An Analysis of Power Consumption in Mobile Cloud Computing

With the rapid proliferation of mobile devices, mobile cloud computing is emerging as an increasingly omnipresent paradigm enabling users to use battery-powered mobile devices to access a wide range of compute-intensive applications hosted on the clouds. Often, the assumption is that mobile devices consume less power when they access an application run on the cloud than when the application is run on the device itself. This, however, is increasingly questionable with the significant recent progress in improving power efficiency of mobile devices (e.g., using ultra low power GPUs). This paper aims at analyzing and comparing the benefits of these two alternatives using mobile cloud gaming as an example. Our evaluation shows that, despite the recent advances towards reducing power consumption in mobile devices, mobile cloud computing remains the best of the two alternatives in a wide range of scenarios.

[1]  Maurice Gagnaire,et al.  A Mobile Application Offloading Algorithm for Mobile Cloud Computing , 2015, 2015 3rd IEEE International Conference on Mobile Cloud Computing, Services, and Engineering.

[2]  Dimitrios Koutsonikolas,et al.  Power-throughput tradeoffs of 802.11n/ac in smartphones , 2015, 2015 IEEE Conference on Computer Communications (INFOCOM).

[3]  Rajkumar Buyya,et al.  A Context Sensitive Offloading Scheme for Mobile Cloud Computing Service , 2015, 2015 IEEE 8th International Conference on Cloud Computing.

[4]  Rajkumar Buyya,et al.  A Review on Distributed Application Processing Frameworks in Smart Mobile Devices for Mobile Cloud Computing , 2013, IEEE Communications Surveys & Tutorials.

[5]  Mahadev Satyanarayanan,et al.  Cloudlets: at the leading edge of mobile-cloud convergence , 2014, 6th International Conference on Mobile Computing, Applications and Services.

[6]  David Wetherall,et al.  Demystifying 802.11n power consumption , 2010 .

[7]  Bharat K. Bhargava,et al.  A Survey of Computation Offloading for Mobile Systems , 2012, Mobile Networks and Applications.

[8]  Minyong Kim,et al.  A Novel GPU Power Model for Accurate Smartphone Power Breakdown , 2015 .

[9]  Jianming Zhang,et al.  Energy-efficient and network-aware offloading algorithm for mobile cloud computing , 2014, Comput. Networks.

[10]  Gernot Heiser,et al.  An Analysis of Power Consumption in a Smartphone , 2010, USENIX Annual Technical Conference.

[11]  Alec Wolman,et al.  Outatime: Using Speculation to Enable Low-Latency Continuous Interaction for Cloud Gaming , 2014 .

[12]  Parth H. Pathak,et al.  A first look at 802.11ac in action: Energy efficiency and interference characterization , 2014, 2014 IFIP Networking Conference.

[13]  Ralf Steinmetz,et al.  Will Mobile Cloud Gaming Work? Findings on Latency, Energy, and Cost , 2013 .

[14]  Douglas C. Schmidt,et al.  Analyzing Mobile Application Software Power Consumption via Model-driven Engineering , 2011, PECCS.

[15]  Abdelmounaam Rezgui,et al.  Mobile Cloud Gaming: Issues and Challenges , 2013, MobiWIS.

[16]  Hao Wu,et al.  Heuristics to allocate high-performance cloudlets for computation offloading in mobile ad hoc clouds , 2015, The Journal of Supercomputing.

[17]  Ramesh Govindan,et al.  Estimating mobile application energy consumption using program analysis , 2013, 2013 35th International Conference on Software Engineering (ICSE).