一种天基计算任务星间自主迁移调度方法及装置
By training a scheduling action network at ground control stations, satellite nodes autonomously generate scheduling decisions, solving the problem of low mission execution efficiency in large-scale constellations, achieving efficient resource utilization and real-time scheduling, and adapting to the dynamic needs of low-Earth orbit constellations.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIAN INSTITUE OF SPACE RADIO TECH
- Filing Date
- 2023-10-25
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies cannot effectively address the dynamic deployment service needs of large-scale constellations, suffer from poor real-time performance, and struggle to achieve efficient utilization of distributed resources and task execution.
An inter-satellite autonomous migration scheduling method for space-based computing tasks is adopted. By training the scheduling action network at the ground control station, satellite nodes autonomously generate scheduling decisions. The scheduling action network is constructed using reinforcement learning algorithms, taking into account both computing and communication resources, and scheduling task execution in real time.
It improves mission execution efficiency, adapts to the high dynamism of large-scale low-Earth orbit constellations, avoids difficulties in global information collection, and enhances the real-time nature of decision-making and resource utilization.
Smart Images
Figure CN117544218B_ABST