Energy-Aware Inference Offloading for DNN-Driven Applications in Mobile Edge Clouds

With increasing focus on Artificial Intelligence (AI) applications, Deep Neural Networks (DNNs) have been successfully used in a number of application areas. As the number of layers and neurons in DNNs increases rapidly, significant computational resources are needed to execute a learned DNN model....

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on parallel and distributed systems 2021-04, Vol.32 (4), p.799-814
Main Authors: Xu, Zichuan, Zhao, Liqian, Liang, Weifa, Rana, Omer F., Zhou, Pan, Xia, Qiufen, Xu, Wenzheng, Wu, Guowei
Format: Article
Language:English
Subjects:
5G mobile communication
Algorithms
approximation and online algorithms
Artificial intelligence
Artificial neural networks
Base stations
Cloud computing
Computation offloading
Data centers
Edge computing
Electronic devices
Heuristic algorithms
Inference
Inference offloading
Mobile computing
mobile edge clouds
Mobile handsets
Task analysis
Video data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With increasing focus on Artificial Intelligence (AI) applications, Deep Neural Networks (DNNs) have been successfully used in a number of application areas. As the number of layers and neurons in DNNs increases rapidly, significant computational resources are needed to execute a learned DNN model. This ever-increasing resource demand of DNNs is currently met by large-scale data centers with state-of-the-art GPUs. However, increasing availability of mobile edge computing and 5G technologies provide new possibilities for DNN-driven AI applications, especially where these application make use of data sets that are distributed in different locations. One fundamental process of a DNN-driven application in mobile edge clouds is the adoption of "inferencing" - the process of executing a pre-trained DNN based on newly generated image and video data from mobile devices. We investigate offloading DNN inference requests in a 5G-enabled mobile edge cloud (MEC), with the aim to admit as many inference requests as possible. We propose exact and approximate solutions to the problem of inference offloading in MECs. We also consider dynamic task offloading for inference requests, and devise an online algorithm that can be adapted in real time. The proposed algorithms are evaluated through large-scale simulations and using a real world test-bed implementation. The experimental results demonstrate that the empirical performance of the proposed algorithms outperform their theoretical counterparts and other similar heuristics reported in literature.
ISSN:1045-9219
1558-2183
DOI:10.1109/TPDS.2020.3032443