Unmanned aerial vehicle task offloading method and device for low-orbit satellite network, electronic device and storage medium
By constructing a joint optimization model and a Lyapunov optimization framework, and combining deep neural networks for online decision-making, the problems of long-term energy consumption and resource cost management in low-Earth orbit satellite networks were solved, and stable and efficient task offloading was achieved.
Patent Information
- Application Number
- CN202610968556.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-07-01
- Publication Date
- 2026-09-15
- Estimated Expiration
- 2046-07-01
AI Technical Summary
Traditional low-Earth orbit satellite network mission offloading methods have failed to effectively manage long-term computing energy consumption and resource costs, resulting in unstable operation of satellite networks over long time scales and exceeding budget for terrestrial network resource usage, triggering service throttling or tariff penalties.
A joint optimization model is constructed with the goal of maximizing the long-term average task unloading volume. By using a virtual computational energy consumption queue and a virtual resource wholesale cost queue, combined with the Lyapunov optimization framework, the long-term constraint is transformed into a single-slot static optimization problem, and a deep neural network is used for online decision optimization.
Without relying on prior information about future missions, it has achieved effective management of high mission offloading volume and long-term energy consumption and cost constraints of satellite networks over long periods of time, ensuring stable system operation and economic sustainability of resources.