Multi-agent-based time-sensitive task scheduling optimization strategy in satellite-terrestrial collaboration
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
With the deep integration of intelligent Internet of things technology and 5G/6G communication technology, satellite edge computing (SatEC) offers new computational services to areas with weak terrestrial network coverage through its aerospace collaborative computing network. However, the SatEC system faces dual challenges of unbalanced dynamic resource allocation between satellite and ground and insufficient task priority control under multi-dimensional spatiotemporal constraints. Existing methods have defects in hierarchical decision-making, spatiotemporal feature extraction, and task urgency quantification mapping, which limit the efficiency of time-sensitive task processing. To address this problem, a multi-agent deep reinforcement learning algorithm based on self-attention temporal convolutional networks was proposed in this paper. The algorithm achieved joint optimization of task prioritization and resource allocation by constructing a multi-agent architecture, employed a hybrid neural network integrating spatiotemporal features to accurately extract dynamic correlation characteristics of satellite-ground collaboration scenarios, and established a dynamic scheduling mechanism based on a probabilistic model to synergistically optimize latency constraints and task completion rates. Simulation results show that, compared with the baseline algorithm, the proposed algorithm achieves significant improvements in both task completion rate and delay control, demonstrating its effectiveness and superiority in complex satellite edge computing scenarios.
Fields of Study & Subjects
Satellite Communication Systems
IoT and Edge/Fog Computing
Advanced Wireless Network Optimization
Publication details
- Journal / source
- DOAJ (DOAJ: Directory of Open Access Journals)
- Publication date
- 1 March 2026
- Language
- ZH