在使用移動網路時，使用者常感受到手機迅速耗電的現象，因此本論文旨在移動網路中，發展一個能學習使用者習慣的省電機制。目前針對移動網路下耗電情形的解決方法皆是學習封包模式，並預測下個封包出現的時間，來制定相關的省電模式。但這樣的作法忽略了使用者與手機互動的關聯，並不能達到最佳的省電效能。
因此在本論文中，我們以人機互動的觀點，分析研究使用者過去使用手機的習慣，預測使用者下次使用手機的時間點，並在使用者下次使用手機前，以開關網路的方式迫使封包群聚收送，達到省電的目的。由實驗結果證明，本論文所提出之省電機制在影響可接受的使用者體驗下，約可延長手機三天的使用時間。且本論文所提出之省電機制在節電效能表現優於其他現有方法。

Recent researches indicate that radio tail is one of the main causes for energy consumption of mobile devices in 3G/4G mobile networks. However, applications (apps) on a mobile device, such as e-mail, instant messaging, keep awaking the network interface to retrieve the latest information, resulting in numerous radio tails and thus consuming lots of energy. In this thesis, a power-saving scheme based on user behaviors is proposed to reduce the occurrence of the radio tails. In the proposed scheme, while a user is not using the device, application traffics are merged together by switching on/off the network interface, and thus power consumption caused by radio tails is reduced. Unlike other existing schemes, the proposed scheme does not need to monitor network traffic, which requires the root permission of mobile devices; it only collects app usage and screen status to learn user behaviors, and controls wake up/sleep timers of the network interface according to the collected contexts for the mobile user. The proposed scheme has been implemented as an Android app, named as Automatic Battery Savior (ABS), in this thesis. Our evaluation results show that devices installed with ABS outperform those with the baseline method.

[1] N. Balasubramanian, A. Balasubramanian, and A. Venkataramani, "Energy consumption in mobile phones: a measurement study and implications for network applications," in Proceedings of the 9th ACM SIGCOMM conference on Internet measurement conference, 2009, pp. 280-293.
[2] S. Deng and H. Balakrishnan, "Traffic-aware techniques to reduce 3g/lte wireless energy consumption," in Proceedings of the 8th international conference on Emerging networking experiments and technologies, 2012, pp. 181-192.
[3] F. Yu, G. Xue, H. Zhu, Z. Hu, M. Li, and G. Zhang, "Cutting without pain: Mitigating 3G radio tail effect on smartphones," in INFOCOM, 2013 Proceedings IEEE, 2013, pp. 440-444.
[4] Y. Kim and J. Kim, "Personalized Diapause: Reducing Radio Energy Consumption of Smartphones by Network-Context Aware Dormancy Predictions}," in Presented as part of the 2012 Workshop on Power-Aware Computing and Systems}, 2012.
[5] F. Xu, Y. Liu, T. Moscibroda, R. Chandra, L. Jin, Y. Zhang, et al., "Optimizing background email sync on smartphones," in Proceeding of the 11th annual international conference on Mobile systems, applications, and services, 2013, pp. 55-68.
[6] V. Kononen and P. Paakkonen, "Optimizing power consumption of always-on applications based on timer alignment," in Communication Systems and Networks (COMSNETS), 2011 Third International Conference on, 2011, pp. 1-8.
[7] E. J. Vergara and S. Nadjm-Tehrani, "Energy-aware cross-layer burst buffering for wireless communication," in Proceedings of the 3rd International Conference on Future Energy Systems: Where Energy, Computing and Communication Meet, 2012, p. 24.
[8] Slv3r, "Auto3G," Vers. 1.5.5. ed. Google Play: Slv3r, 2014.
[9] A. Aucinas, N. Vallina-Rodriguez, Y. Grunenberger, V. Erramilli, K. Papagiannaki, J. Crowcroft, et al., "Staying online while mobile: The hidden costs," ACM CoNEXT, vol. 13, 2013.
[10] J.-M. Kang, S.-s. Seo, and J.-K. Hong, "Usage pattern analysis of smartphones," in Network Operations and Management Symposium (APNOMS), 2011 13th Asia-Pacific, 2011, pp. 1-8.
[11] J. Huang, F. Qian, Z. M. Mao, S. Sen, and O. Spatscheck, "Screen-off traffic characterization and optimization in 3G/4G networks," in Proceedings of the 2012 ACM conference on Internet measurement conference, 2012, pp. 357-364.
[12] I. Monsoon Solutions. (2014). Power Monitor. Available: http://www.msoon.com/LabEquipment/PowerMonitor/
[13] T. Yan, D. Chu, D. Ganesan, A. Kansal, and J. Liu, "Fast app launching for mobile devices using predictive user context," in Proceedings of the 10th international conference on Mobile systems, applications, and services, 2012, pp. 113-126.
[14] Wikipedia contributors. (2014). Hamming distance. Available: http://en.wikipedia.org/w/index.php?title=Special:Cite&page=Hamming_distance&id=600525858
[15] Z.-X. Liao, Y.-C. Pan, W.-C. Peng, and P.-R. Lei, "On mining mobile apps usage behavior for predicting apps usage in smartphones," in Proceedings of the 22nd ACM international conference on Conference on information & knowledge management, 2013, pp. 609-618.
[16] W. contributors. (2014). Approximation error. Available: http://www.en.wikipedia.org/w/index.php?title=Special:Cite&page=Approximation_error&id=612303007
[17] Y. Huang, B. Song, and S. S. Soliman, "Adaptive fast dormancy for energy efficient wireless packet data communications," in Communications (ICC), 2013 IEEE International Conference on, 2013, pp. 6194-6199.
[18] M. Martins and R. Fonseca, "Application modes: a narrow interface for end-user power management in mobile devices," in Proceedings of the 14th Workshop on Mobile Computing Systems and Applications, 2013, p. 5.
[19] N. Ding, D. Wagner, X. Chen, Y. C. Hu, and A. Rice, "Characterizing and modeling the impact of wireless signal strength on smartphone battery drain," in Proceedings of the ACM SIGMETRICS/international conference on Measurement and modeling of computer systems, 2013, pp. 29-40.
[20] J. Huang, F. Qian, A. Gerber, Z. M. Mao, S. Sen, and O. Spatscheck, "A close examination of performance and power characteristics of 4G LTE networks," in Proceedings of the 10th international conference on Mobile systems, applications, and services, 2012, pp. 225-238.
[21] R. Herrmann, P. Zappi, and T. Rosing, "Context Aware Power Management of Mobile Systems for Sensing Applications," in 2nd International Workshop on Mobile Sensing, 2012.
[22] T. Soikkeli, J. Karikoski, and H. Hammainen, "Diversity and end user context in smartphone usage sessions," in Next generation mobile applications, services and technologies (NGMAST), 2011 5th international conference on, 2011, pp. 7-12.
[23] C. S. Bontu and E. Illidge, "DRX mechanism for power saving in LTE," Communications Magazine, IEEE, vol. 47, pp. 48-55, 2009.
[24] Z.-X. Liao, P.-R. Lei, T.-J. Shen, S.-C. Li, and W.-C. Peng, "Mining temporal profiles of mobile applications for usage prediction," in Data Mining Workshops (ICDMW), 2012 IEEE 12th International Conference on, 2012, pp. 890-893.
[25] M. Vlachos, S. Y. Philip, and V. Castelli, "On Periodicity Detection and Structural Periodic Similarity," in SDM, 2005, pp. 449-460.
[26] N. Imai and K. Yoshihara, "A power-saving standby method to extend battery life in dual-mode cellular phones," in Consumer Communications and Networking Conference (CCNC), 2012 IEEE, 2012, pp. 224-229.
[27] Y. Xu, M. Lin, H. Lu, G. Cardone, N. Lane, Z. Chen, et al., "Preference, context and communities: a multi-faceted approach to predicting smartphone app usage patterns," in Proceedings of the 17th annual international symposium on International symposium on wearable computers, 2013, pp. 69-76.
[28] P. K. Athivarapu, R. Bhagwan, S. Guha, V. Navda, R. Ramjee, D. Arora, et al., "Radiojockey: mining program execution to optimize cellular radio usage," in Proceedings of the 18th annual international conference on Mobile computing and networking, 2012, pp. 101-112.
[29] G. Xue, H. Zhu, Z. Hu, J. Yu, Y. Zhu, and G. Zhang, "SmartCut: Mitigating 3G Radio Tail Effect on Smartphones."
[30] J. Wu, Y. Wu, S. Zhou, and Z. Niu, "Traffic-aware power adaptation and base station sleep control for energy-delay tradeoffs in green cellular networks," in Global Communications Conference (GLOBECOM), 2012 IEEE, 2012, pp. 3171-3176.
[31] K. Church and B. Smyth, "Understanding the intent behind mobile information needs," in Proceedings of the 14th international conference on Intelligent user interfaces, 2009, pp. 247-256.