CoEdge: Cooperative DNN Inference With Adaptive Workload Partitioning Over Heterogeneous Edge Devices

Recent advances in artificial intelligence have driven increasing intelligent applications at the network edge, such as smart home, smart factory, and smart city. To deploy computationally intensive Deep Neural Networks (DNNs) on resource-constrained edge devices, traditional approaches have relied...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE/ACM transactions on networking Ročník 29; číslo 2; s. 595 - 608
Hlavní autori: Zeng, Liekang, Chen, Xu, Zhou, Zhi, Yang, Lei, Zhang, Junshan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.04.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Adaptive control
Artificial intelligence
Artificial neural networks
Cloud computing
Computational modeling
cooperative DNN inference
distributed computing
Edge intelligence
Electronic devices
energy efficiency
Feature extraction
Image edge detection
Inference
Network latency
Performance evaluation
Runtime
Smart buildings
Smart homes
Task analysis
Wide area networks
Workload
Workloads
ISSN:1063-6692, 1558-2566
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Recent advances in artificial intelligence have driven increasing intelligent applications at the network edge, such as smart home, smart factory, and smart city. To deploy computationally intensive Deep Neural Networks (DNNs) on resource-constrained edge devices, traditional approaches have relied on either offloading workload to the remote cloud or optimizing computation at the end device locally. However, the cloud-assisted approaches suffer from the unreliable and delay-significant wide-area network, and the local computing approaches are limited by the constrained computing capability. Towards high-performance edge intelligence, the cooperative execution mechanism offers a new paradigm, which has attracted growing research interest recently. In this paper, we propose CoEdge, a distributed DNN computing system that orchestrates cooperative DNN inference over heterogeneous edge devices. CoEdge utilizes available computation and communication resources at the edge and dynamically partitions the DNN inference workload adaptive to devices' computing capabilities and network conditions. Experimental evaluations based on a realistic prototype show that CoEdge outperforms status-quo approaches in saving energy with close inference latency, achieving up to 25.5% ~ 66.9% energy reduction for four widely-adopted CNN models.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1063-6692
1558-2566
DOI:10.1109/TNET.2020.3042320