On Using Stochastic Approximation for Frequency Scaling in Android OS

  • Stanislav Sartasov Saint Petersburg State University, 28, Universitetskiy pr, 198504, Saint Petersburg, Russia
  • Evgenii Bogdanov Saint Petersburg State University, 28, Universitetskiy pr, 198504, Saint Petersburg, Russia
  • Alexander Bozhniuk Saint Petersburg State University, 28, Universitetskiy pr, 198504, Saint Petersburg, Russia
  • David Bykov Saint Petersburg State University, 28, Universitetskiy pr, 198504, Saint Petersburg, Russia
  • Oleg Granichin Saint Petersburg State University, 28, Universitetskiy pr, 198504, Saint Petersburg, Russia
Keywords: stochastic approximation, dynamic voltage frequency scaling, energy efficiency, Android OS.

Abstract

Simultaneous perturbation stochastic approximation demonstrate good results for control theory problems where system states dynamically changes. In this paper a dynamic voltage frequency scaling governor creation based on this approach for smartphone CPU under Android OS is described and ways to improve it are considered. The new governor shows results comparable to default Android OS governors

Author Biographies

Stanislav Sartasov, Saint Petersburg State University, 28, Universitetskiy pr, 198504, Saint Petersburg, Russia

Senior Lecturer of the Department of System Program-Department of Mathematics and Mechanics, St. Petersburg State University, stanislav.sartasov@spbu.ru

Evgenii Bogdanov, Saint Petersburg State University, 28, Universitetskiy pr, 198504, Saint Petersburg, Russia

Graduate of the educational program of the bachelor’s degree “Software Engineering” SPbSU, evgenij.bogdanov.1999@gmail.com

Alexander Bozhniuk, Saint Petersburg State University, 28, Universitetskiy pr, 198504, Saint Petersburg, Russia

Student of the educational bachelor’s program “Software Engineering” SPbSU 3 years of study, bozhnyuks@mail.ru

David Bykov, Saint Petersburg State University, 28, Universitetskiy pr, 198504, Saint Petersburg, Russia

Student of the educational bachelor’s program “Software Engineering” SPbSU 3
years of study, bykov.david@gmail.com

Oleg Granichin, Saint Petersburg State University, 28, Universitetskiy pr, 198504, Saint Petersburg, Russia

Doctor of Physical and Mathematical Sciences, Professor, Oleg_granichin@mail.ru

References

C. Sahin, F.Cayci, I. Manotas, J. Clause, F. Kiamilev, L. Pollock, and K. Winbladh, “Initial explorations on design pattern energy usage,” in Proc. of 1st International Workshop on Green and Sustainable Software, GREENS, June 2012. 2012, pp. 55–61; doi: 10.1109/GREENS.2012.6224257

J. C. Spall, “Multivariate stochastic approximation using a simultaneous perturbation gradient approximation,” IEEE Trans. on Automatic Control, vol. 37, no. 3, pp. 332–341, 1992; doi: 10.1109/9.119632

O. Granichin and N. Amelina, “Simultaneous perturbation stochastic approximation for tracking under unknown but bounded disturbances,” IEEE Trans. on Automatic Control, vol. 60, no. 6, pp. 1653–1658, 2015; doi: 10.1109/TAC.2014.2359711

O. Granichin, L. Gurevich, and A. Vakhitov, “Discrete-time minimum tracking based on stochastic approximation algorithm with randomized differences,” in Proc. of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference, 2009, pp. 5763–5767; doi: 10.1109/CDC.2009.5400839

D. Brodowski and N. Golde, “Cpu frequency and voltage scaling code in the Linux™ kernel. Linux cpufreq. cpufreq governors,” in The Linux Kernel Archives. [Online]. Available: https://www.kernel. org/doc/Documentation/cpu-freq/governors.txt

K. Poornambigai, M. L. Raj, and P. Meena, “Reducing the energy consumption using DVFS performance optimizing scheme,” EPRA International Journal of Research and Development (IJRD), vol. 2, no. 1, pp. 79–88, 2017.

Y. L. Chen, M. F. Chang, C. W. Yu, X. Z. Chen, and W. Y. Liang, “Learning-directed dynamic voltage and frequency scaling scheme with adjustable performance for single-core and multi-core embedded and mobile systems,” Sensors, vol. 18, no. 9, art. 3068, pp. 1–28, 2018; doi: 10.3390/s18093068

J. Lee, S. Nam, and S. Park, “Energy-Efficient Control of Mobile Processors Based on Long Short-Term Memory,” IEEE Access, vol. 7, pp. 80552–80560, 2019; doi: 10.1109/ACCESS.2019.2923334

A. Das, M. J. Walker, A. Hansson, B. M. Al-Hashimi, and G. V. Merrett, “Hardware-software interaction for run-time power optimization: A case study of embedded Linux on multicore smartphones,” in Proc. of 2015 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), 2015, pp. 165–170; doi: 10.1109/ISLPED.2015.7273508

X. Li, W. Wen, and X. Wang, “Usage history-directed power management for smartphone,” in Algorithms and Architectures for Parallel Processing. ICA3PP 2015. Lecture Notes in Computer Science, vol. 9528, Springer, Cham., pp. 288-302; doi: 10.1007/978-3-319-27119-4_20

L. Broyde, K. Nixon, X. Chen, H. Li, and Y. Chen, “MobiCore: An adaptive hybrid approach for power-efficient CPU management on Android devices,” in Proc. of 2017 30th IEEE International System-on-Chip Conference (SOCC), 2017, pp. 221–226; doi: 10.1109/SOCC.2017.8226044

O. Granichin, “Linear regression and filtering under nonstandard assumptions (arbitrary noise),” IEEE Transactions on Automatic Control, vol. 49, no. 10, pp. 1830–1837, 2004; doi: 10.1109/TAC.2004.835585

E. Bogdanov, A. Bozhnyuk, S. Sartasov, and O. Granichin, “On Application of Simultaneous Perturbation Stochastic Approximation for Dynamic Voltage-Frequency Scaling in Android OS,” in Proc. of 2021 7th International Conference on Event-Based Control, Communication, and Signal Processing (EBCCSP), 2021, pp. 1–7; doi: 10.1109/EBCCSP53293.2021.9502396

Xiaomi Corp. “Xiaomi Redmi Note 8 pro specifications,” in MI Official site. [Online]. Available: https: //www.mi.com/global/redmi-note-8-pro/specs/

“Android OS cpufreq specification,” in Google Git. [Online]. Available: https://android.googlesource.com/kernel/common/+/a7827a2a60218b25f222b54f77ed38f57aebe08b/Documentation/cpu-freq/index.txt

V. Myasnikov, S. Sartasov, I. Slesarev, and P. Gessen, “Energy consumption measurement frameworks for Android OS: A systematic literature review,” in Proc. of the Fifth Conference on Software Engineering and Information Management (ser. CEUR Workshop Proceedings), SEIM, St. Petersburg, May 16, 2020, 2020, pp. 18–29.

“Samsung Galaxy A3 specifications,” in Gsmarena. [Online]. Available: https://www.gsmarena.com/samsung_galaxy_a3_(2016)-7791.php

Published
2021-08-15
How to Cite
Sartasov, S., Bogdanov, E., Bozhniuk, A., Bykov, D., & Granichin, O. (2021). On Using Stochastic Approximation for Frequency Scaling in Android OS. Computer Tools in Education, (2), 26-40. https://doi.org/10.32603/2071-2340-2021-2-26-40
Section
Software Engineering