手機上的應用程式之啟動延遲已經成為影響使用者感受的一個重要因素，為了加速啟動的過程，Android採用LRU演算法為基礎的背景應用程式管理機制，然而在背景儲存過多的應用程式將導致手機耗電量增加，進而影響電池使用的時間，因此啟動延遲與手機續航力將成為一個兩難的課題。

本論文的主要困難點有二，第一是如何監控與評估手機上應用程式的耗電行為，我們提供了一個靜態的耗電量測工具:ANEPROF，以及一套動態的耗電模型:Energy Hunter，第二個困難點在於如何管理背景的應用程式，把低耗電或高延遲的應用快取起來，把不重要的應用程式移出背景。

根據我們邀請的受測者之模擬結果，我們所開發的Android應用程式管理系統將能同時減少15%的啟動延遲以及18%的電池續航力。

Launch delay has been an important factor affecting users' experiences in mobile applications. To launch applications quickly, modern mobile systems such as Android often employ mechanisms such as LRU-based activity stack to keep inactive applications in the background. Whenever the user wants to run and interact with a background application again, that application can be switched back into the foreground immediately from the activity stack without delay in initializing the applications anew. Since background applications still consume the battery power of the smart phone, the challenge is to effect a balance between application launch delay and battery lifetime.

The challenge entails two aspects. First, it is necessary to understand the power consumption and launch delay of mobile applications. Although it is not difficult to estimate the execution time of applications, their power consumption is hard to measure. In this thesis, we introduce two tools for measuring the power consumption of applications. The first is an offline power analysis tool called {\em ANEPROF}, and the second is an online energy model called {\em Energy Hunter}. Both offer systematic and formalized approaches for power estimation. ANEPROF is a measurement-based power analyzer which can obtain function-level power distribution and distinguish the power consumptions of threads, Java methods, and JVM services. We apply ANEPROF to provide the power consumption of default Android applications through a series of static measurement. Energy Hunter is a model-based power estimator which can track the energy footprint of individual Android applications down to the hardware components. We adopt Energy Hunter to offer runtime system power and the power consumption of third-party applications running on the system.

Given information of the power consumption and launch delay of applications, the second aspect is to manage the applications to balance the power consumption and launch delay of the whole system. Current Android implementation examines only those applications that are already in the activity stack, which limits the amount of tradeoffs that can be made. If it is possible to predict what applications to be used in the near future, then the activity stack can be better managed to optimize the tradeoff of power consumption and launch delay. In this thesis, we propose an innovative application management strategy that terminates "unfavorable" background applications to save energy and pre-launch "favorable" applications to improve the application launch delay. The core of the strategy is a context-aware prediction scheme that predicts what applications will be used next based on the environmental contexts of the mobile system.

The proposed tools and the application management strategy are evaluated through a trace-driven simulation and a 30 volunteers experiment. To evaluate the accuracy and overhead of ANEPROF, we design five sets of experiments to compare with other estimation schemes. With a 5% overhead and 14% maximal profiling error rate, ANEPROF can provide the accurate enough power consumption information for application designers. To verify Energy Hunter, we collect the energy consumption by ANEPROF as ground truth and compare the results with that from Energy Hunter. In the experiments, Energy Hunter can provide average 92% accuracy estimation. With ANEPROF and Energy Hunter, the proposed application management framework achieves 15% reduction of average application launch delay and 18% increase of average battery lifetime.

[1] Mian Dong and Lin Zhong, \Demo: chameleon: a color-adaptive web browser for mobile
oled displays", pp. 375{376, 2011.
[2] Jeongyeup Paek, Kyu-Han Kim, Jatinder P. Singh, and Ramesh Govindan, \Energy-
ecient positioning for smartphones using cell-id sequence matching", in Proceedings
of the 9th international conference on Mobile systems, applications, and services, New
York, NY, USA, 2011, MobiSys '11, pp. 293{306, ACM.
[3] Yongsoo Joo, Junhee Ryu, Sangsoo Park, and Kang G. Shin, \Fast: quick applica-
tion launch on solid-state drives", in Proceedings of the 9th USENIX conference on
File and stroage technologies, Berkeley, CA, USA, 2011, FAST'11, pp. 19{19, USENIX
Association.
[4] Charu Aggarwal, Joel L. Wolf, and Philip S. Yu, \Caching on the world wide web",
IEEE Trans. on Knowl. and Data Eng., vol. 11, no. 1, pp. 94{107, Jan. 1999.
[5] V. Kononen and P. Paakkonen, \Optimizing power consumption of always-on appli-
cations based on timer alignment", in Communication Systems and Networks (COM-
SNETS), 2011 Third International Conference on, 2011, pp. 1{8.
[6] Hosub Lee, Young Sang Choi, and Yeo-Jin Kim, \An adaptive user interface based on
spatiotemporal structure learning", Communications Magazine, IEEE, vol. 49, no. 6,
pp. 118{124, 2011.
[7] Andrew Sears and Ben Shneiderman, \Split menus: eectively using selection frequency
to organize menus", ACM Trans. Comput.-Hum. Interact., vol. 1, no. 1, pp. 27{51, Mar.
1994.
[8] Tengfei Bao, Happia Cao, Enhong Chen, Jilei Tian, and Hui Xiong, \An unsupervised
approach to modeling personalized contexts of mobile users", in Proceedings of the 2010
IEEE International Conference on Data Mining, Washington, DC, USA, 2010, ICDM
'10, pp. 38{47, IEEE Computer Society.
[9] Tingxin Yan, David Chu, Deepak Ganesan, Aman Kansal, and Jie Liu, \Fast app
launching for mobile devices using predictive user context", in Proceedings of the 10th
international conference on Mobile systems, applications, and services, New York, NY,
USA, 2012, MobiSys '12, pp. 113{126, ACM.
[10] Jason Flinn and M. Satyanarayanan, \Powerscope: A tool for proling the energy
usage of mobile applications", in Proceedings of the Second IEEE Workshop on Mobile
Computer Systems and Applications, Washington, DC, USA, 1999, WMCSA '99, pp.
2{, IEEE Computer Society.
[11] Changjiu Xian, Le Cai, and Yung-Hsiang Lu, \Power measurement of software programs
on computers with multiple i/o components", Instrumentation and Measurement, IEEE
Transactions on, vol. 56, no. 5, pp. 2079{2086, 2007.
[12] Keith I. Farkas, Jason Flinn, Godmar Back, Dirk Grunwald, and Jennifer M. Anderson,
\Quantifying the energy consumption of a pocket computer and a java virtual machine",
SIGMETRICS Perform. Eval. Rev., vol. 28, no. 1, pp. 252{263, June 2000.
[13] \Traceview: A graphical log viewer for android", 2013,
http://developer.android.com/tools/help/traceview.html.
[14] Chien-Wei Chang, Chun-Yu Lin, Chung-Ta King, Yi-Fan Chung, and Shau-Yin Tseng,
\Implementation of jvm tool interface on dalvik virtual machine", in VLSI Design
Automation and Test (VLSI-DAT), 2010 International Symposium on, 2010, pp. 143{
146.
[15] V. Kononen and P. Paakkonen, \Optimizing power consumption of always-on appli-
cations based on timer alignment", in Communication Systems and Networks (COM-
SNETS), 2011 Third International Conference on, 2011, pp. 1{8.
[16] \Simple network time protocol (sntp) version 4 for ipv4, ipv6 and osi", 2010,
http://www.faqs.org/rfcs/rfc2030.html.
[17] Justin Manweiler and Romit Roy Choudhury, \Avoiding the rush hours: Wi energy
management via trac isolation", in Proceedings of the 9th international conference on
Mobile systems, applications, and services, New York, NY, USA, 2011, MobiSys '11,
pp. 253{266, ACM.
[18] Selim Gurun and Chandra Krintz, \Autodvs: an automatic, general-purpose, dynamic
clock scheduling system for hand-held devices", in Proceedings of the 5th ACM inter-
national conference on Embedded software, New York, NY, USA, 2005, EMSOFT '05,
pp. 218{226, ACM.
[19] Ruibin Xu, Daniel Mosse, and Rami Melhem, \Minimizing expected energy in real-
time embedded systems", in Proceedings of the 5th ACM international conference on
Embedded software, New York, NY, USA, 2005, EMSOFT '05, pp. 251{254, ACM.
[20] Alex Shye, Benjamin Scholbrock, and Gokhan Memik, \Into the wild: studying real user
activity patterns to guide power optimizations for mobile architectures", in Proceedings
of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture, New
York, NY, USA, 2009, MICRO 42, pp. 168{178, ACM.
[21] W. L. Bircher, M. Valluri, J. Law, and L. K. John, \Runtime identication of mi-
croprocessor energy saving opportunities", in Proceedings of the 2005 international
symposium on Low power electronics and design, New York, NY, USA, 2005, ISLPED
'05, pp. 275{280, ACM.
[22] \Weka 3: Data mining software in java", 2013, http://www.cs.waikato.ac.nz/ml/weka/.
[23] Huanhuan Cao, Tengfei Bao, Qiang Yang, Enhong Chen, and Jilei Tian, \An eective
approach for mining mobile user habits", in Proceedings of the 19th ACM international
conference on Information and knowledge management, New York, NY, USA, 2010,
CIKM '10, pp. 1677{1680, ACM.
[24] Moo-Ryong Ra, Jeongyeup Paek, Abhishek B. Sharma, Ramesh Govindan, Martin H.
Krieger, and Michael J. Neely, \Energy-delay tradeos in smartphone applications",
in Proceedings of the 8th international conference on Mobile systems, applications, and
services, New York, NY, USA, 2010, MobiSys '10, pp. 255{270, ACM.
[25] Wanghong Yuan and Klara Nahrstedt, \Energy-ecient cpu scheduling for multimedia
applications", ACM Trans. Comput. Syst., vol. 24, no. 3, pp. 292{331, Aug. 2006.
[26] Robin Kravets and P. Krishnan, \Application-driven power management for mobile
communication", Wirel. Netw., vol. 6, no. 4, pp. 263{277, July 2000.
[27] Seungwoo Kang, Jinwon Lee, Hyukjae Jang, Hyonik Lee, Youngki Lee, Souneil Park,
Taiwoo Park, and Junehwa Song, \Seemon: scalable and energy-ecient context mon-
itoring framework for sensor-rich mobile environments", in Proceedings of the 6th in-
ternational conference on Mobile systems, applications, and services, New York, NY,
USA, 2008, MobiSys '08, pp. 267{280, ACM.
[28] David Brooks, Vivek Tiwari, and Margaret Martonosi, \Wattch: a framework for
architectural-level power analysis and optimizations", SIGARCH Comput. Archit.
News, vol. 28, no. 2, pp. 83{94, May 2000.
[29] Todd Austin, Eric Larson, and Dan Ernst, \Simplescalar: An infrastructure for com-
puter system modeling", Computer, vol. 35, no. 2, pp. 59{67, Feb. 2002.
[30] Andreas Weissel and Frank Bellosa, \Process cruise control: event-driven clock scaling
for dynamic power management", in Proceedings of the 2002 international conference
on Compilers, architecture, and synthesis for embedded systems, New York, NY, USA,
2002, CASES '02, pp. 238{246, ACM.
[31] Heng Zeng, Carla S. Ellis, Alvin R. Lebeck, and Amin Vahdat, \Ecosystem: managing
energy as a rst class operating system resource", SIGOPS Oper. Syst. Rev., vol. 36,
pp. 123{132, October 2002.
[32] Canturk Isci and Margaret Martonosi, \Runtime power monitoring in high-end proces-
sors: Methodology and empirical data", in Proceedings of the 36th annual IEEE/ACM
International Symposium on Microarchitecture, Washington, DC, USA, 2003, MICRO
36, pp. 93{, IEEE Computer Society.
[33] Gilberto Contreras and Margaret Martonosi, \Power prediction for intel xscaler; proces-
sors using performance monitoring unit events", in Proceedings of the 2005 international
symposium on Low power electronics and design, New York, NY, USA, 2005, ISLPED
'05, pp. 221{226, ACM.
[34] Andrea Acquaviva, Luca Benini, and Bruno Ricco, \Compilers and operating systems
for low power", chapter Energy characterization of embedded real-time operating sys-
tems, pp. 53{73. Kluwer Academic Publishers, Norwell, MA, USA, 2003.
[35] Fay Chang, Keith I. Farkas, and Parthasarathy Ranganathan, \Energy-driven statis-
tical sampling: detecting software hotspots", in Proceedings of the 2nd international
conference on Power-aware computer systems, Berlin, Heidelberg, 2003, PACS'02, pp.
110{129, Springer-Verlag.
[36] Jason Flinn and M. Satyanarayanan, \Energy-aware adaptation for mobile applica-
tions", SIGOPS Oper. Syst. Rev., vol. 33, no. 5, pp. 48{63, Dec. 1999.
[37] T. K. Tan, A. K. Raghunathan, G. Lakishminarayana, and N. K. Jha, \High-level
software energy macro-modeling", in Proceedings of the 38th annual Design Automation
Conference, New York, NY, USA, 2001, DAC '01, pp. 605{610, ACM.
[38] Jing Cao and Albert Nymeyer, \High-delity markovian power model for protocols", in
Proceedings of the Conference on Design, Automation and Test in Europe, 3001 Leuven,
Belgium, Belgium, 2010, DATE '10, pp. 267{270, European Design and Automation
Association.
[39] Arindam Mallik, Jack Cosgrove, Robert P. Dick, Gokhan Memik, and Peter Dinda,
\Picsel: measuring user-perceived performance to control dynamic frequency scaling",
SIGPLAN Not., vol. 43, no. 3, pp. 70{79, Mar. 2008.
[40] Eduardo Cuervo, Aruna Balasubramanian, Dae-ki Cho, Alec Wolman, Stefan Saroiu,
Ranveer Chandra, and Paramvir Bahl, \Maui: making smartphones last longer with
code ooad", in Proceedings of the 8th international conference on Mobile systems,
applications, and services, New York, NY, USA, 2010, MobiSys '10, pp. 49{62, ACM.
[41] Andreas Merkel and Frank Bellosa, \Memory-aware scheduling for energy eciency on
multicore processors", in Proceedings of the 2008 conference on Power aware computing
and systems, Berkeley, CA, USA, 2008, HotPower'08, pp. 1{1, USENIX Association.
[42] Upendra Rathnayake and Max Ott, \Predicting network availability using user con-
text", in Proceedings of the 5th Annual International Conference on Mobile and Ubiq-
uitous Systems: Computing, Networking, and Services, ICST, Brussels, Belgium, Bel-
gium, 2008, Mobiquitous '08, pp. 49:1{49:8, ICST (Institute for Computer Sciences,
Social-Informatics and Telecommunications Engineering).
[43] Matthew E. Tolentino and Kirk W. Cameron, \Improving the energy eciency of
high-performance server systems", in Proceedings of the twentieth ACM symposium on
Operating systems principles, New York, NY, USA, 2005, SOSP '05, pp. 1{9, ACM.
[44] Manish Anand, Edmund B. Nightingale, and Jason Flinn, \Ghosts in the machine: in-
terfaces for better power management", in Proceedings of the 2nd international confer-
ence on Mobile systems, applications, and services, New York, NY, USA, 2004, MobiSys
'04, pp. 23{35, ACM.
[45] Narseo Vallina-Rodriguez and Jon Crowcroft, \Erdos: achieving energy savings in
mobile os", in Proceedings of the sixth international workshop on MobiArch, New York,
NY, USA, 2011, MobiArch '11, pp. 37{42, ACM.
[46] Arjun Roy, Stephen M. Rumble, Ryan Stutsman, Philip Levis, David Mazieres, and
Nickolai Zeldovich, \Energy management in mobile devices with the cinder operating
system", in Proceedings of the sixth conference on Computer systems, New York, NY,
USA, 2011, EuroSys '11, pp. 139{152, ACM.
[47] Jong-Phil Kim, Doo-Hwan Kim, and Jang-Eui Hong, \Estimating power consumption
of mobile embedded software based on behavioral model", in Consumer Electronics
(ICCE), 2010 Digest of Technical Papers International Conference on, 2010, pp. 105{
106.
[48] Tao Li and Lizy Kurian John, \Run-time modeling and estimation of operating system
power consumption", SIGMETRICS Perform. Eval. Rev., vol. 31, no. 1, pp. 160{171,
June 2003.