CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices

Liekang Zeng, Xu Chen, Zhi Zhou, Lei Yang, Junshan Zhang

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish (US)
Article number9296560
Pages (from-to)595-608
Number of pages14
JournalIEEE/ACM Transactions on Networking
Volume29
Issue number2
DOIs
StatePublished - Apr 2021

Keywords

  • Edge intelligence
  • cooperative DNN inference
  • distributed computing
  • energy efficiency

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices'. Together they form a unique fingerprint.

Cite this