成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	范均誌 Fan, Chun-Chih
論文名稱：	應用於不確定性服務需求之動態電源管理自我調適決策 Self-Tuning Policy for Dynamic Power Management on Non-Stationary Service Requests
指導教授：	楊中平 Young, Chung-Ping
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 資訊工程學系 Department of Computer Science and Information Engineering
論文出版年：	2005
畢業學年度：	93
語文別：	英文
論文頁數：	49
中文關鍵詞：	電源管理
外文關鍵詞：	power management, DVS, DPM, energy saving
相關次數：	點閱：64 下載：1
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

　　能源消耗是系統設計上的重要議題，而動態電源管理(DMP)是節省能源的一項重要技術之ㄧ。動態電源管理是用來降低電子系統耗電量的設計方法，它藉由調整系統的功率及效能並以滿足系統工作負載為條件來達到省電的功能。在真實世界中的系統，如個人數位助理(PDAs),筆記型電腦等，工作負載與使用者如何操作系統很有密切的關係。但是在系統設計時期，我們卻無法得知未來的工作負載是如何變化。在這樣的情況下，動態電源管理必須要能處理不確定性服務需求的環境。因此，我們提出線上分析(on-line)的動態電源管理自我調適決策來解決不確定性服務需求的問題，該決策將系統視為馬可夫鏈鎖(Markov Chains)來取得較佳省電效果的。傳統中的動態電源管理節由關閉系統中閒置的裝置來節省能源，在此論文中，我們尚延伸動態電源管理機制去調整系統工作中裝置的電源狀態，以節省更多能源。論文中的自我調適決策是透過一個滑動視窗(sliding window)來調整動態電源管理的所做出的判斷，藉此來滿足不確定性服務需求的使用環境。最後，我們模擬Intel PXA270的硬體特性來展示我們所提出之動態電源管理自我調適決策的效果。

　Energy consumption is an important system design issue. Dynamic Power Management (DPM) has been a key technique to save energy. The DPM is a design methodology to reduce power consumption of electric system by reconfiguring their power and performance level. However, for a large class of application in electric system likes PDAs and laptops, the workload for the system strongly depends on applications running and user operation on the system, which is very common in real-life systems. Hence, the workload is unknown at design time. To satisfy this condition, DPM schemes must deal with unknown and nonstationary stochastic environment. In this work, we present an on-line self-tuning DPM policy, which modeled as Markov Chains, to handle the nonstationary workload. Conventional DPM performs selective shutdown of idle system components. We extend DPM to manage multiple active power states of system component. We introduce a workload self-tuning technique based on sliding window, which dynamically adjust policy decision of DPM to meet the variations of environment. We simulate hardware characteristics of a processor to demonstrate the effectiveness of our approach.

1 Introduction ........................................................... 1
　1.1 Background and Motive ...............................................1
1.2 Literature Organization ...............................................3

2 Related Works ...........................................................5

3 System Level Power Management ...........................................8
　3.1 Dynamic Power Management Technologies ...............................8
　　3.1.1 Timeout ........................................................10
　　3.1.2 Predictive Techniques ..........................................10
　　3.1.3 Stochastic Control .............................................11
　3.2 Dynamic Voltage and Frequency Scaling Technologies .................11
　　3.2.1 DVFS on Non-Real-Time Applications .............................12
　　3.2.2 DVFS on Real-Time Applications .................................14

4 Self-Tuning Policy .....................................................15
　4.1 Availability on Power Model ........................................15
　4.2 Assumption .........................................................18
　4.3 The Poisson Probability Distribution ...............................20
　4.4 Modeling Power-Managed System ......................................22
　4.5 Processor Power States .............................................27
　4.6 Self-Tuning Policy Algorithm .......................................29
　　4.6.1 Performance States .............................................29
　　4.6.2 Power States ...................................................33

5 Simulation .............................................................37
　5.1 Methodology ........................................................37
　5.2 Simulator System Model .............................................38
　5.3 Simulation Results .................................................40

6 Conclusion .............................................................45

Reference ................................................................46
                                    

[1] L. Benini, A. Bogliolo, G. Paleologo, and G.D. Micheli, “Policy optimization for dynamic power management,” IEEE Trans. On Computer-Aided Design of Integrated Circuits and Systems, Vol. 18, 813-833, 1999.

[2] L. Benini, A. Bogliolo, and G.D. Micheli, “A survey of design techniques for system-level dynamic power management,” IEEE Transactions on VLSI Systems, Vol. 8, 299-315, 2000.

[3] E. Y. Chung, L. Benini, A. Bogliolo, and G.D. Micheli, “Dynamic power management for non-stationary service requests,” in Proc. Design and Test in Europe (DATE), 77-81, 1999.

[4] ARM Ltd, “ARM Intelligent Energy Manager,” http://www.arm.com/products/CPUs/cpu-arch-IEM.html

[5] T.D.Burd and R.Broderson, “Energy efficient CMOS microprocessor Design,” in Proc. of the 28th Annual Hawaii International Conference on System Sciences, 1995.

[6] Eui-Young Chung, Benini, L., Bogliolo, A., Yung-Hsiang Lu, and De Micheli, G.,“Dynamic power management for non-stationary service requests, Computers,” IEEE Transactions on Volume 51, Issue 11, Nov. 2002 Page(s):1345 - 1361

[7] Intel, “Intel PXA27x Processor Family Electrical, Mechanical, and Thermal Specification,” http://www.intel.com/design/pca/applicationsprocessors/manuals/280002.htm

[8] P. Greenawalt, “Modeling Power Management for Hard Disks, Proc. Int’l Workshop Modeling, Analysis, and Simulation for Computer and Telecomm”. Systems, pp. 62-65, 1994.

[9] R. Golding, P. Bosh, and J. Wilkes, “Idleness is not sloth,” HP Laboratories Tech. Rep. HPL-96-140, 1996.

[10] M. Srivastava, A. Chandrakasan, and R. Brodersen, “Predictive system shutdown and other architectural techniques for energy efficient programmable computation,” IEEE Trans. VLSI Syst., vol. 4, pp. 42–55, Mar. 1996.

[11] T. Pering, T. Burd, and R. Brodersen, “The simulation and evaluation of dynamic voltage scaling algorithms,” in Proc. Int. Symp. Low Power Electronics & Design, pp. 76-81, Aug. 1998.

[12] B. Mangione-Smith, “Low-power communication protocols: Paging and beyond,” in IEEE Symp. Low-Power Electronics, Apr. 1995, pp. 8–11.

[13] J. Oh and M. Pedram, “Gated clock routing minimizing the switched capacitance,” in Design Automation and Test in Europe Conf., Feb. 1998, pp. 692–697.

[14] Y.-H. Lu and G. De Micheli, “Adaptive Hard Disk Power Management on Personal Computers,” Proc. Great Lakes Symp. VLSI, pp. 50-53, 1999.

[15] C.-H. Hwang and A. Wu, “A Predictive System Shutdown Method for Energy Saving of Event-Driven Computation,” Proc. Int’l Conf. Computer-Aided Design, pp.28-32, 1997.

[16] E.-Y. Chung, L. Benini, and G. De Micheli, “Dynamic Power Management Using Adaptive Learning Tree,” Proc. Int’l Conf. Computer-Aided Design, pp. 274-279, 1999.

[17] Q. Qiu and M. Pedram, “Dynamic Power Management Based on Continuous-Time Markov Decision Processes”. In Design Automation Conference, pages 555–561, 1999.

[18] T. Simunic, L. Benini, P. Glynn, and G. De Micheli, “Dynamic power management of portable systems using semi-Markov decision processes,” in DATE, Proc. Design Automation and Test in Europe, Mar. 2000.

[19] T. Simunic, L. Benini, and G. De Micheli, “Event-Driven Power Management of Portable Systems, Proc”. Int’l Symp. System Synthesis, pp. 18-23, 1999.

[20] Intel, “Intel PXA27x Processor Family Power Requirements Application Note,” http://www.intel.com/design/pca/applicationsprocessors/applnots/280005.htm

[21] Intel, Microsoft, and Toshiba, “Advanced Configuration and Power Interface Specification Revision 3.0,” http://www.acpi.info/, September 2, 2004.

[22] K. Li, R. Kumpf, P. Horton, and T. Anderson. “A quantitative analysis of disk drive power management in portable computers,” In USENIX Winter Conference, pages 279–292, 1994.

[23] M. Weiser, B. Welch, A. Demers, and S. Shenker, “Scheduling for reduced CPU energy,” in Proc. Symp. Operating Systems Design & Implementation, Usenix
Association, Nov. 1994.

[24] K. Govil, E. Chan, and H. Wasserman, “Comparing algorithms for dynamic speed-setting of a low-power CPU,” in Proc. MOBICOM, pp. 13-25, 1995.

[25] Intel, “Intel PXA27x Processor Family Developer’s Manual,” Oct, 2004
http://www.intel.com/design/pca/applicationsprocessors/manuals/280000.htm

[26] Padmanabhan Pillai, Kang G. Shin, “Real-time dynamic voltage scaling for low-power embedded operating systems,” in Proc. of 18th Symposium on Operating Systems Principles, Banff, Canada, October, 2001.

[27] F. Yao, A. Demers, and S. Shenker, “A scheduling model for reduced CPU energy," in Proc. Ann. Symp. Foundations Computer Science, pp. 374-381, 1995.

[28] I. Hong, M. Potkonjak, and M. B. Srivastava, “On-line scheduling of hard real-time tasks on variable voltage processor," in Proc. Int. Conf Computer-Aided Design, pp. 653-656, Nov. 1998.

[29] C. M. Krishna and Y.-H. Lee, Voltage-clock-scaling adaptive scheduling techniques for low power in hard real-time systems," in Proc. Real-Time Technology & Applications Symp., May 2000.

[30] Y. Shin, K. Choi, and T. Sakurai, “Power optimization of real-time embedded systems on variable speed processors," in Proc. Int. Conf. Computer-Aided Design, pp. 365-368, Nov. 2000.

[31] A. Acquaviva, L. Benini, and B. Ricco, “An adaptive algorithm for low power streaming multimedia processing," in Proc. Design Automat. & Test in Europe Conf., Mar. 2001.

[32] J. Pouwelse, K. Langendoen, and H. Sips, “Energy priority scheduling for variable voltage processors," in Proc. Int. Symp. Low Power Electronics & Design, Aug. 2001.

[33] J. Pouwelse, K. Langendoen, and H. Sips, “Dynamic Voltage Scaling on a Low-Power Microprocessor,” 7th International Conference on Mobile Computing and Networking (MOBICOM), Rome, Italy, July 2001.

[34] D. Gross and C. M. Hanis, “Fundamentals of Queueing Theory,” Wiley (1985).

校內：立即公開
校外：2005-09-07公開

簡易檢索 / 詳目顯示

相關論文