Advancements in Accelerating Deep Neural Network Inference on AIoT Devices: A Survey

doi:10.1109/TSUSC.2024.3353176

	Advancements in Accelerating Deep Neural Network Inference on AIoT Devices: A Survey
	Cheng, Long 1; Gu, Yan 1; Liu, Qingzhi 2; Yang, Lei 3; Liu, Cheng 4; Wang, Ying 4
	2024-11-01
发表期刊	IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING
ISSN	2377-3782
卷号	9 期号:6 页码:830-847
摘要	The amalgamation of artificial intelligence with Internet of Things (AIoT) devices have seen a rapid surge in growth, largely due to the effective implementation of deep neural network (DNN) models across various domains. However, the deployment of DNNs on such devices comes with its own set of challenges, primarily related to computational capacity, storage, and energy efficiency. This survey offers an exhaustive review of techniques designed to accelerate DNN inference on AIoT devices, addressing these challenges head-on. We delve into critical model compression techniques designed to adapt to the limitations of devices and hardware optimization strategies that aim to boost efficiency. Furthermore, we examine parallelization methods that leverage parallel computing for swift inference, as well as novel optimization strategies that fine-tune the execution process. This survey also casts a future-forward glance at emerging trends, including advancements in mobile hardware, the co-design of software and hardware, privacy and security considerations, and DNN inference on AIoT devices with constrained resources. All in all, this survey aspires to serve as a holistic guide to advancements in the acceleration of DNN inference on AIoT devices, aiming to provide sustainable computing for upcoming IoT applications driven by artificial intelligence.
关键词	Computational modeling Hardware Artificial neural networks Optimization Internet of Things Adaptation models Data models AIoT devices DNN inference model compression parallel computing performance optimization survey
DOI	10.1109/TSUSC.2024.3353176
收录类别	SCI
语种	英语
资助项目	Zhejiang Lab[2021PC0AC01] ; Fundamental Research Funds for the Central Universities[2023YQ002]
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Information Systems ; Telecommunications
WOS记录号	WOS:001375683800012
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41135
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Ying
作者单位	1.North China Elect Power Univ, Sch Control & Comp Engn, Beijing 102206, Peoples R China 2.Wageningen Univ & Res, Informat Technol Grp, NL-6708 Wageningen, Netherlands 3.George Mason Univ, Dept Informat Sci & Technol, Fairfax, VA 22030 USA 4.Chinese Acad Sci, State Key Lab Comp Architecture, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Cheng, Long,Gu, Yan,Liu, Qingzhi,et al. Advancements in Accelerating Deep Neural Network Inference on AIoT Devices: A Survey[J]. IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING,2024,9(6):830-847.
APA	Cheng, Long,Gu, Yan,Liu, Qingzhi,Yang, Lei,Liu, Cheng,&Wang, Ying.(2024).Advancements in Accelerating Deep Neural Network Inference on AIoT Devices: A Survey.IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING,9(6),830-847.
MLA	Cheng, Long,et al."Advancements in Accelerating Deep Neural Network Inference on AIoT Devices: A Survey".IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING 9.6(2024):830-847.