Fuzzy-Controlled Voltage Scaling Based on Supply Current Tracking

We discuss an adaptive fuzzy logic controller to accurately and robustly predict and track supply current variations of digital processors. The proposed controller tracks supply current variations without updating any parameter during its runtime prediction. It can be used to adjust the supply voltage and clock frequency of digital processors based on workload variations when accounting for timing-constraints and other practical requirements. Additionally, we comprehensively examine the stability analysis of the closed-loop configuration containing the fuzzy controller and the digital processor model. We prove that the fuzzy controller guarantees the asymptotic stability of the closed-loop architecture. Several experiments are performed to exhibit effectiveness of the proposed fuzzy controller comparing to the other existing conventional prediction methods. The results show that the proposed controller outperforms the other existing methods.

[1]  Kevin Skadron,et al.  Reducing multimedia decode power using feedback control , 2003, Proceedings 21st International Conference on Computer Design.

[2]  Jan M. Rabaey,et al.  Low Power Design Essentials , 2009, Series on Integrated Circuits and Systems.

[3]  Sharad Malik,et al.  Instruction level power analysis and optimization of software , 1996, Proceedings of 9th International Conference on VLSI Design.

[4]  Samarjit Chakraborty,et al.  Control theory-based DVS for interactive 3D games , 2008, 2008 45th ACM/IEEE Design Automation Conference.

[5]  T. Morrison,et al.  Dynamical Systems , 2021, Nature.

[6]  Venkataramanan Balakrishnan,et al.  System identification: theory for the user (second edition): Lennart Ljung; Prentice-Hall, Englewood Cliffs, NJ, 1999, ISBN 0-13-656695-2 , 2002, Autom..

[7]  Luca Benini,et al.  Policy optimization for dynamic power management , 1998, Proceedings 1998 Design and Automation Conference. 35th DAC. (Cat. No.98CH36175).

[8]  Margaret Martonosi,et al.  Formal control techniques for power-performance management , 2005, IEEE Micro.

[9]  Ayman A. Al-Lawama,et al.  The Advantages of PID Fuzzy Controllers Over The Conventional Types , 2008 .

[10]  Douglas M. Bates,et al.  Nonlinear Regression Analysis and Its Applications , 1988 .

[11]  Wei Sun,et al.  Predict task running time in grid environments based on CPU load predictions , 2008, Future Gener. Comput. Syst..

[12]  José Pineda de Gyvez,et al.  Dynamic voltage scaling based on supply current tracking using fuzzy Logic controller , 2009, 2009 16th IEEE International Conference on Electronics, Circuits and Systems - (ICECS 2009).

[13]  Ali Afzali-Kusha,et al.  Dynamic Voltage and Frequency Scheduling for Embedded Processors Considering Power/Performance Tradeoffs , 2011, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[14]  Michael C. Huang,et al.  A framework for dynamic energy efficiency and temperature management , 2000, MICRO 33.

[15]  W.J.M. Kickert.  ANALYSIS OF A FUZZY LOGIC CONTROLLER , 1993 .

[16]  Abraham Kandel,et al.  Stability analysis of fuzzy control systems , 1999, Fuzzy Sets Syst..

[17]  F. Windmeijer,et al.  An R-squared measure of goodness of fit for some common nonlinear regression models , 1997 .

[18]  Anantha Chandrakasan,et al.  Dynamic voltage scheduling using adaptive filtering of workload traces , 2001, VLSI Design 2001. Fourteenth International Conference on VLSI Design.

[19]  Kevin Skadron,et al.  Control-theoretic dynamic frequency and voltage scaling for multimedia workloads , 2002, CASES '02.

[20]  Ali H. Sayed,et al.  Adaptive Filters , 2008 .

[21]  R. Ayyanar,et al.  Estimation of Microprocessor Instantaneous Load Current , 2009, IEEE Transactions on Advanced Packaging.

[22]  Mandayam A. L. Thathachar,et al.  On the stability of fuzzy systems , 1997, IEEE Trans. Fuzzy Syst..

[23]  Ryozo Katoh,et al.  Stability analysis of fuzzy control system applying conventional methods , 1991, Proceedings IECON '91: 1991 International Conference on Industrial Electronics, Control and Instrumentation.

[24]  David Blaauw,et al.  Reliability modeling and management in dynamic microprocessor-based systems , 2006, 2006 43rd ACM/IEEE Design Automation Conference.

[25]  Sungroh Yoon,et al.  Run-Time Adaptive Workload Estimation for Dynamic Voltage Scaling , 2009, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[26]  Brad Calder,et al.  Phase tracking and prediction , 2003, ISCA '03.