DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference
IEEE Transactions on Mobile Computing · 2024-10 · 23 (10) · 9042-9059
DOI: 10.1109/tmc.2024.3357218 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2024-10. Verfasst von Ziyang Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 69-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: National Key R&D Program of China, An Open Competition Project of Heilongjiang Province, China.
Abstract (Originalsprache)
Due to limited resources on edge and different characteristics of deep neural network (DNN) models, it is a big challenge to optimize DNN inference performance in terms of energy consumption and end-to-end latency. In addition to dynamic voltage frequency scaling (DVFS) technique, edge-cloud architecture provides a collaborative approach for efficient DNN inference. However, current edge-cloud collaborative inference methods have not optimized various compute resources on edge devices. Thus, we propose DVFO, a novel DVFS-enabled edge-cloud collaborative inference framework, which co-optimizes DVFS and offloading parameters via deep reinforcement learning (DRL). Specifically, DVFO automatically co-optimizes 1) the CPU, GPU and memory frequencies of edge devices, and 2) the offloaded feature map. In addition, it leverages a thinking-while-moving concurrent mechanism to accelerate the DRL learning process, and a spatial-channel attention mechanism to identify the less important DNN feature map for efficient offloading. This approach improves inference performance for different DNN models under various edge-cloud network conditions. Extensive evaluations using two datasets and six widely-deployed DNN models on five heterogeneous edge devices show that DVFO significantly reduces the energy consumption by 33% on average, compared to state-of-the-art schemes. Moreover, DVFO achieves up to 28.6% $\sim$ ∼ 59.1% end-to-end latency reduction, while maintaining accuracy within 1% loss on average.
Förderung
- National Key R&D Program of China
- An Open Competition Project of Heilongjiang Province, China
Zitieren
APA
Zhang, Z., Zhao, Y., Li, H., Lin, C., & Liu, J. (2024). DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference. IEEE Transactions on Mobile Computing, 23(10), 9042-9059. https://doi.org/10.1109/tmc.2024.3357218
Vancouver
Zhang Z, Zhao Y, Li H, Lin C, Liu J. DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference. IEEE Transactions on Mobile Computing. 2024;23(10):9042-9059. doi:10.1109/tmc.2024.3357218
BibTeX
@article{Zhang2024,
author = {Zhang, Ziyang and Zhao, Yang and Li, Huan and Lin, Changyao and Liu, Jie},
title = {DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference},
journal = {IEEE Transactions on Mobile Computing},
year = {2024},
volume = {23},
number = {10},
pages = {9042--9059},
doi = {10.1109/tmc.2024.3357218}
}
EUVIMED