing task offloading
By employing a DAG structure and HEFT algorithm to determine task priorities in an edge computing environment, and combining this with the FD-DDPG model for dynamic scheduling, the problems of task dependency and fault perception are solved. This enables efficient and low-energy offloading of computing tasks in industrial quality inspection, thereby improving the stability and efficiency of the production line.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-02
- Publication Date
- 2026-07-17
AI Technical Summary
Existing industrial quality inspection computational unloading methods do not fully consider task dependence in surface defect detection scenarios, resulting in increased processing delays and energy consumption. Furthermore, they lack fault detection and dynamic rescheduling capabilities, affecting the stability and efficiency of the production line.
Task dependency modeling based on DAG structure and priority determination using HEFT algorithm are adopted. Dynamic task scheduling is performed by combining FD-DDPG decision model. Through time delay and energy consumption weighted optimization, fault detection and dynamic rescheduling are realized, and the offloading of computing tasks is optimized.
While ensuring real-time performance and reliability, it significantly reduces system energy consumption, improves the efficiency of unloading computing tasks, and enhances the stability and efficiency of the production line.
Smart Images
Figure CN122412082A_ABST