SLAFlow: Profile-Guided SLA-Aware Runtime Orchestration for Multi-Stage Edge AI Services
Electronics · 11.11.2026 · 15 (22) · 5233
DOI: 10.3390/electronics15225233 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 11.11.2026. Verfasst von Feng Zhou und 4 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fudan University Postdoctoral Mobile Station, China Electronics Jinxin Digital Technology Group Co., Ltd..
Abstract (Originalsprache)
Multi-stage edge AI services must balance output quality against the latency of retrieval, generation, and refinement. SLAFlow uses profiles measured on the execution platform to jointly select retrieval depth, generation-token budget, and refinement depth under a request’s remaining deadline and revisits the feasibility and benefit of optional refinement during execution. We evaluate an ophthalmic workflow on a CPU-only workstation at a doctor’s desk, combining physical measurements with trace-driven policy simulation. Under nominal arrivals and the tight SLA, SLAFlow achieves a deadline-weighted quality (DWQ) of 0.668 with 2.7% violations, compared with 0.479 and 33.1% for the queue-based heuristic. Across four evaluated conditions, SLAFlow has observed mean DWQ differences of +0.004 to +0.022 relative to Token-Only; under Bursty/Tight, violations increase from 9.0% to 11.4%. Under Bursty/Tight, however, its observed DWQ gain over Static-Small is only 0.003, while violations increase from 1.5% to 11.4%. Independent calibration observes seven prediction exceedances in 180 records and three false-feasible decisions in 160 predicted-feasible cases. Matched queued executions have physical p95 end-to-end latencies 3.2% and 4.4% above simulation.
Förderung
- Fudan University Postdoctoral Mobile Station
- China Electronics Jinxin Digital Technology Group Co., Ltd.
Zitieren
APA
Zhou, F., Hu, S., Du, X., Li, N., & Zhou, T. (2026). SLAFlow: Profile-Guided SLA-Aware Runtime Orchestration for Multi-Stage Edge AI Services. Electronics, 15(22), 5233. https://doi.org/10.3390/electronics15225233
Vancouver
Zhou F, Hu S, Du X, Li N, Zhou T. SLAFlow: Profile-Guided SLA-Aware Runtime Orchestration for Multi-Stage Edge AI Services. Electronics. 2026;15(22):5233. doi:10.3390/electronics15225233
BibTeX
@article{Zhou2026,
author = {Zhou, Feng and Hu, Shijing and Du, Xiaozheng and Li, Nan and Zhou, Tongming},
title = {SLAFlow: Profile-Guided SLA-Aware Runtime Orchestration for Multi-Stage Edge AI Services},
journal = {Electronics},
year = {2026},
volume = {15},
number = {22},
pages = {5233},
doi = {10.3390/electronics15225233}
}
EUVIMED