Machine Learning for Noise Sensor Placement and Full-Chip Voltage Emergency Detection

doi:10.1109/TCAD.2016.2611502

	Machine Learning for Noise Sensor Placement and Full-Chip Voltage Emergency Detection
	Xiaochen Liu1 ; Shupeng Sun 2; Xin Li 2; Haifeng Qian 3; Pingqiang Zhou1
	2017-03
发表期刊	IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS (IF:2.7[JCR-2023],2.9[5-Year])
ISSN	0278-0070
卷号	36 期号:3 页码:421-434
发表状态	已发表
DOI	10.1109/TCAD.2016.2611502
摘要	Power supply fluctuation can be potential threat to the correct operations of processors, in the form of voltage emer-gency that happens when supply voltage drops below a certain threshold. Noise sensors (with either analog or digital outputs) can be placed in the nonfunction area of processors to detect voltage emergencies by monitoring the runtime voltage fluc-tuations. Our work addresses two important problems related to building a sensor-based voltage emergency detection system: 1) offline sensor placement, i. e., where to place the noise sen-sors so that the number and locations of sensors are optimized in order to strike a balance between design cost and chip reli-ability and 2) online voltage emergency detection, i. e., how to use these placed sensors to detect voltage emergencies in the hotspot locations. In this paper, we propose integrated solutions to these two problems, respectively, for analog and digital (more specifically, binary) sensor outputs, by exploiting the voltage cor-relation between the sensor candidate locations and the hotspot locations. For the analog case, we use the Group Lasso and an ordinary least squares approach; for the binary case, we integrate the Group Lasso and the SVM approach. Experimental results show that, our approach can achieve 2.3X-2.7X better voltage emergency detection results on average for analog out-puts when compared to the state-of-the-art work; and for the binary case, on average our methodology can achieve up to 21% improvement in prediction accuracy compared to an approach called max-probability-no-prediction.
关键词	Group Lasso linear support vector machine (LSVM) machine learning noise sensor sensor placement voltage emergency
URL	查看原文
收录类别	SCI ; EI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Interdisciplinary Applications ; Engineering, Electrical & Electronic
WOS记录号	WOS:000395876400006
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI入藏号	20173404055657
EI主题词	Artificial intelligence ; Bins ; Location ; Support vector machines ; Voltage control
EI分类号	Storage:694.4 ; Computer Software, Data Handling and Applications:723 ; Artificial Intelligence:723.4 ; Specific Variables Control:731.3
WOS关键词	REGRESSION ; MODEL ; MANAGEMENT ; FRAMEWORK ; SELECTION
原始文献类型	Article
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/1489
专题	信息科学与技术学院信息科学与技术学院_PI研究组_周平强组信息科学与技术学院_硕士生
作者单位	1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China 2.ECE Department, Carnegie Mellon University, Pittsburgh, PA, USA 3.IBM T. J. Watson Research Center, Yorktown Heights, NY, USA
第一作者单位	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	Xiaochen Liu,Shupeng Sun,Xin Li,et al. Machine Learning for Noise Sensor Placement and Full-Chip Voltage Emergency Detection[J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,2017,36(3):421-434.
APA	Xiaochen Liu,Shupeng Sun,Xin Li,Haifeng Qian,&Pingqiang Zhou.(2017).Machine Learning for Noise Sensor Placement and Full-Chip Voltage Emergency Detection.IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,36(3),421-434.
MLA	Xiaochen Liu,et al."Machine Learning for Noise Sensor Placement and Full-Chip Voltage Emergency Detection".IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 36.3(2017):421-434.