Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.27021 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910260682293248 |
|---|---|
| author | Pehlivanoglu, Ayse Nur Li, Aimin Uysal, Elif |
| author_facet | Pehlivanoglu, Ayse Nur Li, Aimin Uysal, Elif |
| contents | This paper studies how to balance onboard and ground computation under intermittent LEO connectivity for optimized inference freshness. As connectivity varies in time, the system switches among the actions of onboard computation, cached semantic transmission, raw-data offloading, and waiting. We define Age of Inference (AoInf) as the performance metric, where the age resets only upon successful task-valid updates. We formulate long-run average AoInf minimization as a finite-state average-cost semi-Markov decision process whose state captures the ground AoInf, orbital contact phase, cache occupancy, and cache age. We then transform the SMDP into an equivalent average-cost MDP and compute the solution via normalized relative value iteration (RVI). Numerical results indicate that the resulting hybrid policy reduces average AoInf relative to onboard-only and offload-only baselines, while requiring less computational resources on the satellite than the former, and fewer communication resources than the latter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27021 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | In-Orbit Intelligence or Ground Offloading? Inference Freshness under Intermittent Satellite Connectivity Pehlivanoglu, Ayse Nur Li, Aimin Uysal, Elif Systems and Control This paper studies how to balance onboard and ground computation under intermittent LEO connectivity for optimized inference freshness. As connectivity varies in time, the system switches among the actions of onboard computation, cached semantic transmission, raw-data offloading, and waiting. We define Age of Inference (AoInf) as the performance metric, where the age resets only upon successful task-valid updates. We formulate long-run average AoInf minimization as a finite-state average-cost semi-Markov decision process whose state captures the ground AoInf, orbital contact phase, cache occupancy, and cache age. We then transform the SMDP into an equivalent average-cost MDP and compute the solution via normalized relative value iteration (RVI). Numerical results indicate that the resulting hybrid policy reduces average AoInf relative to onboard-only and offload-only baselines, while requiring less computational resources on the satellite than the former, and fewer communication resources than the latter. |
| title | In-Orbit Intelligence or Ground Offloading? Inference Freshness under Intermittent Satellite Connectivity |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2605.27021 |