الگوریتم کاهش انرژی مصرفی پویا برای سیستم‌های بی‌درنگ بحرانی-مختلط با پردازنده‌های چندهسته‌ای
محورهای موضوعی : مهندسی برق و کامپیوتر
سید حسن صادق زاده
1
(پیام نور)
کلید واژه: سیستم‌های تعبیه‌شده بحرانی- مختلط, پردازنده‌های چندهسته‌ای, انرژی مصرفی, تغییر پویای ولتاژ و فرکانس,
چکیده مقاله :
امروزه برخلاف سیستم‌های تعبیه‌شده سنتی که دارای وظایف با درجه اهمیت یکسان هستند، بسیاری از سیستم‌های تعبیه‌شده، بحرانی- مختلط می‌باشند و بیشتر مورد استفاده قرار می‌گیرند. سیستم‌های بحرانی- مختلط، سیستم‌های تعبیه‌شده بی‌درنگی هستند که برای تجمیع برنامه‌های ایمنی- بحرانی و ایمنی- غیربحرانی بر روی یک بستر مشترک سخت‌افزاری معرفی شده‌اند. پردازنده‌های چندهسته‌ای، قابلیت تجمیع کاربردهای متفاوت بر روی یک سخت‌افزار را فراهم کرده و می‌توانند انتخاب مناسبی برای سیستم‌های تعبیه‌شده بحرانی- مختلط باشند. با این حال، کاهش انرژی مصرفی در این سیستم‌ها به‌دلیل حجم بالای پردازش و طراحی عموماً مبتنی بر باتری آنها یک نیاز ضروری است؛ بنابراین در این مقاله، یک روش زمان‌بندی ابتکاری به‌منظور کاهش انرژی مصرفی در سیستم‌های بحرانی- مختلط متشکل از پردازنده چندهسته‌ای معرفی می‌شود. این الگوریتم ضمن تضمین اجرای به‌موقع وظایف بحرانی، انرژی مصرفی سیستم را با تغییر پویای ولتاژ و فرکانس (DVFS) کاهش خواهد داد. نتایج به‌دست‌آمده از شبیه‌سازی‌ها نشان مي‌دهند که انرژي مصرفي الگوریتم پیشنهادی در مقايسه با روش‌هاي مشابه تا 30% بهبود مي‌يابد.
Today, unlike traditional embedded systems that have tasks with the same degree of importance, many critical embedded systems are mixed and are used more often. Mixed critical systems are real-time embedded systems introduced to consolidate critical safety and non-critical safety programs on a common hardware platform. Multi-core processors provide the ability to integrate different applications on one hardware and can be a suitable choice for mixed critical embedded systems. However, reducing the energy consumption in these systems is a necessary requirement due to the high volume of processing and their generally battery-based design. Therefore, in this paper, an innovative scheduling method is introduced to reduce energy consumption in mixed critical systems consisting of multi-core processors. This algorithm will reduce the energy consumption of the system by DVFS, while ensuring the timely execution of critical tasks. The results obtained from the simulations show that the energy consumption of the proposed algorithm is improved by 30% compared to similar methods.
[1] س. ح. صادق‌زاده و ی. صداقت، "زمان‌بندی آگاه از انرژی مصرفی برای سیستم‌های بی‌درنگ تک‌پردازنده‌ای بحرانی- مختلط،" نشریه علمی- پژوهشی نشريه مهندسي برق و مهندسي كامپيوتر ايران، سال 16، شماره 4، صص. 334-327، زمستان 1397.
[2] D. Zhu, "Reliability-aware dynamic energy management in dependable embedded real-time systems," ACM TECS, vol. 10, no. 2, Article ID: 26, 27 pp., Dec. 2011.
[3] P. Marwedel, Embedded System Design: Embedded Systems Foundations of Cyber-Physical Systems, Berlin, Germany: Springer, 2010.
[4] H. Kopetz, Real-Time Systems: Design Principles for Distributed Embedded Applications, Springer Science & Business Media, 2011.
[5] S. Baruah, et al., "Scheduling real-time mixed-criticality jobs," IEEE Trans. on Computers, vol. 61, no. 8, pp. 1140-1152, Aug. 2012.
[6] F. Santy, L. George, P. Thierry, and J. Goossens, "Relaxing mixedcriticality scheduling strictness for task sets scheduled with FP," in Proc. Euromicro Conf. on Real-Time Systems, ECRTS’12, pp. 155-165, Pisa, Italy, 11-13 Jul. 2012.
[7] S. Baruah, et al., "The preemptive uniprocessor scheduling of mixed-criticality implicit-deadline sporadic task systems," in Proc. Euromicro Conf. on Real-Time Systems, ECRTS'12, pp. 145-154, Pisa, Italy, 11-13 Jul. 2012.
[8] P. Taeju and K. Soontae, "Dynamic scheduling algorithm and its schedulability analysis for certifiable dual-criticality systems," in Proc. Int. Conf. Embedded Software, EMSOFT'11, pp. 253-262, Taipei Taiwan, 9-14 Oct. 2011.
[9] S. Baruah, H. Li, and L. Stougie, "Towards the design of certifiable mixed-criticality systems," in Proc. 16th IEEE Real-Time and Embedded Technology and Applications Symp., pp. 13-22, Stockholm, Sweden, 12-15 Apr. 2010.
[10] P. Huang, H. Yang, and L. Thiele, "On the scheduling of fault-tolerant mixed-criticality systems," in Proc. Design Automation Conf. (DAC), ACM/EDAC/IEEE, DAC'14, 6 pp., 1-5 Jun. 2014.
[11] S. Baruah and S. Vestal, "Schedulability analysis of sporadic tasks with multiple criticality specifications," in Proc. Euromicro Conf. on Real-Time Systems, ECRTS'08, pp. 147-155, Prague, Czech Republic, 2-4 Jul. 2008.
[12] Z. Lia, C. Guo, X. Hua, and S. Ren, "Reliability guaranteed energy minimization on mixed-criticality systems," J. of Syst. and Software, vol. 112, pp. 1-10, Feb. 2016.
[13] H. Su, D. Zhu, and S. Brandt, "An elastic mixed-criticality task model and early-release EDF scheduling algorithms," ACM TODAES, vol. 22, no. 2, Article ID: 28, 28 pp., Apr. 2017.
[14] A. Thekkilakattil, R. Dobrin, and S. Punnekkat, "Fault-tolerant scheduling of mixed-criticality real-time tasks under error bursts," Procedia Computer Science, vol. 46, pp. 1148-1155, 2015.
[15] P. Ekberg and W. Yi, "Bounding and shaping the demand of mixed-criticality sporadic tasks," in Proc. 24th Euromicro Conference on Real-Time Systems, ECRTS, pp. 135-144, Pisa, Italy, 11-13 Jul. 2012.
[16] S. Vestal, "Preemptive scheduling of multi-criticality systems with varying degrees of execution time assurance," in Proc. 28th IEEE Int. Real-Time Systems Symp., pp. 239-243, Tucson, AZ, USA, 3-6 Dec. 2007.
[17] J. Lin, A. M. K. Cheng, D. Steel, and M. Yu-Chi Wu, "Scheduling mixed-criticality real-time tasks in a fault-tolerant system," International Journal of Embedded and Real-Time Communication Systems, vol. 6, no. 2, 22 pp., 2015.
[18] C. Kamienski, et al., "Application development for the Internet of Things: a context-aware mixed criticality systems development platform," Computer Communications, vol. 104, pp. 1-16, 15 May 2017.
[19] A. Taherin, M. Salehi, and A. Ejlali, "Reliability-aware energy management in mixed-criticality systems," IEEE Trans. on Sustainable Computing, vol. 3, no. 3, pp. 195-208, Jul.-Sept. 2018.
[20] M. Salehi, A. Ejlali, and B. M. Al-Hashimi, "Two-phase low-energy N-modular redundancy for hard real-time multi-core systems," IEEE TPDS, vol. 27, no. 5, pp. 1497-1510, May 2015.
[21] S. Baruah, C. Bipasa, L. Haohan, and S. Insik, "Mixed-criticality scheduling on multiprocessors," Real-Time Systems, vol. 50, no. 1, pp. 142-177, Jan. 2014.
[22] C. Gu, G. Nan, D. Qingxu, and Y. Wang, "Partitioned mixed-criticality scheduling on multiprocessor platforms," in Proc. Design, Automation & Test in Europe Conf. & Exhibition, DATE'14, 6 pp., Dresden, Germany, 24-28 Mar. 2014.
[23] Y. Zhang and K. Chakrabarty, "Dynamic adaptation for fault tolerance and power management in embedded real-time systems," ACM Trans. on Embedded Computing Systems, vol. 3, no. 2, pp. 336-360, May 2004.
[24] L. Benini, A. Bogliolo, and G. De Micheli, "A survey of design techniques for system-level dynamic power management," IEEE Trans. VLSI Sys., vol. 8, no. 3, pp. 299-316, Jun. 2000.
[25] T. D. Burd, T. A. Pering, A. J. Stratakos, and R. W. Brodersen, "A dynamic voltage scaled microprocessor system," IEEE J. Solid-State Circuits, vol. 35, no. 11, pp. 1571-1580, Nov. 2000.
[26] M. A. Haque, H. Aydin, and D. Zhu, "On reliability management of energy-aware real-time systems through task replication," IEEE Trans. Parallel Distrib. Syst., vol. 28, no. 3, pp. 813-825, Mar. 2017.
[27] Y. Zhang and R.Chen, "A survey of energy-aware scheduling in mixed-criticality systems," Journal of Systems Architecture, vol.1, no.17, Article ID: 102524, Jun. 2022.
[28] J. Chen and C. Kuo, "Energy-efficient scheduling for realtime systems on dynamic voltage scaling (dvs) platforms," in Proc. Embedded and Real-Time Computing Systems and Applications, RTCSA'07, pp. 28-38, Daegu, South Korea, 21-24 Aug. 2007.
[29] A. Burns and R. I. Davis, Mixed-Criticality Systems: A Review, Tech. Rep., Dept. Comput. Sci. Univ. York, 61 pp. 1-61, 2016.
[30] S. Narayana, P. Huang, G. Giannopoulou, L. Thiele, and R. V. Prasad, "Exploring energy saving for mixed-criticality systems on multi-cores," in Proc. IEEE Real-Time and Embedded Technology and Applications Symp., RTAS'16, 12 pp., Vienna, Austria, 11-14 Apr. 2016.
[31] P. Huang, P. Kumar, G. Giannopoulou, and L. Thiele, "Energy efficient DVFS scheduling for mixed-criticality systems," in Proc. Int. Conf. Embedded Software, EMSOFT'14, 10 pp., Uttar Pradesh, India, 12-17 Oct. 2014.
[32] V. Moghaddas, M. Fazeli, and A. Patooghy, "Reliability-oriented scheduling for static-priority real-time tasks in standby-sparing systems," Microprocessors and Microsystems, Pt A, vol. 45, pp. 208-215, Aug. 2016.
[33] V. Legout, M. Jan, and L. Pautet, "Mixed-criticality multiprocessor real-time systems: energy consumption vs deadline misses," in Proc. 1st. Workshop on Real-Time Mixed Criticality Syst., ReTiMiCS'13', 6 pp., Taipei, Taiwan. Aug. 2013.
[34] M. Völp, M. Hähnel, and A. Lackorzynski, "Has energy surpassed timeliness? scheduling energy-constrained mixed-criticality systems," in Proc. IEEE Real-Time and Embedded Technology and Applications Symp., RTAS'14, pp. 275-284, Berlin, Germany, 15-17 Apr. 2014.
[35] F. Zhang and A. Burns, "Schedulability analysis for real-time systems with EDF scheduling," IEEE Trans. on Computers, vol. 589, no. 9, pp. 1250-1258, Sept. 2009.
[36] N. Audsley, Optimal Priority Assignment and Feasibility of Static Priority Tasks with Arbitrary Start Times, Dept. of Comp. Sci., University of York, UK, 1991.
[37] A. K. Singh, M. Shafique, A. Kumar, and J. Henkel, "Mapping on multi/many-core systems: Survey of current and emerging trends," in Proc. of 50th ACM/EDAC/IEEE Design Automation Conf., DAC'13, pp. 275-284, Austin, TX, USA, 29 May-7 Jun. 2013.
[38] A. Bastoni, B. B. Brandenburg, and J. H. Anderson, "An emperical comparison of global, partitioned and clustered multiprocessor EDF mchedulers," in Proc. 31st IEEE Real-Time Systems Symp., RTSS'10, San Diego, CA, USA, 30 Nov.-3 Dec. 2010.