As a driving force in the advancement of intelligent in-orbit applications, DNN models have been gradually integrated into satellites, producing daily latency-constraint and computation-intensive tasks. However, the substantial computation capability of DNN models, coupled with the instability of the satellite-ground link, pose significant challenges, hindering timely completion of tasks. It becomes necessary to adapt to task stream changes when dealing with tasks requiring latency guarantees, such as dynamic observation tasks on the satellites. To this end, we consider a system model for a collaborative inference system with latency constraints, leveraging the multi-exit and model partition technology. To address this, we propose an algorithm, which is tailored to effectively address the trade-off between task completion and maintaining satisfactory task accuracy by dynamically choosing early-exit and partition points. Simulation evaluations show that our proposed algorithm significantly outperforms baseline algorithms across the task stream with strict latency constraints.

翻译：作为智能在轨应用发展的驱动力，DNN模型已逐步集成到卫星中，产生大量时延受限且计算密集型的任务。然而，DNN模型强大的计算能力，加之星地链路的不稳定性，给任务的及时完成带来了重大挑战。在处理需要时延保障的任务（如卫星上的动态观测任务）时，需适应任务流的变化。为此，我们考虑一个利用多出口和模型分区技术的时延约束协同推理系统模型。针对这一问题，我们提出了一种算法，该算法通过动态选择提前出口和分区点，有效权衡任务完成率与任务精度的保持。仿真评估表明，在严格时延约束的任务流中，我们提出的算法显著优于基线算法。