Volume 22, Issue 1 (JIAEEE Vol.22 No.1 2025)
Journal of Iranian Association of Electrical and Electronics Engineers 2025, 22(1): 99-109 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
ziaee F, Ghazvini M, Kaedi M. Power Management Optimization in Multi-Core Processors via Machine Learning and DVFS. Journal of Iranian Association of Electrical and Electronics Engineers 2025; 22 (1) :99-109
URL: http://jiaeee.com/article-1-1583-en.html
URL: http://jiaeee.com/article-1-1583-en.html
Shahid Bahonar University of Kerman
Abstract: (667 Views)
As transistor sizes in processors continue to shrink, overall energy consumption has paradoxically increased due to the growing number of transistors. This trend has led to significant thermal challenges and a decline in system performance. Additionally, circuit aging has become a major concern, adversely impacting both processor performance and longevity. Dynamic Voltage and Frequency Scaling (DVFS) is a widely used power management technique that mitigates energy consumption and enhances system durability by dynamically adjusting processor voltage and frequency. This paper introduces a novel machine learning-based approach for power management in multi-core processors. The proposed method utilizes input feature analysis and integrates a decision tree algorithm with DVFS techniques to precisely predict and allocate the optimal voltage and frequency for each core. Evaluation results reveal that the model achieves a prediction accuracy of 95%, effectively forecasting system performance under various workloads. This approach offers a valuable contribution to the development of energy-efficient systems.
Keywords: Multi-core processors, Power manager, Machine learning, Dynamic Voltage and Frequency Scaling (DVFS), Decision tree algorithm
Type of Article: Research |
Subject:
Electronic
Received: 2023/03/11 | Accepted: 2024/11/19 | Published: 2025/05/29
Received: 2023/03/11 | Accepted: 2024/11/19 | Published: 2025/05/29
Extended Abstract [PDF 266 KB] (8 Download)
References
1. [1] شرفینژاد، سیدرضا. علیزاده، بیژن. "درستی‌سنجی صوری معماری مدیریت توان در سطح سیستم برای پردازنده‌های مدرن"، نشریه مهندسی برق و الکترونیک ایران، سال هجدهم، شماره چهارم، زمستان 1400.
2. [2] نوری، مسعود. بکرانی، مهدی. "آینه جریان توان پایین مبتنی بر ماسفت با گیت شبه شناور"، نشریه مهندسی برق و الکترونیک ایران، سال بیست و یکم، شماره اول، بهار 1403.
3. [3] P. Manoj, A. Jantsch, and M. Shafique, "SmartDPM: Machine Learning-Based Dynamic Power Management for Multi-Core Microprocessors", Journal of Low Power Electronics, vol. 14, no. 4, pp. 460-474, 2018. [DOI:10.1166/jolpe.2018.1576]
4. [4] L. R. Juracy, M. T. Moreira, A. d. M. Amory, and F. G. Moraes, "A survey of aging monitors and reconfiguration techniques", arXiv preprint arXiv:2007.07829, 2020.
5. [5] S. Pagani, P. S. Manoj, A. Jantsch, and J. Henkel, "Machine learning for power, energy, and thermal management on multicore processors: A survey", IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 39, no. 1, pp. 101-116, 2018. [DOI:10.1109/TCAD.2018.2878168]
6. [6] F. A. Endo, "Génération dynamique de code pour l'optimisation énergétique", Université Grenoble Alpes (ComUE), 2015.
7. [7] H. Jung and M. Pedram, "Supervised learning based power management for multicore processors", IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 29, no. 9, pp. 1395-1408, 2010. [DOI:10.1109/TCAD.2010.2059270]
8. [8] H. Shen, J. Lu, and Q. Qiu, "Learning based DVFS for simultaneous temperature, performance and energy management", in Thirteenth International Symposium on Quality Electronic Design (ISQED), 2012, pp. 747-754: IEEE. [DOI:10.1109/ISQED.2012.6187575]
9. [9] Panda, Prasanta, Aruna Tripathy, and Kanhu Charan Bhuyan. "Reinforcement Learning-Based Dynamic Voltage and Frequency Scaling for Energy-Efficient Computing", 2024 Third International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE). IEEE, 2024. [DOI:10.1109/ICDCECE60827.2024.10549241]
10. [10] K. Yu, "Deep Reinforcement Learning Based DVFS Algorithm Frameworks", SWINBURNE UNIVERSITY OF TECHNOLOGY, 2022.
11. [11] Tian, Zhongyuan, et al. "Collaborative power management through knowledge sharing among multiple devices", IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 38.7 (2018): 1203-1215. [DOI:10.1109/TCAD.2018.2837131]
12. [12] S. K. Thethi and R. Kumar, "Power optimization of a single-core processor using LSTM based encoder-decoder model for online DVFS", Sādhanā, vol. 48, no. 2, p. 37, 2023. [DOI:10.1007/s12046-023-02086-3]
13. [13] S. Yue, D. Zhu, Y. Wang, and M. Pedram, "Reinforcement learning based dynamic power management with a hybrid power supply", in 2012 IEEE 30th International Conference on Computer Design (ICCD), 2012, pp. 81-86: IEEE. [DOI:10.1109/ICCD.2012.6378621]
14. [14] L. Li et al., "An Improved Q-Learning for System Power Optimization with Temperature, Performance and Energy Constraint Modeling", in 2020 IEEE Conference on Telecommunications, Optics and Computer Science (TOCS). [DOI:10.1109/TOCS50858.2020.9339699]
15. [15] A. Das, R. A. Shafik, G. V. Merrett, B. M. Al-Hashimi, A. Kumar, and B. Veeravalli, "Reinforcement learning-based inter-and intra-application thermal optimization for lifetime improvement of multicore systems", in Proceedings of the 51st Annual Design Automation Conference, 2014, pp. 1-6. [DOI:10.1145/2593069.2593199]
16. [16] A. Iranfar, S. N. Shahsavani, M. Kamal, and A. Afzali-Kusha, "A heuristic machine learning-based algorithm for power and thermal management of heterogeneous MPSoCs", in 2015 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), 2015, pp. 291-296: IEEE. [DOI:10.1109/ISLPED.2015.7273529]
17. [17] A. Yeganeh-Khaksar, M. Ansari, S. Safari, S. Yari-Karin, and A. Ejlali, "Ring-DVFS: Reliability-aware reinforcement learning-based DVFS for real-time embedded systems", IEEE Embedded Systems Letters, vol. 13, no. 3, pp. 146-149, 2020. [DOI:10.1109/LES.2020.3033187]
18. [18] S. Kim, K. Bin, S. Ha, K. Lee, and S. Chong, "zTT: Learning-based DVFs with zero thermal throttling for mobile devices", in Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services, 2021, pp. 41-53. [DOI:10.1145/3458864.3468161]
19. [19] C. Robert, "Machine learning, a probabilistic perspective", ed: Taylor & Francis, 2014. [DOI:10.1080/09332480.2014.914768]
20. [20] M. P. Deisenroth, A. A. Faisal, and C. S. Ong, Mathematics for machine learning. Cambridge University Press, 2020. [DOI:10.1017/9781108679930]
21. [21] Y. Wang and M. Pedram, "Model-free reinforcement learning and bayesian classification in system-level power management", IEEE Transactions on Computers, vol. 65, pp. 3713-3726, 2016. [DOI:10.1109/TC.2016.2543219]
22. [22] V. Spiliopoulos, A. Bagdia, A. Hansson, P. Aldworth, and S. Kaxiras, "Introducing DVFS-management in a full-system simulator", in 2013 IEEE 21st International symposium on modelling, analysis and simulation of computer and telecommunication systems, 2013, pp. 535-545: IEEE. [DOI:10.1109/MASCOTS.2013.75]
23. [23] S. K. Thethi and R. Kumar, "Online DVFS using Deep Learning: Sequence to Sequence LSTM Networks with Attention", 2022. [DOI:10.36227/techrxiv.21539991]
24. [24] Yu, Ke, et al. "An improved DVFS algorithm for energy-efficient real-time task scheduling", 2020 IEEE 22nd International Conference on High Performance Computing and Communications; IEEE 18th International Conference on Smart City; IEEE 6th International Conference on Data Science and Systems (HPCC/SmartCity/DSS). IEEE, 2020. [DOI:10.1109/HPCC-SmartCity-DSS50907.2020.00033]
25. [25] Yu, Ke, et al. "A Framework for Deep Q-Learning Based Hybrid DVFS Algorithms for Real-Time Systems", 2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom). IEEE, 2021. [DOI:10.1109/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00127]
26. [26] P. Pillai and K. G. Shin, "Real-time dynamic voltage scaling for low-power embedded operating systems", in Proceedings of the eighteenth ACM symposium on Operating systems principles, 2001, pp. 89-102. [DOI:10.1145/502034.502044]
27. [27] Farzane Nakhaee et al. 2017. Lifetime improvement by exploiting aggressive voltage scaling during runtime of error-resilient applications. Integration, the VLSI Journal (2017). [DOI:10.1016/j.vlsi.2017.10.013]
28. [28] Carvalho, Sidartha AL, Daniel C. Cunha, and Abel G. Silva-Filho. "On the use of nonlinear methods for low-power CPU frequency prediction based on Android context variables", 2016 IEEE 15th International Symposium on Network Computing and Applications (NCA). IEEE, 2016. [DOI:10.1109/NCA.2016.7778627]
29. [29] Patterson, David A. "Computer Organization and Design", (2022).
30. [30] C. Robert, "Machine learning, a probabilistic perspective", ed: Taylor & Francis, 2014. [DOI:10.1080/09332480.2014.914768]
31. [31] M. P. Deisenroth, A. A. Faisal, and C. S. Ong, Mathematics for machine learning: Cambridge University Press, 2020. [DOI:10.1017/9781108679930]
32. [32] Cormen, Thomas H., et al. Introduction to algorithms. MIT press, 2022.
Send email to the article author
| Rights and permissions | |
 |
This Journal is an open access Journal Licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. (CC BY NC 4.0) |
