Scheduling Training-Inference Co-Location in Demand Response for Sustainable Edge AI
IEEE Transactions on Services Computing · 2026-05 · 19 (3) · 2438-2451
DOI: 10.1109/tsc.2026.3686889 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2026-05. Verfasst von Konglin Zhu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: China Association for Campus Management, National Key Research and Development Program of China, Beijing Natural Science Foundation.
Abstract (Originalsprache)
In the pursuit of data privacy and reduced latency, the adoption of edge intelligence has surged. Meanwhile, the enormous increase in AI has resulted in significant energy consumption. Edge intelligence plays a crucial role in Energy Demand Response (EDR). However, existing edge intelligence falls short of meeting the demands of co-locating training and inference tasks while satisfying EDR. Specifically, the intertwinement between balancing energy consumption, system delay and model accuracy, and uncertain future inputs adds to the challenge of designing an online sustainable system for co-located training and inference tasks. To address these challenges, we propose a novel two-timescale system for co-locating training and inference EDR. Our approach satisfies EDR by strategically planning training schedules on macro-timescales and migrating inference requests between heterogeneous edges on micro-timescales while minimizing long-term cost. We introduce a novel online polynomial time algorithm that first breaks down the problem into two subproblems, which are subsequently solved using an online-learning-based fractional algorithm and a randomized roun ding algorithm, respectively. Rigorous analysis demonstrates that our approach achieves both sublinear dynamic regret and sublinear dynamic fit. Extensive trace-driven evaluations validate the practical superiority of our approach over multiple existing methods, highlighting its effectiveness in real-world scenarios.
Förderung
- China Association for Campus Management
- National Key Research and Development Program of China
- Beijing Natural Science Foundation
- Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing
- National Science Foundation
Zitieren
APA
Zhu, K., Wei, S., Wu, X., Jiao, L., Dong, J., & Zhang, L. (2026). Scheduling Training-Inference Co-Location in Demand Response for Sustainable Edge AI. IEEE Transactions on Services Computing, 19(3), 2438-2451. https://doi.org/10.1109/tsc.2026.3686889
Vancouver
Zhu K, Wei S, Wu X, Jiao L, Dong J, Zhang L. Scheduling Training-Inference Co-Location in Demand Response for Sustainable Edge AI. IEEE Transactions on Services Computing. 2026;19(3):2438-2451. doi:10.1109/tsc.2026.3686889
BibTeX
@article{Zhu2026,
author = {Zhu, Konglin and Wei, Siyuan and Wu, Xuan'er and Jiao, Lei and Dong, Jin and Zhang, Lin},
title = {Scheduling Training-Inference Co-Location in Demand Response for Sustainable Edge AI},
journal = {IEEE Transactions on Services Computing},
year = {2026},
volume = {19},
number = {3},
pages = {2438--2451},
doi = {10.1109/tsc.2026.3686889}
}
EUVIMED