Energy Consumption in Mobile Phones: Measurement, Design Implications, and Algorithms

In this paper, we present a measurement study of the energy consumption characteristics of three widespread mobile networking technologies: 3G, GSM, and WiFi. We find that 3G and GSM incur a high tail energy overhead because of lingering in high power states after completing a transfer. Based on these measurements, we develop a model for the energy consumed by network activity for each technology. Armed with this model, we seek to reduce the energy consumption of common mobile applications. Towards this goal, we develop TailEnder, a protocol that schedules transfers so as to minimize the cumulative energy consumed while meeting user-specified delay-tolerance deadlines. We show that the TailEnder algorithm is within a factor 1.28× of the optimal and show that no deterministic online algorithm can achieve a better competitive ratio. For applications like web search that can benefit from prefetching, TailEnder can aggressively prefetch several times more data and improve user-specified response times while consuming less energy. We evaluate the benefits of TailEnder for three different case study applications—email, news feeds, and web search—based on real user logs and show significant reduction in energy consumption in each case. Experiments conducted on the mobile phone shows that TailEnder can download 60% more news feed updates and download search results for more than 50% of web queries, compared to using the default policy. Our model-driven simulation shows that TailEnder can reduce energy by 35% for email applications, 52% for news feeds and 40% for web search.

[1]  Jeffrey C. Mogul,et al.  Using predictive prefetching to improve World Wide Web latency , 1996, CCRV.

[2]  Leonard Kleinrock,et al.  Web prefetching in a mobile environment , 1998, IEEE Wirel. Commun..

[3]  Wei Luo,et al.  Impacts of inactivity timer values on UMTS system capacity , 2002, 2002 IEEE Wireless Communications and Networking Conference Record. WCNC 2002 (Cat. No.02TH8609).

[4]  John Augustine,et al.  Optimal power-down strategies , 2004, 45th Annual IEEE Symposium on Foundations of Computer Science.

[5]  Jul-Hung Yeh,et al.  Impact of inactivity timer on energy consumption in WCDMA and cdma2000 , 2004, 2004 Symposium on Wireless Telecommunications.

[6]  Eyal de Lara,et al.  Efficient and transparent dynamic content updates for mobile clients , 2006, MobiSys '06.

[7]  Philippe Baptiste.  Scheduling unit tasks to minimize the number of idle periods: a polynomial time algorithm for offline dynamic power management , 2006, SODA '06.

[8]  Rajesh K. Gupta,et al.  CoolSpots: reducing the power consumption of wireless mobile devices with multiple radio interfaces , 2006, MobiSys '06.

[9]  Alec Wolman,et al.  Wireless wakeups revisited: energy management for voip over wi-fi smartphones , 2007, MobiSys '07.

[10]  Ahmad Rahmati,et al.  Context-for-wireless: context-sensitive energy-efficient wireless data transfer , 2007, MobiSys '07.

[11]  Deepak Ganesan,et al.  Triage: balancing energy and quality of service in a microserver , 2007, MobiSys '07.

[12]  Morteza Zadimoghaddam,et al.  Scheduling to minimize gaps and power consumption , 2013, Journal of Scheduling.

[13]  Prasant Mohapatra,et al.  Energy Consumption and Conservation in WiFi Based Phones: A Measurement-Based Study , 2007, 2007 4th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks.

[14]  Jukka K. Nurminen,et al.  Energy-Consumption in Mobile Peer-to-Peer - Quantitative Results from File Sharing , 2008, 2008 5th IEEE Consumer Communications and Networking Conference.

[15]  Xin Liu,et al.  Experiences in a 3G network: interplay between the wireless channel and applications , 2008, MobiCom '08.

[16]  Yu Xiao,et al.  Energy Consumption of Mobile YouTube: Quantitative Measurement and Analysis , 2008, 2008 The Second International Conference on Next Generation Mobile Applications, Services, and Technologies.