What is the limit of energy saving by dynamic voltage scaling?

Dynamic voltage scaling (DVS) is a technique that varies the supply voltage and clock frequency based on the computation load to provide desired performance with the minimal amount of energy consumption. It has been demonstrated as one of the most effective low power system design techniques, in particular for real time systems. Previously, there are works on both ends of the DVS systems: the ideal variable voltage system which can change its voltage with no physical constraints, and the multiple voltage system which has a number of discrete voltages available simultaneously. In this paper, we study the DVS systems between these two extreme cases. We consider systems that can vary the operating voltage dynamically under various real-life physical constraints. Based on the system's different behavior during voltage transition, we define the feasible DVS system and the practical DVS system. We build mathematical model to analyze the potential of DVS on energy saving for these different systems. Finally, we simulate the behavior of a secure wireless communication networks with DVS systems. The results show that DVS results in energy reduction from 36% to 79%, and the real life DVS systems can be very close to the ideal system in energy saving.

[1]  Miodrag Potkonjak,et al.  Power optimization of variable-voltage core-based systems , 1999, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[2]  Lama H. Chandrasena,et al.  A rate selection algorithm for quantized undithered dynamic supply voltage scaling , 2000, ISLPED'00: Proceedings of the 2000 International Symposium on Low Power Electronics and Design (Cat. No.00TH8514).

[3]  M. Potkonjak,et al.  Techniques for energy minimization of communication pipelines , 1998, 1998 IEEE/ACM International Conference on Computer-Aided Design. Digest of Technical Papers (IEEE Cat. No.98CB36287).

[4]  Mark C. Johnson,et al.  Datapath scheduling with multiple supply voltages and level converters , 1997, TODE.

[5]  Gang Quan,et al.  Energy efficient fixed-priority scheduling for real-time systems on variable voltage processors , 2001, DAC '01.

[6]  Mark Horowitz,et al.  Clustered voltage scaling technique for low-power design , 1995, ISLPED '95.

[7]  Massoud Pedram,et al.  Energy Minimization Using Multiple Supply Voltages , 1997, ISLPED.

[8]  Thomas D. Burd,et al.  Design issues for Dynamic Voltage Scaling , 2000, ISLPED'00: Proceedings of the 2000 International Symposium on Low Power Electronics and Design (Cat. No.00TH8514).

[9]  Majid Sarrafzadeh,et al.  Variable voltage scheduling , 1995, ISLPED '95.

[10]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[11]  F. Frances Yao,et al.  A scheduling model for reduced CPU energy , 1995, Proceedings of IEEE 36th Annual Foundations of Computer Science.

[12]  Majid Sarrafzadeh,et al.  Provably good algorithm for low power consumption with dual supply voltages , 1999, 1999 IEEE/ACM International Conference on Computer-Aided Design. Digest of Technical Papers (Cat. No.99CH37051).

[13]  R.W. Brodersen,et al.  A dynamic voltage scaled microprocessor system , 2000, IEEE Journal of Solid-State Circuits.

[14]  Anantha P. Chandrakasan,et al.  Low-power CMOS digital design , 1992 .

[15]  Miodrag Potkonjak,et al.  Power optimization of variable voltage core-based systems , 1998, Proceedings 1998 Design and Automation Conference. 35th DAC. (Cat. No.98CH36175).

[16]  Hiroto Yasuura,et al.  Voltage scheduling problem for dynamically variable voltage processors , 1998, Proceedings. 1998 International Symposium on Low Power Electronics and Design (IEEE Cat. No.98TH8379).

[17]  Thomas D. Burd,et al.  Voltage scheduling in the IpARM microprocessor system , 2000, ISLPED'00: Proceedings of the 2000 International Symposium on Low Power Electronics and Design (Cat. No.00TH8514).