SOC dynamic power management using artificial neural network


Autoria(s): Lu, HX (Lu, Huaxiang); Lu, Y (Lu, Yan); Tang, ZF (Tang, Zhifang); Wang, SJ (Wang, Shoujue)
Data(s)

2006

Resumo

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques-BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79 . 1.45 . 1.18-competitive separately for traditional timeout PM . adaptive predictive PM and stochastic PM.

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques-BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79 . 1.45 . 1.18-competitive separately for traditional timeout PM . adaptive predictive PM and stochastic PM.

zhangdi于2010-03-29批量导入

Made available in DSpace on 2010-03-29T06:06:05Z (GMT). No. of bitstreams: 1 2235.pdf: 365887 bytes, checksum: 2aa32fc72f0224057ab6c9043c1ef50d (MD5) Previous issue date: 2006

IEEE Syst Man & Cybernet Soc. Jinan Univ

Chinese Acad Sci, Inst Semicond, Neural Network Lab, Beijing 100083, Peoples R China

IEEE Syst Man & Cybernet Soc. Jinan Univ

Identificador

http://ir.semi.ac.cn/handle/172111/9768

http://www.irgrid.ac.cn/handle/1471x/65885

Idioma(s)

英语

Publicador

IEEE COMPUTER SOC

10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA

Fonte

Lu, HX (Lu, Huaxiang); Lu, Y (Lu, Yan); Tang, ZF (Tang, Zhifang); Wang, SJ (Wang, Shoujue) .SOC dynamic power management using artificial neural network .见:IEEE COMPUTER SOC .ISDA 2006 Sixth International Conference on Intelligent Systems Design and Applications,10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA ,2006,Vol 1: 133-137

Palavras-Chave #人工智能 #power management #BP #RBF
Tipo

会议论文