CoEdge: Cooperative DNN Inference With Adaptive Workload Partitioning Over Heterogeneous Edge Devices
Top Cited Papers
- 16 December 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 29 (2) , 595-608
Abstract
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.Keywords
All Related Versions
Funding Information
- National Science Foundation of China (U20A20159, U1711265, 61972432)
- Program for Guangdong Introducing Innovative and Entrepreneurial Teams (2017ZT07X355)
- Guangdong Provincial Pearl River Talents Program (2017GC010465)
- U.S. National Science Foundation (IIS-1838024, EEC-1801727, CNS-1950485)
This publication has 41 references indexed in Scilit:
- Software Defined Cooperative Offloading for Mobile CloudletsIEEE/ACM Transactions on Networking, 2017
- A review of Internet of Things for smart home: Challenges and solutionsJournal of Cleaner Production, 2017
- MCDNN2016
- Deep Residual Learning for Image Recognition2016
- Going deeper with convolutions2015
- Smart e-Health Gateway: Bringing intelligence to Internet-of-Things based ubiquitous healthcare systems2015
- Smart factories in Industry 4.0: A review of the concept and of energy management approached in production based on the Internet of Things paradigm2014
- New types of deep neural network learning for speech recognition and related applications: an overview2013
- Towards energy-proportional datacenter memory with mobile DRAM2012
- A bridging model for parallel computationCommunications of the ACM, 1990