SatOps Decision speeds up satellite communication choices by five times
SatOps-Decision: Low-Latency Discriminative Decisions for Onboard Satellite Communication Operations
Machine LearningArtificial IntelligenceNetworking and Internet Architecture
Summary
Satellites need to make fast and accurate decisions to keep their communication systems running smoothly. The authors developed SatOps-Decision, a new method that quickly picks the best operational option for satellites using a special kind of learned model. Their tests show it is more than four times faster and much more accurate than previous methods, helping satellites respond faster with fewer mistakes. This method works by evaluating choices locally on the satellite in just one calculation step.
What this means in practice
- •For satellite operations teams: Provide faster and more accurate onboard operational decisions to improve communication system reliability.
- •For real-time embedded system engineers: Use the low-latency discriminative decision approach to speed up critical decisions in embedded hardware beyond satellites.
Authors
Lifan Mei, Yuxuan Li, Jiaxian Tu, Shenghe Xu
Abstract
We propose SatOps-Decision, a method for low-latency decisions in satellite communication operations. To the best of our knowledge, it is the first application of Jev-style general-purpose discriminative decision models to satellite operations, and the accompanying benchmark is the first dedicated to this approach. The learned scorer, a locally adapted Laya encoder with its native decision head, selects among supplied operational answers in a single forward pass. The benchmark combines authored operational contracts, controlled state changes and independently checked labels in an auditable construction. Evaluation prioritizes complete-request latency and raw decision accuracy; all main accuracy comparisons use the same 1,024 held-out questions, separate from training and development. SatOps-Decision's local scorer has a median latency of 90.3 ms per decision, versus 493.9 ms for Qwen3.5-0.8B generation and 388.4 ms for OneJev1.6-0.8B: $5.47\times$ and $4.30\times$ speedups based on median request times in the measured FP32/MPS implementations. Its mean raw accuracy is 85.3%, versus 42.5% for frozen Laya, 40.7% for Qwen generation and 58.6% for OneJev. As cloud accuracy references, original Jev 1.14/1.13 reach 87.4/81.9%.