Energy-Efficient Optimal Mode Selection for Edge AI Inference via Integrated Sensing-Communication-Computation

doi:10.1109/TMC.2024.3440581

	Energy-Efficient Optimal Mode Selection for Edge AI Inference via Integrated Sensing-Communication-Computation
	Liu, Shu1 ; Wen, Dingzhu1 ; Li, Da 2; Chen, Qimei 3; Zhu, Guangxu 4; Shi, Yuanming1
	2024-12-01
发表期刊	IEEE TRANSACTIONS ON MOBILE COMPUTING (IF:7.7[JCR-2023],6.5[5-Year])
ISSN	1536-1233
EISSN	1558-0660
卷号	23 期号:12 页码:1-15
发表状态	已发表
DOI	10.1109/TMC.2024.3440581
摘要	Existing edge inference methods only consider one paradigm, i.e., one of on-device inference, on-server inference, or edge-device cooperative inference. Each paradigm has its pros and cons as well as dominant application scopes. For example, the on-device paradigm is the best choice when the inference task is not computationally intensive, the on-server paradigm is suitable if the communication capacity is strong, and the edge-device cooperative mode should be selected in the scenario of weak on-device communication and computation. However, each paradigm suffers from poor performance if deployed outside of its application scope, thus leading to limited potential and flexibility. This paper proposes an edge AI inference framework, which makes the first attempt to jointly consider the three modes for making full use of their benefits. In addition, sensing for data acquisition is enabled at both the edge server and the device. This can effectively improve the inference accuracy with rich information on the target area from two different views. On the other hand, energy cost minimization turns out to be a key target all over the world and a significant issue in wireless networks. To this end, we target minimizing the system energy cost under a given inference accuracy guarantee and other network resource constraints, by coordinating sensing, communication, and computation in different modes. By optimally solving the optimization problem, an integrated sensing-communication-computation (ISCC) based task-oriented mode selection scheme is proposed. A practical ISCC platform is built and extensive experiments are conducted to verify our theoretical analysis.
关键词	Task analysis Servers Feature extraction Sensors Accuracy Computational modeling Performance evaluation Edge AI inference mode selection integrated sensing-communication-computation task-oriented communications
URL	查看原文
收录类别	SCI ; EI
语种	英语
资助项目	Shanghai Sailing Program[23YF1427400] ; Technology Innovation Special Project of Hubei Province[2023BCB041] ; Wuhan Knowledge Innovation Special Basic Research Project[2022020801010110] ; Research and Application of Low-Carbon Key Technologies for AI-Based Digital Information Infrastructures[2206-420118-89-04-959008] ; National Natural Science Foundation of China[62371313] ; Guangdong Basic and Applied Basic Research Foundation[2022A1515010109] ; Shenzhen-Hong Kong-Macau Technology Research Programme[SGDX20230821091559018] ; Longgang District Special Funds for Science and Technology Innovation[LGKCSDPT2023002] ; National Nature Science Foundation of China[62271318] ; Shanghai Rising-Star Program[22QA1406100]
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Telecommunications
WOS记录号	WOS:001359244600207
出版者	IEEE COMPUTER SOC
来源库	IEEE
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/411252
专题	信息科学与技术学院信息科学与技术学院_PI研究组_石远明组信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_文鼎柱组
通讯作者	Wen, Dingzhu
作者单位	1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China 2.College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China 3.School of Electronic Information, Wuhan University, Wuhan, China 4.Shenzhen Research Institute of Big Data, Shenzhen, China
第一作者单位	信息科学与技术学院
通讯作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Liu, Shu,Wen, Dingzhu,Li, Da,et al. Energy-Efficient Optimal Mode Selection for Edge AI Inference via Integrated Sensing-Communication-Computation[J]. IEEE TRANSACTIONS ON MOBILE COMPUTING,2024,23(12):1-15.
APA	Liu, Shu,Wen, Dingzhu,Li, Da,Chen, Qimei,Zhu, Guangxu,&Shi, Yuanming.(2024).Energy-Efficient Optimal Mode Selection for Edge AI Inference via Integrated Sensing-Communication-Computation.IEEE TRANSACTIONS ON MOBILE COMPUTING,23(12),1-15.
MLA	Liu, Shu,et al."Energy-Efficient Optimal Mode Selection for Edge AI Inference via Integrated Sensing-Communication-Computation".IEEE TRANSACTIONS ON MOBILE COMPUTING 23.12(2024):1-15.