.png){kind=icon}
.png){kind=icon}
Return
Autonomous scheduling method for multi-satellite collaboration with multi-dimensional optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.swevo.2025.102255.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Satellite network systems play an important role in the fields of communication, navigation and remote sensing. Aiming at the complex constraints and dynamic dependencies in multi-satellite collaborative mission scheduling, this paper designs a multi-satellite collaborative multi-dimensional optimization mission autonomous scheduling method. Based on the dynamic weighted graph, the weights of nodes and edges are used to reflect the constraints and dependencies between missions and resources, and between missions in the spatiotemporal dimension. The graph neural network and multi-layer attention mechanism are combined to capture the interaction characteristics and to express the complex associations in a refined manner. On this basis, through the real-time update mechanism of the weighted graph and the hierarchical strategy network, the algorithm can dynamically respond to environmental changes at each decision time step, thereby improving the adaptability to dynamic changes and the solution efficiency. Finally, a large number of simulation experiments are conducted to verify the flexibility and scalability of the algorithm in multi-satellite collaborative mission scheduling. The results show that the algorithm designed in this paper can adaptively schedule missions in complex and changing environments. In terms of four key indicators, the total benefit of mission scheduling is increased by an average of 19.2%, the number of successfully scheduled missions is increased by 13.8%, and the smooth control of running time and load balancing of resource utilization are effectively achieved.
Keywords:
Earth observing satellites
Scheduling
Deep reinforcement learning
Neural network
Rule-based heuristics
Journal
IF:
8.5
Papers:
2.1K
Citations:
1.0W