Adaptive Early Exit of Computation for Energy-Efficient and Low-Latency Machine Learning over IoT Networks
Authors:
- 8 January 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 200-206
Abstract
Large Machine Learning (ML) models require considerable computing resources and raise challenges for integrating them with the decentralized operation of heterogeneous and resource-constrained Internet of Things (IoT) devices. Running ML tasks on the cloud can introduce network delay, throughput, and privacy concerns, whereas running ML tasks on IoT devices is penalized by their constrained resources. For this reason, recent research proposed cooperative execution of ML tasks over IoT networks but disregarded resource variability and the IoT devices’ energy constraints simultaneously. In this paper, we propose Early Exit of Computation (EEoC), an adaptive, energy-efficient, low-latency inference scheme over IoT networks. EEoC adaptively distributes the inference computation load between the IoT device and the edge server, based on estimated communication and computation resources, to jointly minimize prediction latency and energy consumption. We evaluate our solution’s latency and energy profile on a real testbed running two widely used neural networks. Results show that EEoC can reduce latency and energy consumption up to 24.6% and 46.5%, respectively, compared to other state-of-the-art solutions without sacrificing accuracy.Keywords
This publication has 14 references indexed in Scilit:
- Convergence of Edge Computing and Deep Learning: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2020
- Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge ComputingIEEE Transactions on Wireless Communications, 2020
- Boomerang: On-Demand Cooperative Deep Neural Network Inference for Edge Intelligence on the Industrial Internet of ThingsIEEE Network, 2019
- Deep Learning With Edge Computing: A ReviewProceedings of the IEEE, 2019
- DeepWear: Adaptive Local Offloading for On-Wearable Deep LearningIEEE Transactions on Mobile Computing, 2019
- Energy and Policy Considerations for Deep Learning in NLP2019
- DeepThings: Distributed Adaptive Deep Learning Inference on Resource-Constrained IoT Edge ClustersIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018
- NeurosurgeonACM SIGARCH Computer Architecture News, 2017
- Ultra-low power and dependability for IoT devices (Invited paper for IoT technologies)2017
- BranchyNet: Fast inference via early exiting from deep neural networks2016