移动计算中自适应负载转移决策模型研究
|
摘要
以智能手机为代表的移动设备,受限于设备自身的尺寸、大容量电池制造工艺的滞后、无线通信网络的不稳定,已经越来越难以满足移动用户对智能手机执行功能更加复杂、能耗需求更高应用的需求。移动设备系统电能消耗与电池容量增长速度的不一致,系统能提供的计算能力与新应用的需求增长速度的不一致是移动设备发展中面临的挑战。移动负载转移思想,提出移动设备可以与服务器构成一个协作系统,通过负载转移的方式将部分应用功能(任务)转移至(协作)服务器端远程执行,提升应用执行的性能,如减少执行时间、减少设备能耗、提高执行结果质量等。
与之对应的移动协作应用由多个任务组成,包括若干个可负载转移任务,即该任务既可以在移动设备本地执行,也可以在协作服务器端执行。移动负载转移的核心问题是如何使得移动协作应用,一方面可以尽可能地通过远程协作提升执行性能；另一方面又尽可能地减少由于资源可用性变化造成的执行延迟或者失败。例如,减小移动设备到协作服务器之间端到端的带宽波动对数据传输时间的影响,减小服务器负载变化对执行时间的影响等。移动负载转移决策引擎的任务就是根据协作系统的资源可用性和移动应用执行性能要求,动态决定移动协作应用中,每一个可负载转移任务的执行位置。现有的决策引擎多采用“静态决策策略”,采用静态决策策略的决策引擎仅仅在应用执行前启动,为应用的每一个任务选择执行位置后即停止。在应用执行过程中,决策引擎不对协作系统资源可用性变化进行跟踪,不对应用执行进度进行跟踪,不再调整任务执行位置,直至执行完成或者确认失败。静态决策策略缺乏应对资源变化的灵活,可能导致应用执行的延迟、失败,或增加移动设备额外的能量开销。
本文的工作1围绕如何使得移动负载转移决策引擎更加灵活地,自适应地应对协作系统资源可用性的变化,提高决策的准确性,提高应用执行的性能而展开。本文提出“执行路径”的概念描述移动协作应用中各个任务在远程或本地执行的不同组合,采用图论的方法对移动协作应用的执行过程进行建模。采用“应用执行路径图”描述一个移动协作应用各种不同的执行组合以及与之对应的执行路径。决策引擎的任务是根据协作系统资源可用性情况,目标函数(减少执行时间、减少设备能耗等),应用执行性能要求等为应用选择一条最优的执行路径。一方面可以尽可能地有效利用系统资源,提升应用执行性能,同时也尽量减小执行延迟和失败的风险。为了改进“静态决策策略”的不足,本文提出一组“自适应决策策略”,具体而言,本文
1.提出“动态决策策略”。动态决策策略允许决策引擎在应用执行的全过程中,跟踪协作系统资源可用性情况变化和应用执行进度,并且可以根据协作系统资源可用性变化,调整协作应用的执行路径。
2.提出“冗余路径执行”。与现有的“静态决策策略”中,移动协作应用只能采取一条路径执行不同。冗余路径执行允许协作应用同时采用多条执行路径同时执行,最早返回的结果将被使用。同时,决策引擎通过引入概率风险模型,评估因为对协作系统资源可用性估值偏差造成错误决策的概率和相应的风险,辅助应用执行路径、单路径执行或者冗余路径执行方案的选择。
3.提出“联合决策策略”。联合决策策略允许协作服务器一起参与移动设备的负载转移决策过程。移动设备可以共享应用执行的性能要求,如执行完成的时间期限、最低执行结果质量要求等。当协作服务器接收到移动设备的任务数据和执行要求后,可以根据自身负载情况动态调整,如在负载条件允许下,提供更高质量的执行结果等。
4.提出“渐进式数据传输”模式,以减少网络波动对于数据传输的影响。由于在服务器端,计算处理和网络传输通常不会造成资源重叠,渐进式数据传输不会影响应用执行时间。先前数据传递时候的网络带宽测试数据,也可以作为后续传送时,估算传送时间的依据。
评估实验采用移动人脸识别应用(mobile face detection)和移动全景图应用(mobile panorama)作为目标应用。在运行安卓(Android)操作系统的Nexus S智能手机上,分别实现了基于动态决策策略和支持冗余路径执行方案的Wing负载转移决策系统,以及基于联合自适应决策策略和支持渐进式数据传输模式的Mind负载转移决策系统。
评估实验采用控制变量的方法,评估自适应决策策略在应对协作服务器负载波动时的决策质量。实验结果显示,相比静态决策策略,采用单路径执行的动态决策策略可以减少30%(50%)左右的应用执行时间,30%(50%)左右的设备能耗。同时,Wing系统在执行动态决策时候的决策时间开销很小,与采用静态决策策略的时间开销相似。
评估实验采用基于网络Trace数据的模拟实验方法,评估自适应决策策略在应对移动设备到服务器之间端到端网络连接质量波动时的决策质量。网络Trace数据集合包括约2400分钟的WiFi网络Trace数据,涵盖静态应用场景和移动(步行)应用场景,总计约1万多条数据记录(上行带宽、下行带宽、往返时延等),提供了约1万多个决策评估点。实验评估还采用了4种常见的基本网络带宽估值模型。评估结果显示,与静态决策策略相比,采用单路径执行的动态决策策略平均可以降低40-50%的错误决策概率,同时减少30%左右的应用执行时间,40-50%左右的设备能耗。采用冗余路径执行(路径切换时保留原有执行路径的)的动态决策策略平均可以降低30%左右的应用执行时间,降低30%左右的设备能耗。与静态决策策略相比,采用渐进式数据传输模式的联合决策策略,可以降低10-20%的错误决策概率。
Besides light-weight Internet applications, computation-and/or energy-heavy appli-cations are increasingly deployed to mobile devices. However, the limited computation power, battery lifetime and network connectivity make it difficult for mobile devices to become the center of mobile computing. Mobile offloading, or remote execution, between a mobile device and a capable server has proven effective in improving mobile applica-tion's performance.
A mobile collaborative application consists of several tasks, some of which are "of-floadable" that can be offloaded to the collaboration server for execution. Lying at the core of a mobile offloading system is the offload engine that is responsible for determin-ing when and where to execute each task—i.e., locally on the mobile device or remotely on the server—based on resource availability and application's performance requirements. For example, in order for the mobile device to offload a computation-and/or energy-heavy task to the server, its execution state must first be sent to the server, and the execution re-sult should later be returned to the mobile device. Fluctuations in network condition and server workload may affect data transmission time and server response time. The offload engine must thus carefully weigh the expected gain in the device's energy consumption and the task completion time against the cost of network communication.
In the thesis2, collaborative application's execution is modeled with a graph, where the execution is decomposed into different stages which are connected via transaction-s. The execution of an application may take different paths, each of which consumes different amount of time and device energy. The offload engine must select an optimal execution path, balancing between resource availability and performance requirements.
Existing offload decision-making strategies usually assume that resource availability—e.g., network bandwidth and server workload—remains unchanged throughout path exe-cution. This assumption yields non-adaptive offload decisions, which, once determined, remain unchanged until the execution is completed or a failure is detected. However, ac- tual resource availability often exhibits high variability on the time-scale of seconds and also varies with location. The highly variable condition of the underlying resources dic-tates computation and communication costs, possibly causing long application execution delays (even failures) or missing opportunities to improve application performance.
Realizing the impact of resource-availability variations on the application execution performance, the thesis proposes a set of novel adaptive offload decision-making strate-gies, trying to minimize the risk of application execution delays or failures as well as to improve application execution performance and device energy performances by oppor-tunistically exploiting resource-availability improvements, if any. To be more specific, the thesis proposes following contributions.
·Dynamic decision making strategy is proposed to enable offload decision-making at runtime to (re)-evaluate the impact of resource-availability changes on appli-cation performance and then change the execution path accordingly on-the-fly. This enables mobile application's responsive and flexible adaptation to resource-availability variations.
·Redundant execution is proposed to enable application execution using multiple execution paths so as to better explore performance improvement opportunities. Redundant execution enables mobile collaborative application to be executed with two execution paths simultaneously, whichever result comes first is used. Offload engine can also introduce probability-based decision-making approach, account-ing for the risk of incorrect decisions to minimize its impact on application execu-tion.
·Joint decision-making strategy is proposed to enable mobile client to share its execution performance requirements with the server, thus permitting the server to advise on an offload decision.
·Server may also enable incremental delivery of results, so as to reduce the execu-tion delay/failure due to the fluctuating wireless network condition.
The thesis studies the design, implementation of adaptive-decision making strate-gies based mobile offloading systems, Wing and Mind. The thesis evaluates the decision quality of adaptive decision making strategies in coping with server workload variance and network connectivity variance. Wing is based on dynamic decision making strategy and redundant path execution while Mind is based on joint decision making strategy and incremental data delivery mechanism. Two mobile applications, mobile face detection and mobile panorama, are created as target applications for evaluation.
A controlled experiment is designed to evaluate the quality of adaptive decision making strategies in adaptation to collaboration server workload variance. This synthetic experiment is intended to help to understand system's behavior in controlled scenarios rather than precisely emulate actual server workload variance. Our experimental results indicate that Wing can achieve30%(50%) reduction of application execution time and30%(50%) reduction of device energy consumption. The overhead incurred by Wing is trivial, which is within10ms when performing per runtime decision making.
A trace-based emulation experiment is designed to evaluate the quality of adaptive decision making strategies in adaptation to end-to-end network bandwidth fluctuations between mobile device and collaboration server. The use of real-world traces provides experimental repeatability and allows a careful comparison among different strategies. The network trace is collected in the north and central campus of University of Michigan and in Ann Arbor city, covering both stationary scenarios, e.g., offices, public cafeteria and walking scenarios3. The total length of WiFi network trace is around2,400minutes, including over10,000records and decision making points for evaluation. Furthermore, the experiment evaluates the impact of4basic types of most commonly used network bandwidth estimators (Spot, Ody, Avg, Medium) on decision quality. Experiment results show that comparing with non-adaptive decision making strategy, dynamic decision mak-ing strategy with single path execution can reduce incorrect decision rate by an average of40-50%while achieving a30%(40-50%) reduction of application execution time (device energy consumption) over the non-adaptive offload decision-making strategy. With redun-dant path execution, dynamic decision making strategy is able to achieve30%reduction of application execution time and30%reduction of device energy consumption. Evaluation shows that joint decision making strategy with incremental data delivery can reduce in-correct decisions by an average of10-20%over the non-adaptive offload decision-making strategy.
In conclusion, the thesis proposes a set of adaptive decision making strategies to cope with resource dynamics fluctuations in mobile offloading between a mobile device and a collaboration server. As far as is known, this is the first effort trying to address the impact of highly-variable resource availability on the application execution performance. The synthetic experiment and in-depth evaluation based on real-world network traces indicate that comparing with non-adaptive decision making strategy, adaptive decision making strategies can significantly improve application execution performance in terms of execution time and device energy consumption while reducing execution delays and/or failures. The proposed strategies and underlying approaches are applicable not only to mobile offloading but also to other research work where adaptation to resource changes is required to ensure performance.
与之对应的移动协作应用由多个任务组成,包括若干个可负载转移任务,即该任务既可以在移动设备本地执行,也可以在协作服务器端执行。移动负载转移的核心问题是如何使得移动协作应用,一方面可以尽可能地通过远程协作提升执行性能；另一方面又尽可能地减少由于资源可用性变化造成的执行延迟或者失败。例如,减小移动设备到协作服务器之间端到端的带宽波动对数据传输时间的影响,减小服务器负载变化对执行时间的影响等。移动负载转移决策引擎的任务就是根据协作系统的资源可用性和移动应用执行性能要求,动态决定移动协作应用中,每一个可负载转移任务的执行位置。现有的决策引擎多采用“静态决策策略”,采用静态决策策略的决策引擎仅仅在应用执行前启动,为应用的每一个任务选择执行位置后即停止。在应用执行过程中,决策引擎不对协作系统资源可用性变化进行跟踪,不对应用执行进度进行跟踪,不再调整任务执行位置,直至执行完成或者确认失败。静态决策策略缺乏应对资源变化的灵活,可能导致应用执行的延迟、失败,或增加移动设备额外的能量开销。
本文的工作1围绕如何使得移动负载转移决策引擎更加灵活地,自适应地应对协作系统资源可用性的变化,提高决策的准确性,提高应用执行的性能而展开。本文提出“执行路径”的概念描述移动协作应用中各个任务在远程或本地执行的不同组合,采用图论的方法对移动协作应用的执行过程进行建模。采用“应用执行路径图”描述一个移动协作应用各种不同的执行组合以及与之对应的执行路径。决策引擎的任务是根据协作系统资源可用性情况,目标函数(减少执行时间、减少设备能耗等),应用执行性能要求等为应用选择一条最优的执行路径。一方面可以尽可能地有效利用系统资源,提升应用执行性能,同时也尽量减小执行延迟和失败的风险。为了改进“静态决策策略”的不足,本文提出一组“自适应决策策略”,具体而言,本文
1.提出“动态决策策略”。动态决策策略允许决策引擎在应用执行的全过程中,跟踪协作系统资源可用性情况变化和应用执行进度,并且可以根据协作系统资源可用性变化,调整协作应用的执行路径。
2.提出“冗余路径执行”。与现有的“静态决策策略”中,移动协作应用只能采取一条路径执行不同。冗余路径执行允许协作应用同时采用多条执行路径同时执行,最早返回的结果将被使用。同时,决策引擎通过引入概率风险模型,评估因为对协作系统资源可用性估值偏差造成错误决策的概率和相应的风险,辅助应用执行路径、单路径执行或者冗余路径执行方案的选择。
3.提出“联合决策策略”。联合决策策略允许协作服务器一起参与移动设备的负载转移决策过程。移动设备可以共享应用执行的性能要求,如执行完成的时间期限、最低执行结果质量要求等。当协作服务器接收到移动设备的任务数据和执行要求后,可以根据自身负载情况动态调整,如在负载条件允许下,提供更高质量的执行结果等。
4.提出“渐进式数据传输”模式,以减少网络波动对于数据传输的影响。由于在服务器端,计算处理和网络传输通常不会造成资源重叠,渐进式数据传输不会影响应用执行时间。先前数据传递时候的网络带宽测试数据,也可以作为后续传送时,估算传送时间的依据。
评估实验采用移动人脸识别应用(mobile face detection)和移动全景图应用(mobile panorama)作为目标应用。在运行安卓(Android)操作系统的Nexus S智能手机上,分别实现了基于动态决策策略和支持冗余路径执行方案的Wing负载转移决策系统,以及基于联合自适应决策策略和支持渐进式数据传输模式的Mind负载转移决策系统。
评估实验采用控制变量的方法,评估自适应决策策略在应对协作服务器负载波动时的决策质量。实验结果显示,相比静态决策策略,采用单路径执行的动态决策策略可以减少30%(50%)左右的应用执行时间,30%(50%)左右的设备能耗。同时,Wing系统在执行动态决策时候的决策时间开销很小,与采用静态决策策略的时间开销相似。
评估实验采用基于网络Trace数据的模拟实验方法,评估自适应决策策略在应对移动设备到服务器之间端到端网络连接质量波动时的决策质量。网络Trace数据集合包括约2400分钟的WiFi网络Trace数据,涵盖静态应用场景和移动(步行)应用场景,总计约1万多条数据记录(上行带宽、下行带宽、往返时延等),提供了约1万多个决策评估点。实验评估还采用了4种常见的基本网络带宽估值模型。评估结果显示,与静态决策策略相比,采用单路径执行的动态决策策略平均可以降低40-50%的错误决策概率,同时减少30%左右的应用执行时间,40-50%左右的设备能耗。采用冗余路径执行(路径切换时保留原有执行路径的)的动态决策策略平均可以降低30%左右的应用执行时间,降低30%左右的设备能耗。与静态决策策略相比,采用渐进式数据传输模式的联合决策策略,可以降低10-20%的错误决策概率。
Besides light-weight Internet applications, computation-and/or energy-heavy appli-cations are increasingly deployed to mobile devices. However, the limited computation power, battery lifetime and network connectivity make it difficult for mobile devices to become the center of mobile computing. Mobile offloading, or remote execution, between a mobile device and a capable server has proven effective in improving mobile applica-tion's performance.
A mobile collaborative application consists of several tasks, some of which are "of-floadable" that can be offloaded to the collaboration server for execution. Lying at the core of a mobile offloading system is the offload engine that is responsible for determin-ing when and where to execute each task—i.e., locally on the mobile device or remotely on the server—based on resource availability and application's performance requirements. For example, in order for the mobile device to offload a computation-and/or energy-heavy task to the server, its execution state must first be sent to the server, and the execution re-sult should later be returned to the mobile device. Fluctuations in network condition and server workload may affect data transmission time and server response time. The offload engine must thus carefully weigh the expected gain in the device's energy consumption and the task completion time against the cost of network communication.
In the thesis2, collaborative application's execution is modeled with a graph, where the execution is decomposed into different stages which are connected via transaction-s. The execution of an application may take different paths, each of which consumes different amount of time and device energy. The offload engine must select an optimal execution path, balancing between resource availability and performance requirements.
Existing offload decision-making strategies usually assume that resource availability—e.g., network bandwidth and server workload—remains unchanged throughout path exe-cution. This assumption yields non-adaptive offload decisions, which, once determined, remain unchanged until the execution is completed or a failure is detected. However, ac- tual resource availability often exhibits high variability on the time-scale of seconds and also varies with location. The highly variable condition of the underlying resources dic-tates computation and communication costs, possibly causing long application execution delays (even failures) or missing opportunities to improve application performance.
Realizing the impact of resource-availability variations on the application execution performance, the thesis proposes a set of novel adaptive offload decision-making strate-gies, trying to minimize the risk of application execution delays or failures as well as to improve application execution performance and device energy performances by oppor-tunistically exploiting resource-availability improvements, if any. To be more specific, the thesis proposes following contributions.
·Dynamic decision making strategy is proposed to enable offload decision-making at runtime to (re)-evaluate the impact of resource-availability changes on appli-cation performance and then change the execution path accordingly on-the-fly. This enables mobile application's responsive and flexible adaptation to resource-availability variations.
·Redundant execution is proposed to enable application execution using multiple execution paths so as to better explore performance improvement opportunities. Redundant execution enables mobile collaborative application to be executed with two execution paths simultaneously, whichever result comes first is used. Offload engine can also introduce probability-based decision-making approach, account-ing for the risk of incorrect decisions to minimize its impact on application execu-tion.
·Joint decision-making strategy is proposed to enable mobile client to share its execution performance requirements with the server, thus permitting the server to advise on an offload decision.
·Server may also enable incremental delivery of results, so as to reduce the execu-tion delay/failure due to the fluctuating wireless network condition.
The thesis studies the design, implementation of adaptive-decision making strate-gies based mobile offloading systems, Wing and Mind. The thesis evaluates the decision quality of adaptive decision making strategies in coping with server workload variance and network connectivity variance. Wing is based on dynamic decision making strategy and redundant path execution while Mind is based on joint decision making strategy and incremental data delivery mechanism. Two mobile applications, mobile face detection and mobile panorama, are created as target applications for evaluation.
A controlled experiment is designed to evaluate the quality of adaptive decision making strategies in adaptation to collaboration server workload variance. This synthetic experiment is intended to help to understand system's behavior in controlled scenarios rather than precisely emulate actual server workload variance. Our experimental results indicate that Wing can achieve30%(50%) reduction of application execution time and30%(50%) reduction of device energy consumption. The overhead incurred by Wing is trivial, which is within10ms when performing per runtime decision making.
A trace-based emulation experiment is designed to evaluate the quality of adaptive decision making strategies in adaptation to end-to-end network bandwidth fluctuations between mobile device and collaboration server. The use of real-world traces provides experimental repeatability and allows a careful comparison among different strategies. The network trace is collected in the north and central campus of University of Michigan and in Ann Arbor city, covering both stationary scenarios, e.g., offices, public cafeteria and walking scenarios3. The total length of WiFi network trace is around2,400minutes, including over10,000records and decision making points for evaluation. Furthermore, the experiment evaluates the impact of4basic types of most commonly used network bandwidth estimators (Spot, Ody, Avg, Medium) on decision quality. Experiment results show that comparing with non-adaptive decision making strategy, dynamic decision mak-ing strategy with single path execution can reduce incorrect decision rate by an average of40-50%while achieving a30%(40-50%) reduction of application execution time (device energy consumption) over the non-adaptive offload decision-making strategy. With redun-dant path execution, dynamic decision making strategy is able to achieve30%reduction of application execution time and30%reduction of device energy consumption. Evaluation shows that joint decision making strategy with incremental data delivery can reduce in-correct decisions by an average of10-20%over the non-adaptive offload decision-making strategy.
In conclusion, the thesis proposes a set of adaptive decision making strategies to cope with resource dynamics fluctuations in mobile offloading between a mobile device and a collaboration server. As far as is known, this is the first effort trying to address the impact of highly-variable resource availability on the application execution performance. The synthetic experiment and in-depth evaluation based on real-world network traces indicate that comparing with non-adaptive decision making strategy, adaptive decision making strategies can significantly improve application execution performance in terms of execution time and device energy consumption while reducing execution delays and/or failures. The proposed strategies and underlying approaches are applicable not only to mobile offloading but also to other research work where adaptation to resource changes is required to ensure performance.
引文
[1]Satyanarayanan M. Fundamental challenges in mobile computing [C]. In Proceed-ings of the 15th Annual ACM Symposium on Principles of Distributed Computing, New York, NY, USA:1-7.
[2]Heidemann J, Guy R G, Popek G J. Primarily Disconnected Operation:Experi-ences with Ficus [C]. In Proceedings of the 2nd Workshop on the Management of Replicated Data,1992:2-5.
[3]Abowd G D, Mynatt E D. Charting Past, Present and Future Research in Ubiquitous Computing [J]. ACM Transactions on Computer-Human Interaction,2000,7:29-58.
[4]Forman G H, Zahorjan J. The Challenges of Mobile Computing [J]. Computer, 1994,27 (4):38-47.
[5]Duchamp D. Issues in Wireless Mobile Computing [C]. In Proceedings of 3rd Workshop on Workstation Operating Systems,1992:2-10.
[6]Imielinski T, Badrinath B R. Mobile Wireless Computing:Challenges in Data Man-agement [J]. Communications of the ACM,1994,37:18-28.
[7]Nimmagadda Y, Kumar K, Lu Y-H, et al. Real-time moving object recognition and tracking using computation offloading [C]. In Proceedings of IEEE/RSJ Interna-tional Conference on Intelligent Robots and Systems (IROS),2010:2449-2455.
[8]Benjamin S. The Android mobile platform [D]. Eastern Michigan University,2008.
[9]Kemp R, Palmer N, Kielmann T, et al. Cuckoo:a computation offloading frame-work for smartphones [C]. In Proceeding of the 2nd International Conference on Mobile Computing, Applications, and Services, MobiCASE'10,2010.
[10]Bahl V. Cloud in the palm of your hands [C]. In the Twelfth Microsoft Research Faculty Summit, Redmond, Washington, United States, July 18-20,2011.
[11]Canalyslnc. Smartphone Market Analysis 2011 [R].2011.
[12]Butler M. Android:Changing the Mobile Landscape [J]. IEEE Pervasive Comput-ing,2011:4-7.
[13]Burnette E. Hello, Android:introducing Google's mobile development platform [M]. Pragmatic Bookshelf,2009.
[14]Pascale P, Pulec V. Android UI Patterns [R].2011.
[15]Cisco VNI:Forecast and Methodology,2010-2015 [R].2011.7.
[16]Cisco Visual Networking Index:Global Mobile Data Traffic Forecast Update, 2011-2016 [R].2011.7.
[17]Satyanarayanan M. Mobile computing:the next decade [C]. In Proceedings of the 1st ACM Workshop on Mobile Cloud Computing, New York, NY, USA,2010: 5:1-5:6.
[18]Dianxi S, et al. Mobile computing and its developement trend [R]. Infobus,2011.
[19]Magnus Dahlen E F. Energy storage technology and market trend [C].2010.
[20]Shearer F. Power management in mobile devices [M]. Newnes,2007.
[21]China Unicom. Wireless Technology Comparison [R].2008.
[22]PROXIM Wireless. Mobile Data Offloading through WiFi [R].2011.
[23]Mobile Broadband:The Benefits of Additional Spectrum [R]. Federal Communi-cations Commission USA,2010.
[24]Kumar K, Lu Y. Cloud computing for mobile users:Can offloading computation save energy? [J]. Computer,2010,43 (4):51-56.
[25]Kumar K, Liu J, Lu Y-H, et al. A Survey of Computation Offloading for Mobile Systems [J]. Mobile Networks and Applications:1-12.
[26]Gu X, Nahrstedt K, Messer A, et al. Adaptive Offloading Inference for Delivering Applications in Pervasive Computing Environments [C]. In Proceedings of IEEE International Conference on Pervasive Computing and Communications (PerCom 2003), Dallas-Fort,2003:107.
[27]Messer A, Greenberg I, Bernadat P, et al. Towards a Distributed Platform for Resource-Constrained Devices [C]. In Proceedings of the 22nd International Con-ference on Distributed Computing Systems (ICDCS'02), Washington, DC, USA, 2002:43-
[28]Chen G, Kang B-T, Kandemir M, et al. Studying Energy Trade Offs in Offloading Computation/Compilation in Java-Enabled Mobile Devices [J]. IEEE Transactions on Parallel and Distributed Systems 2004,15 (9):795-809.
[29]Hong Y-J, Kumar K, Lu Y-H. Energy Efficient Content-based Image Retrieval for Mobile Systems [C]. In Proceedings of IEEE International Symposium on Circuits and Systems,2009:1673-1676.
[30]Li Z, Wang C, Xu R. Computation offloading to save energy on handheld devices: a partition scheme [C]. In Proceedings of the 2001 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems, New York, NY, USA,2001:238-246.
[31]Li Z, Wang C, Xu R. Task Allocation for Distributed Multimedia Processing on Wirelessly Networked Handheld Devices [C]. In Proceedings of the 16th Inter-national Parallel and Distributed Processing Symposium, Washington, DC, USA, 2002:312-318.
[32]Ou S, Yang K, Liotta A. An Adaptive Multi-Constraint Partitioning Algorithm for Offloading in Pervasive Systems [C]. In Proceedings of the 4th Annual IEEE Inter-national Conference on Pervasive Computing and Communications,13-17 March 2006:116-125.
[33]Wang C, Li Z. Parametric analysis for adaptive computation offloading [C]. In Pro-ceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation, New York, NY, USA,2004:119-130.
[34]Kremer U, Hicks J, Rehg J. A compilation framework for power and energy man-agement on mobile computers [C]. In Proceedings of the 14th International Con-ference on Languages and Compilers for Parallel Computing, Berlin, Heidelberg, 2003:115-131.
[35]Flinn J, Narayanan D, Satyanarayanan M. Self-tuned remote execution for per-vasive computing [C]. In Hot Topics in Operating Systems (HotOS-VIII),2001: 61-66.
[36]Flinn J, Park S, Satyanarayanan M. Balancing Performance, Energy, and Quality in Pervasive Computing [C]. In Proceedings of The 22nd International Conference on Distributed Computing System,2002:217-226.
[37]Cuervo E, Balasubramanian A, ki Cho D, et al. MAUI:making smartphones last longer with code offload [C]. In Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services,2010:49-62.
[38]Flinn J, Satyanarayanan M. Energy-aware adaptation for mobile applications [J]. SIGOPS Operating Systems Review,1999,33 (5):48-63.
[39]Balan R K, Satyanarayanan M, Park S Y, et al. Tactics-based remote execution for mobile computing [C]. In Proceedings of the 2nd International Conference on Mobile Systems, Applications, and Services, New York, NY, USA,2003:273-286.
[40]Balan R, Flinn J, Satyanarayanan M, et al. The Case For Cyber Foraging [C]. In the 10th ACM SIGOPS European Workshop,2002:87-92.
[41]Pathak A, Hu C, Zhang M, et al. Enabling Automatic Offloading of Resource-Intensive Smartphone Applications [R]. Purdue university technical report,2010.
[42]Giurgiu I, Riva O, Juric D, et al. Calling the cloud:enabling mobile phones as in-terfaces to cloud applications [C]. In Proceedings of the ACM/IFIP/USENIX 10th International Conference on Middleware, Urbana, IL, USA,2009:83-102.
[43]Rellermeyer J S, Alonso G, Roscoe T. R-OSGi:distributed applications through software modularization [C]. In Proceedings of the ACM/IFIP/USENIX 8th Inter-national Conference on Middleware, New York, NY, USA,2007:1-20.
[44]The OSGi Alliance. OSGi Service Platform Core Specification [R].2012.
[45]Gember A, Akella A. Mobile Device Offloading Using Enterprise Network and Cloud [R]. University of Wisconsin-Madison,2010.
[46]Chu T, et al. Build panoramas on Android phones [R]. Stanford technical report, 2010.
[47]Noble B D, Satyanarayanan M, Narayanan D, et al. Agile application-aware adap-tation for mobility [C]. In Proceedings of the 16th ACM Symposium on Operating Systems Principles, New York, NY, USA,1997:276-287.
[48]Noble B, Satyanarayanan M. Experience with Adaptive Mobile Applications in Odyssey [J]. Mobile Networks and Applications,1999,4 (4):245-254.
[49]Noble B, Price M, Satyanarayanan M. A Programming Interface for Application-Aware Adaptation in Mobile Computing [J]. Computing Systems,1995,8 (4): 345-363.
[50]Jul E, Levy H, Hutchinson N, et al. Fine-grained mobility in the Emerald system [J]. ACM Transactions on Computer Systems,1988,6:109-133.
[51]Birrell A, Nelson G, Owicki S, et al. Network objects [J]. SIGOPS Operating Sys-tem Review,1993,27:217-230.
[52]Cardelli L. A language with distributed scope [C]. In Proceedings of the 22nd ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages, New York, NY, USA,1995:286-297.
[53]Joseph A D, de Lespinasse A F, Tauber J A, et al. Rover:a toolkit for mobile information access [J]. SIGOPS Operating System Review,1995,29:156-171.
[54]Zhang X, Kunjithapatham A, Jeong S, et al. Towards an Elastic Application Model for Augmenting the Computing Capabilities of Mobile Devices with Cloud Com-puting [J]. MOBILE NETWORKS and APPLICATIONS,2011,16:270-284.
[55]Zhang X, Jeong S, Kunjithapatham A, et al. Towards an elastic application model for augmenting computing capabilities of mobile platforms [J]. Mobile Wireless Middleware, Operating Systems, and Applications,2010:161-174.
[56]Zhang X, Schiffman J, Gibbs S, et al. Securing elastic applications on mobile de-vices for cloud computing [C]. In Proceedings of the ACM Workshop on Cloud Computing Security,2009:127-134.
[57]Rong P, Pedram M. Extending the lifetime of a network of battery-powered mo-bile devices by remote processing:a markovian decision-based approach. [C]. In Proceedings of the 40th annual Design Automation Conference,2003:906-911.
[58]Cenepa, Huerta G, Dongman L. An Adaptable Application Offloading Scheme Based on Application Behavior. [C]. In Proceedings of the IEEE 20th Interna-tional Conference on Advanced Information Networking and Application,2008: 387-392.
[59]Gurun S, Wolski R, Krintz C, et al. On the Efficacy of Computation Offloading Decision-Making Strategies [J]. International Journal of High Performance Com-puting Applications,2008,22 (4):460-479.
[60]Wolski R, Gurun S, Krintz R, et al. Using bandwidth data to make computation of-floading decisions [C]. In Proceedings of the International Parallel and Distributed Processing Symposium, High-Performance Grid Computing Workshop,2008.
[61]Goyal S, Carter J. A Lightweight Secure Cyber Foraging Infrastructure for Resource-Constrained Devices [C]. In Proceedings of the 6th IEEE Workshop on Mobile Computing Systems and Applications, Washington, DC,USA,2004:186-195.
[62]Guan T, Zaluska E, De Roure D. A Grid Service Infrastructure for Mobile Devices [C]. In Proceedings of the First International Conference on Semantics, Knowledge and Grid, Washington, DC, USA,2005:42-
[63]Guan T, Zaluska E, De Roure D. Extending Pervasive Devices with the Semantic Grid:A Service Infrastructure Approach [C]. In Proceedings of the 6th IEEE Inter-national Conference on Computer and Information Technology, Washington, DC, USA,2006:113-
[64]Hemmes J, Poellabauer C, Thain D. On-Demand Transient Data Storage and Back-up in Mobile Systems [C]. In Proceedings of Military Communications Confer-ence,2007.
[65]Jamwal V, Iyer S. Automated Refactoring of Objects for Application Partitioning [C]. In Proceedings of the 12th Asia-Pacific Software Engineering Conference, Washington, DC, USA,2005:671-678.
[66]Seshasayee B, Nathuji R, Schwan K. Energy-aware mobile service overlays:Co-operative dynamic power management in distributed mobile systems [C]. In Pro-ceedings of the 4th IEEE International Conference on Autonomic Computing, Jacksonville, Florida, USA, June 11-15,2007
[67]Ou S, Yang K, Zhang J. An effective offloading middleware for pervasive services on mobile devices [J]. Pervasive Mob. Comput.,2007,3 (4):362-385.
[68]Weinsberg Y, Dolev D, Wyckoff P, et al. Accelerating distributed computing appli-cations using a network offloading framework [C]. IEEE International Parallel and Distributed Processing Symposium,2007,1-10.
[69]Rim H, Kim S, Kim Y, et al. Transparent Method Offloading for Slim Execution [C]. In Proceedings of 1st International Symposium on Wireless Pervasive Com-puting,2006.
[70]Xian C, Lu Y-H, Li Z. Adaptive computation offloading for energy conservation on battery-powered systems [C]. In Proceedings of the 13th International Conference on Parallel and Distributed Systems-Volume 01, Washington, DC, USA,2007: 1-8.
[71]Cidon A, London T, Katti S, et al. MARS:adaptive remote execution for multi-threaded mobile devices [C]. In Proceedings of the 3rd ACM SOSP Workshop on Networking, Systems, and Applications on Mobile Handhelds,2011:1-6.
[72]Chun B-G, Ihm S, Maniatis P, et al. CloneCloud:elastic execution between mobile device and cloud [C]. In Proceedings of the 6th conference on Computer systems, New York, NY, USA,2011:301-314.
[73]Gu T, Pung H K, Zhang D Q. A service-oriented middleware for building context-aware services [J]. Journal of Network and Computer Applications,2005,28:1-18.
[74]Chun B, Maniatis P. Dynamically partitioning applications between weak devices and clouds [C]. In Proceedings of the 1st ACM Workshop on Mobile Cloud Com-puting & Services:Social Networks and Beyond,2010:7.
[75]Satyanarayanan M, Bahl P, Caceres R, et al. The Case for VM-Based Cloudlets in Mobile Computing [J]. IEEE Pervasive Computing,2009,8:14-23.
[76]Kosta S, Aucinas A, Hui P, et al. Unleashing the Power of Mobile Cloud Computing using ThinkAir [R]. Technical report, Deutsche Telekom Labs, Berlin, Germany, 2011.
[77]Kosta, Aucinas S, Hui A, et al. ThinkAir:Dynamic resource allocation and parallel execution in the cloud for mobile code offloading [C]. In Proceedings of the 31th conference on Information Communications, Piscataway, NJ, USA,2012.
[78]Clark C, Fraser K, Hand S, et al. Live migration of virtual machines [C]. In Pro-ceedings of the 2nd conference on Symposium on Networked Systems Design & Implementation-Volume 2, Berkeley, CA, USA,2005:273-286.
[79]Chen G, Kang B, Kandemir M, et al. Energy-aware compilation and execution in Java-enabled mobile devices [C]. Proceedings of the 17th International Symposium on Parallel and Distributed Processing, Washington, DC, USA,2003.
[80]Chen G, Kang B, Kandemir M, et al. Studying energy trade offs in offloading com-putation/compilation in Java-enabled mobile devices [J]. IEEE Transactions on Par-allel and Distributed Systems,2004,15 (9):795-809.
[81]Zhao B, Xu Z, Chi C, et al. Mirroring smartphones for good:A feasibility study [J]. ZTE Communications,2011,9 (1):9-14.
[82]Guo Y, Zhang L, Kong J, et al. Jupiter:transparent augmentation of smartphone capabilities through cloud computing [C]. In Proceedings of the 3rd ACM SOSP Workshop on Networking, Systems, and Applications on Mobile Handhelds, New York, NY, USA,2011:2:1-2:6.
[83]Narayanan D, Satyanarayanan M. Predictive Resource Management for Wearable Computing [C]. In Proceedings of the 1st International Conference on Mobile Sys-tems, Applications, and Services,2003.
[84]Bradski G, Kaehler A. Learning OpenCV:Computer vision with the OpenCV li-brary [M]. O'Reilly Media,2008.
[85]Breslau L, Estrin D, Fall K, et al. Advances in Network Simulation [J]. Computer, 2000,33 (5):59-67.
[86]Paxson V, Floyd S. Wide-area traffic:the failure of Poisson modeling [C]. In Pro-ceedings of the Conference on Communications Architectures, Protocols and Ap-plications, New York, NY, USA,1994:257-268.
[87]Willinger W, Taqqu M S, Sherman R, et al. Self-similarity through high-variability: statistical analysis of Ethernet LAN traffic at the source level [J]. IEEE/ACM Trans-action on Networking,1997,5 (1):71-86.
[88]Kim M, Noble B. Mobile network estimation [C]. In Proceedings of the 7th Annual International Conference on Mobile Computing and Networking, New York, NY, USA,2001:298-309.
[89]Wolski R, Spring N T, Hayes J. The Network Weather Service:A Distributed Re-source Performance Forecasting Service for Metacomputing [J]. Journal of Future Generation Computing Systems,1999,15:757-768.
[90]Gurun S, Krintz C, Wolski R. NWSLite:a light-weight prediction utility for mo-bile devices [C]. In Proceedings of the 2nd International Conference on Mobile Systems, Applications, and Services, New York, NY, USA,2004:2-11.
[91]Dong M, Zhong L. Self-constructive high-rate system energy modeling for battery-powered mobile systems [C]. In Proceedings of the 9th International Conference on Mobile systems, Applications, and Services, New York, NY, USA,2011:335-348.
[92]Dong M, Zhong L. Demo:sesame:self-constructive system energy modeling for battery-powered mobile systems [C]. In Proceedings of the 9th International Con-ference on Mobile Systems, Applications, and Services, New York, NY, USA, 2011:373-374.
[93]Vallina-Rodriguez N, Crowcroft J. Energy Management Techniques in Modern Mobile Handsets [J]. Communications Surveys & Tutorials, IEEE:1-20.
[94]Shye A, Scholbrock B, Memik G. Into the wild:studying real user activity pat-terns to guide power optimizations for mobile architectures [C]. In Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture, New York, NY, USA,2009:168-178.
[95]Fan X, Weber W-D, Barroso L A. Power provisioning for a warehouse-sized com-puter [C]. In Proceedings of the 34th Annual International Symposium on Com-puter Architecture, New York, NY, USA,2007:13-23.
[96]Pathak A, Hu Y C, Zhang M, et al. Fine-grained power modeling for smartphones using system call tracing [C]. In Proceedings of the Sixth Conference on Computer Systems, New York, NY, USA,2011:153-168.
[97]Dong M, Zhong L. Self-constructive high-rate system energy modeling for battery-powered mobile systems [C]. In Proceedings of the 9th International Conference on Mobile Systems, Applications, and Services, New York, NY, USA,2011:335-348.
[98]Vallina-Rodriguez N, Hui P, Crowcroft J, et al. Exhausting battery statistics:un-derstanding the energy demands on mobile handsets [C]. In Proceedings of the second ACM SIGCOMM Workshop on Networking, Systems, and Applications on Mobile Handhelds, New York, NY, USA,2010:9-14.
[99]Falaki H, Mahajan R, Kandula S, et al. Diversity in smartphone usage [C]. In Pro-ceedings of the 8th International Conference on Mobile Systems, Applications, and Services, New York, NY, USA,2010:179-194.
[100]Zhang L, Tiwana B, Dick R, et al. Accurate online power estimation and automatic battery behavior based power model generation for smartphones [C]. In Proceed-ings of the 8th IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis,2010:105-114.
[101]Balasubramanian N, Balasubramanian A, Venkataramani A. Energy consumption in mobile phones:a measurement study and implications for network applications [C]. In Proceedings of the 9th ACM SIGCOMM Conference on Internet Measure-ment Conference,Scottsdale, Arizona, USA,2009:280-293.
[102]Schulman A, Schmid T, Dutta P, et al. Demo:Phone Power Monitoring with BattOr [R]. Demo of the 17th Annual International Conference on Mobile Computing and Networking, Las Vegas, Nevada, USA, September 19-23,2011.
[103]Vallina-Rodriguez N, Hui P, Crowcroft J, et al. Exhausting battery statistics:un-derstanding the energy demands on mobile handsets [C]. In Proceedings of the 2nd ACM SIGCOMM Workshop on Networking, Systems, and Applications on Mobile Handhelds, New York, NY, USA,2010:9-14.
[104]Ferreira D, Dey A, Kostakos V. Understanding human-smartphone concerns:a s-tudy of battery life [J]. Pervasive Computing,2011:19-33.
[105]Qian F, Wang Z, Gerber A, et al. Characterizing radio resource allocation for 3G networks [C]. In Proceedings of the 10th Annual Conference on Internet Measure-ment, New York, NY, USA,2010:137-150.
[106]Liu H, Zhang Y, Zhou Y. TailTheft:leveraging the wasted time for saving energy in cellular communications [C]. In Proceedings of the 6th International Workshop on MobiArch,2011:31-36.
[107]Ristanovic N, Le Boudec J-Y, Chaintreau A, et al. Energy Efficient Offloading of 3G Networks [C]. In Proceedings of the 2011 IEEE 8th International Conference on Mobile Ad-Hoc and Sensor Systems, Washington, DC, USA,2011:202-211.
[108]Wang L, Manner J. Energy Consumption Analysis of WLAN,2G and 3G interfaces [C]. In Proceedings of the 2010 IEEE/ACM International Conference on Green Computing and Communications & International Conference on Cyber, Physical and Social Computing, Washington, DC, USA,2010:300-307.
[109]Peng C, Lee S-B, Lu S, et al. Traffic-driven power saving in operational 3G cellu-lar networks [C]. In Proceedings of the 17th Annual International Conference on Mobile Computing and Networking, New York, NY, USA,2011:121-132.
[110]Ra M-R, Paek J, Sharma A B, et al. Energy-delay tradeoffs in smartphone applica-tions [C]. In Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services, New York, NY, USA,2010:255-270.
[111]Sklavos N, Touliou K. A System Level Analysis of Power Consumption and Opti-mization in 3G Mobile Devices [C]. In Proceedings of the 1st Intenational Confer-ence on New Technologies, Mobility, and Security,2007.
[112]Narayanan D, Flinn J, Satyanarayanan M. Using History to Improve Mobile Ap-plication Adaptation [C]. In Proceedings Of The 3rd IEEE Workshop On Mobile Computing Systems And Applications, New York, NY, USA,2000:30-41.
[113]Liang R, et al. A Survey of Human Face Detection [J]. Chinese Journal of Com-puters,2002:141-146.
[114]Bradski G. The opencv library [J]. Doctor Dobbs Journal,2000,25 (11):120-126.
[115]Savage S. Sting:A TCP-based Network Measurement Tool [C]. In USENIX Sym-posium on Internet Technologies and Systems,1999.
[116]Prasad R, Dovrolis C, Murray M, et al. Bandwidth estimation:metrics, measure-ment techniques, and tools [J]. Network, IEEE,2003,17 (6):27-35.
[117]Jain M, Dovrolis C. End-to-end available bandwidth:measurement methodology, dynamics, and relation with TCP throughput [J]. IEEE/ACM Transaction on Net-working,2003,11 (4):537-549.
[118]Zhang D-Y, Hu M-Z, Fang D-H. Analysis and evaluation of link capacity esti-mation tools [C]. In Proceedings of the 4th WSEAS International Conference on Electronics, Control and Signal Processing, Stevens Point, Wisconsin, USA,2005: 175-180.
[119]Kalyanaraman R S, Xiao Y, Yla-Jaaski A. Network Prediction for Adaptive Mobile Applications [C]. In Proceedings of the 3rd International Conference on Mobile U-biquitous Computing, Systems, Services and Technologies, Washington, DC, US-A,2009:141-146.
[120]Nicholson A J, Noble B D. BreadCrumbs:forecasting mobile connectivity [C]. In Proceedings of the 14th ACM International Conference on Mobile computing and Networking, New York, NY, USA,2008:46-57.
[121]Guo S. Android Power Management [R].2010.
[122]Terrenghi L, Lang T, Lehner B. Elastic mobility:stretching interaction [C]. In Proceedings of the 11 th International Conference on Human-Computer Interaction with Mobile Devices and Services, New York, NY, USA,2009:46:1-46:4.
[123]Higgins B D, Reda A, Alperovich T, et al. Intentional networking:opportunistic exploitation of mobile network diversity [C]. In Proceedings of the 16th Annual International Conference on Mobile Computing and Networking, New York, NY, USA,2010:73-84.
[124]Microsoft. Windows Remote Management Specification, v1.1 [R].2008.
[125]Narayanan D, Satyanarayanan M. Predictive Resource Management for Wearable Computing [C]. New York, NY, USA,2003:113-128.
[126]CSDN. Introduction of JPEG Coding Technique [R].
[127]Walther P. Adaptiver Chariot Server [D]. Institute for Computer Systems, ETH Zurich,1997.
[128]Chandra S, Ellis C S. JPEG compression metric as a quality-aware image transcod-ing [C]. In Proceedings of the 2nd Conference on USENIX Symposium on Internet Technologies and Systems-Volume 2, Berkeley, CA, USA,1999:8-8.
[129]Bolliger J. A framework for network-aware applications [D]. Swiss Federal Insti-tute of Technology Zurich,2000.
[130]Marinelli E. Hyrax:cloud computing on mobile devices using MapReduce [D]. School of Computer Science, Carnegie Mellon University,2009.
[2]Heidemann J, Guy R G, Popek G J. Primarily Disconnected Operation:Experi-ences with Ficus [C]. In Proceedings of the 2nd Workshop on the Management of Replicated Data,1992:2-5.
[3]Abowd G D, Mynatt E D. Charting Past, Present and Future Research in Ubiquitous Computing [J]. ACM Transactions on Computer-Human Interaction,2000,7:29-58.
[4]Forman G H, Zahorjan J. The Challenges of Mobile Computing [J]. Computer, 1994,27 (4):38-47.
[5]Duchamp D. Issues in Wireless Mobile Computing [C]. In Proceedings of 3rd Workshop on Workstation Operating Systems,1992:2-10.
[6]Imielinski T, Badrinath B R. Mobile Wireless Computing:Challenges in Data Man-agement [J]. Communications of the ACM,1994,37:18-28.
[7]Nimmagadda Y, Kumar K, Lu Y-H, et al. Real-time moving object recognition and tracking using computation offloading [C]. In Proceedings of IEEE/RSJ Interna-tional Conference on Intelligent Robots and Systems (IROS),2010:2449-2455.
[8]Benjamin S. The Android mobile platform [D]. Eastern Michigan University,2008.
[9]Kemp R, Palmer N, Kielmann T, et al. Cuckoo:a computation offloading frame-work for smartphones [C]. In Proceeding of the 2nd International Conference on Mobile Computing, Applications, and Services, MobiCASE'10,2010.
[10]Bahl V. Cloud in the palm of your hands [C]. In the Twelfth Microsoft Research Faculty Summit, Redmond, Washington, United States, July 18-20,2011.
[11]Canalyslnc. Smartphone Market Analysis 2011 [R].2011.
[12]Butler M. Android:Changing the Mobile Landscape [J]. IEEE Pervasive Comput-ing,2011:4-7.
[13]Burnette E. Hello, Android:introducing Google's mobile development platform [M]. Pragmatic Bookshelf,2009.
[14]Pascale P, Pulec V. Android UI Patterns [R].2011.
[15]Cisco VNI:Forecast and Methodology,2010-2015 [R].2011.7.
[16]Cisco Visual Networking Index:Global Mobile Data Traffic Forecast Update, 2011-2016 [R].2011.7.
[17]Satyanarayanan M. Mobile computing:the next decade [C]. In Proceedings of the 1st ACM Workshop on Mobile Cloud Computing, New York, NY, USA,2010: 5:1-5:6.
[18]Dianxi S, et al. Mobile computing and its developement trend [R]. Infobus,2011.
[19]Magnus Dahlen E F. Energy storage technology and market trend [C].2010.
[20]Shearer F. Power management in mobile devices [M]. Newnes,2007.
[21]China Unicom. Wireless Technology Comparison [R].2008.
[22]PROXIM Wireless. Mobile Data Offloading through WiFi [R].2011.
[23]Mobile Broadband:The Benefits of Additional Spectrum [R]. Federal Communi-cations Commission USA,2010.
[24]Kumar K, Lu Y. Cloud computing for mobile users:Can offloading computation save energy? [J]. Computer,2010,43 (4):51-56.
[25]Kumar K, Liu J, Lu Y-H, et al. A Survey of Computation Offloading for Mobile Systems [J]. Mobile Networks and Applications:1-12.
[26]Gu X, Nahrstedt K, Messer A, et al. Adaptive Offloading Inference for Delivering Applications in Pervasive Computing Environments [C]. In Proceedings of IEEE International Conference on Pervasive Computing and Communications (PerCom 2003), Dallas-Fort,2003:107.
[27]Messer A, Greenberg I, Bernadat P, et al. Towards a Distributed Platform for Resource-Constrained Devices [C]. In Proceedings of the 22nd International Con-ference on Distributed Computing Systems (ICDCS'02), Washington, DC, USA, 2002:43-
[28]Chen G, Kang B-T, Kandemir M, et al. Studying Energy Trade Offs in Offloading Computation/Compilation in Java-Enabled Mobile Devices [J]. IEEE Transactions on Parallel and Distributed Systems 2004,15 (9):795-809.
[29]Hong Y-J, Kumar K, Lu Y-H. Energy Efficient Content-based Image Retrieval for Mobile Systems [C]. In Proceedings of IEEE International Symposium on Circuits and Systems,2009:1673-1676.
[30]Li Z, Wang C, Xu R. Computation offloading to save energy on handheld devices: a partition scheme [C]. In Proceedings of the 2001 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems, New York, NY, USA,2001:238-246.
[31]Li Z, Wang C, Xu R. Task Allocation for Distributed Multimedia Processing on Wirelessly Networked Handheld Devices [C]. In Proceedings of the 16th Inter-national Parallel and Distributed Processing Symposium, Washington, DC, USA, 2002:312-318.
[32]Ou S, Yang K, Liotta A. An Adaptive Multi-Constraint Partitioning Algorithm for Offloading in Pervasive Systems [C]. In Proceedings of the 4th Annual IEEE Inter-national Conference on Pervasive Computing and Communications,13-17 March 2006:116-125.
[33]Wang C, Li Z. Parametric analysis for adaptive computation offloading [C]. In Pro-ceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation, New York, NY, USA,2004:119-130.
[34]Kremer U, Hicks J, Rehg J. A compilation framework for power and energy man-agement on mobile computers [C]. In Proceedings of the 14th International Con-ference on Languages and Compilers for Parallel Computing, Berlin, Heidelberg, 2003:115-131.
[35]Flinn J, Narayanan D, Satyanarayanan M. Self-tuned remote execution for per-vasive computing [C]. In Hot Topics in Operating Systems (HotOS-VIII),2001: 61-66.
[36]Flinn J, Park S, Satyanarayanan M. Balancing Performance, Energy, and Quality in Pervasive Computing [C]. In Proceedings of The 22nd International Conference on Distributed Computing System,2002:217-226.
[37]Cuervo E, Balasubramanian A, ki Cho D, et al. MAUI:making smartphones last longer with code offload [C]. In Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services,2010:49-62.
[38]Flinn J, Satyanarayanan M. Energy-aware adaptation for mobile applications [J]. SIGOPS Operating Systems Review,1999,33 (5):48-63.
[39]Balan R K, Satyanarayanan M, Park S Y, et al. Tactics-based remote execution for mobile computing [C]. In Proceedings of the 2nd International Conference on Mobile Systems, Applications, and Services, New York, NY, USA,2003:273-286.
[40]Balan R, Flinn J, Satyanarayanan M, et al. The Case For Cyber Foraging [C]. In the 10th ACM SIGOPS European Workshop,2002:87-92.
[41]Pathak A, Hu C, Zhang M, et al. Enabling Automatic Offloading of Resource-Intensive Smartphone Applications [R]. Purdue university technical report,2010.
[42]Giurgiu I, Riva O, Juric D, et al. Calling the cloud:enabling mobile phones as in-terfaces to cloud applications [C]. In Proceedings of the ACM/IFIP/USENIX 10th International Conference on Middleware, Urbana, IL, USA,2009:83-102.
[43]Rellermeyer J S, Alonso G, Roscoe T. R-OSGi:distributed applications through software modularization [C]. In Proceedings of the ACM/IFIP/USENIX 8th Inter-national Conference on Middleware, New York, NY, USA,2007:1-20.
[44]The OSGi Alliance. OSGi Service Platform Core Specification [R].2012.
[45]Gember A, Akella A. Mobile Device Offloading Using Enterprise Network and Cloud [R]. University of Wisconsin-Madison,2010.
[46]Chu T, et al. Build panoramas on Android phones [R]. Stanford technical report, 2010.
[47]Noble B D, Satyanarayanan M, Narayanan D, et al. Agile application-aware adap-tation for mobility [C]. In Proceedings of the 16th ACM Symposium on Operating Systems Principles, New York, NY, USA,1997:276-287.
[48]Noble B, Satyanarayanan M. Experience with Adaptive Mobile Applications in Odyssey [J]. Mobile Networks and Applications,1999,4 (4):245-254.
[49]Noble B, Price M, Satyanarayanan M. A Programming Interface for Application-Aware Adaptation in Mobile Computing [J]. Computing Systems,1995,8 (4): 345-363.
[50]Jul E, Levy H, Hutchinson N, et al. Fine-grained mobility in the Emerald system [J]. ACM Transactions on Computer Systems,1988,6:109-133.
[51]Birrell A, Nelson G, Owicki S, et al. Network objects [J]. SIGOPS Operating Sys-tem Review,1993,27:217-230.
[52]Cardelli L. A language with distributed scope [C]. In Proceedings of the 22nd ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages, New York, NY, USA,1995:286-297.
[53]Joseph A D, de Lespinasse A F, Tauber J A, et al. Rover:a toolkit for mobile information access [J]. SIGOPS Operating System Review,1995,29:156-171.
[54]Zhang X, Kunjithapatham A, Jeong S, et al. Towards an Elastic Application Model for Augmenting the Computing Capabilities of Mobile Devices with Cloud Com-puting [J]. MOBILE NETWORKS and APPLICATIONS,2011,16:270-284.
[55]Zhang X, Jeong S, Kunjithapatham A, et al. Towards an elastic application model for augmenting computing capabilities of mobile platforms [J]. Mobile Wireless Middleware, Operating Systems, and Applications,2010:161-174.
[56]Zhang X, Schiffman J, Gibbs S, et al. Securing elastic applications on mobile de-vices for cloud computing [C]. In Proceedings of the ACM Workshop on Cloud Computing Security,2009:127-134.
[57]Rong P, Pedram M. Extending the lifetime of a network of battery-powered mo-bile devices by remote processing:a markovian decision-based approach. [C]. In Proceedings of the 40th annual Design Automation Conference,2003:906-911.
[58]Cenepa, Huerta G, Dongman L. An Adaptable Application Offloading Scheme Based on Application Behavior. [C]. In Proceedings of the IEEE 20th Interna-tional Conference on Advanced Information Networking and Application,2008: 387-392.
[59]Gurun S, Wolski R, Krintz C, et al. On the Efficacy of Computation Offloading Decision-Making Strategies [J]. International Journal of High Performance Com-puting Applications,2008,22 (4):460-479.
[60]Wolski R, Gurun S, Krintz R, et al. Using bandwidth data to make computation of-floading decisions [C]. In Proceedings of the International Parallel and Distributed Processing Symposium, High-Performance Grid Computing Workshop,2008.
[61]Goyal S, Carter J. A Lightweight Secure Cyber Foraging Infrastructure for Resource-Constrained Devices [C]. In Proceedings of the 6th IEEE Workshop on Mobile Computing Systems and Applications, Washington, DC,USA,2004:186-195.
[62]Guan T, Zaluska E, De Roure D. A Grid Service Infrastructure for Mobile Devices [C]. In Proceedings of the First International Conference on Semantics, Knowledge and Grid, Washington, DC, USA,2005:42-
[63]Guan T, Zaluska E, De Roure D. Extending Pervasive Devices with the Semantic Grid:A Service Infrastructure Approach [C]. In Proceedings of the 6th IEEE Inter-national Conference on Computer and Information Technology, Washington, DC, USA,2006:113-
[64]Hemmes J, Poellabauer C, Thain D. On-Demand Transient Data Storage and Back-up in Mobile Systems [C]. In Proceedings of Military Communications Confer-ence,2007.
[65]Jamwal V, Iyer S. Automated Refactoring of Objects for Application Partitioning [C]. In Proceedings of the 12th Asia-Pacific Software Engineering Conference, Washington, DC, USA,2005:671-678.
[66]Seshasayee B, Nathuji R, Schwan K. Energy-aware mobile service overlays:Co-operative dynamic power management in distributed mobile systems [C]. In Pro-ceedings of the 4th IEEE International Conference on Autonomic Computing, Jacksonville, Florida, USA, June 11-15,2007
[67]Ou S, Yang K, Zhang J. An effective offloading middleware for pervasive services on mobile devices [J]. Pervasive Mob. Comput.,2007,3 (4):362-385.
[68]Weinsberg Y, Dolev D, Wyckoff P, et al. Accelerating distributed computing appli-cations using a network offloading framework [C]. IEEE International Parallel and Distributed Processing Symposium,2007,1-10.
[69]Rim H, Kim S, Kim Y, et al. Transparent Method Offloading for Slim Execution [C]. In Proceedings of 1st International Symposium on Wireless Pervasive Com-puting,2006.
[70]Xian C, Lu Y-H, Li Z. Adaptive computation offloading for energy conservation on battery-powered systems [C]. In Proceedings of the 13th International Conference on Parallel and Distributed Systems-Volume 01, Washington, DC, USA,2007: 1-8.
[71]Cidon A, London T, Katti S, et al. MARS:adaptive remote execution for multi-threaded mobile devices [C]. In Proceedings of the 3rd ACM SOSP Workshop on Networking, Systems, and Applications on Mobile Handhelds,2011:1-6.
[72]Chun B-G, Ihm S, Maniatis P, et al. CloneCloud:elastic execution between mobile device and cloud [C]. In Proceedings of the 6th conference on Computer systems, New York, NY, USA,2011:301-314.
[73]Gu T, Pung H K, Zhang D Q. A service-oriented middleware for building context-aware services [J]. Journal of Network and Computer Applications,2005,28:1-18.
[74]Chun B, Maniatis P. Dynamically partitioning applications between weak devices and clouds [C]. In Proceedings of the 1st ACM Workshop on Mobile Cloud Com-puting & Services:Social Networks and Beyond,2010:7.
[75]Satyanarayanan M, Bahl P, Caceres R, et al. The Case for VM-Based Cloudlets in Mobile Computing [J]. IEEE Pervasive Computing,2009,8:14-23.
[76]Kosta S, Aucinas A, Hui P, et al. Unleashing the Power of Mobile Cloud Computing using ThinkAir [R]. Technical report, Deutsche Telekom Labs, Berlin, Germany, 2011.
[77]Kosta, Aucinas S, Hui A, et al. ThinkAir:Dynamic resource allocation and parallel execution in the cloud for mobile code offloading [C]. In Proceedings of the 31th conference on Information Communications, Piscataway, NJ, USA,2012.
[78]Clark C, Fraser K, Hand S, et al. Live migration of virtual machines [C]. In Pro-ceedings of the 2nd conference on Symposium on Networked Systems Design & Implementation-Volume 2, Berkeley, CA, USA,2005:273-286.
[79]Chen G, Kang B, Kandemir M, et al. Energy-aware compilation and execution in Java-enabled mobile devices [C]. Proceedings of the 17th International Symposium on Parallel and Distributed Processing, Washington, DC, USA,2003.
[80]Chen G, Kang B, Kandemir M, et al. Studying energy trade offs in offloading com-putation/compilation in Java-enabled mobile devices [J]. IEEE Transactions on Par-allel and Distributed Systems,2004,15 (9):795-809.
[81]Zhao B, Xu Z, Chi C, et al. Mirroring smartphones for good:A feasibility study [J]. ZTE Communications,2011,9 (1):9-14.
[82]Guo Y, Zhang L, Kong J, et al. Jupiter:transparent augmentation of smartphone capabilities through cloud computing [C]. In Proceedings of the 3rd ACM SOSP Workshop on Networking, Systems, and Applications on Mobile Handhelds, New York, NY, USA,2011:2:1-2:6.
[83]Narayanan D, Satyanarayanan M. Predictive Resource Management for Wearable Computing [C]. In Proceedings of the 1st International Conference on Mobile Sys-tems, Applications, and Services,2003.
[84]Bradski G, Kaehler A. Learning OpenCV:Computer vision with the OpenCV li-brary [M]. O'Reilly Media,2008.
[85]Breslau L, Estrin D, Fall K, et al. Advances in Network Simulation [J]. Computer, 2000,33 (5):59-67.
[86]Paxson V, Floyd S. Wide-area traffic:the failure of Poisson modeling [C]. In Pro-ceedings of the Conference on Communications Architectures, Protocols and Ap-plications, New York, NY, USA,1994:257-268.
[87]Willinger W, Taqqu M S, Sherman R, et al. Self-similarity through high-variability: statistical analysis of Ethernet LAN traffic at the source level [J]. IEEE/ACM Trans-action on Networking,1997,5 (1):71-86.
[88]Kim M, Noble B. Mobile network estimation [C]. In Proceedings of the 7th Annual International Conference on Mobile Computing and Networking, New York, NY, USA,2001:298-309.
[89]Wolski R, Spring N T, Hayes J. The Network Weather Service:A Distributed Re-source Performance Forecasting Service for Metacomputing [J]. Journal of Future Generation Computing Systems,1999,15:757-768.
[90]Gurun S, Krintz C, Wolski R. NWSLite:a light-weight prediction utility for mo-bile devices [C]. In Proceedings of the 2nd International Conference on Mobile Systems, Applications, and Services, New York, NY, USA,2004:2-11.
[91]Dong M, Zhong L. Self-constructive high-rate system energy modeling for battery-powered mobile systems [C]. In Proceedings of the 9th International Conference on Mobile systems, Applications, and Services, New York, NY, USA,2011:335-348.
[92]Dong M, Zhong L. Demo:sesame:self-constructive system energy modeling for battery-powered mobile systems [C]. In Proceedings of the 9th International Con-ference on Mobile Systems, Applications, and Services, New York, NY, USA, 2011:373-374.
[93]Vallina-Rodriguez N, Crowcroft J. Energy Management Techniques in Modern Mobile Handsets [J]. Communications Surveys & Tutorials, IEEE:1-20.
[94]Shye A, Scholbrock B, Memik G. Into the wild:studying real user activity pat-terns to guide power optimizations for mobile architectures [C]. In Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture, New York, NY, USA,2009:168-178.
[95]Fan X, Weber W-D, Barroso L A. Power provisioning for a warehouse-sized com-puter [C]. In Proceedings of the 34th Annual International Symposium on Com-puter Architecture, New York, NY, USA,2007:13-23.
[96]Pathak A, Hu Y C, Zhang M, et al. Fine-grained power modeling for smartphones using system call tracing [C]. In Proceedings of the Sixth Conference on Computer Systems, New York, NY, USA,2011:153-168.
[97]Dong M, Zhong L. Self-constructive high-rate system energy modeling for battery-powered mobile systems [C]. In Proceedings of the 9th International Conference on Mobile Systems, Applications, and Services, New York, NY, USA,2011:335-348.
[98]Vallina-Rodriguez N, Hui P, Crowcroft J, et al. Exhausting battery statistics:un-derstanding the energy demands on mobile handsets [C]. In Proceedings of the second ACM SIGCOMM Workshop on Networking, Systems, and Applications on Mobile Handhelds, New York, NY, USA,2010:9-14.
[99]Falaki H, Mahajan R, Kandula S, et al. Diversity in smartphone usage [C]. In Pro-ceedings of the 8th International Conference on Mobile Systems, Applications, and Services, New York, NY, USA,2010:179-194.
[100]Zhang L, Tiwana B, Dick R, et al. Accurate online power estimation and automatic battery behavior based power model generation for smartphones [C]. In Proceed-ings of the 8th IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis,2010:105-114.
[101]Balasubramanian N, Balasubramanian A, Venkataramani A. Energy consumption in mobile phones:a measurement study and implications for network applications [C]. In Proceedings of the 9th ACM SIGCOMM Conference on Internet Measure-ment Conference,Scottsdale, Arizona, USA,2009:280-293.
[102]Schulman A, Schmid T, Dutta P, et al. Demo:Phone Power Monitoring with BattOr [R]. Demo of the 17th Annual International Conference on Mobile Computing and Networking, Las Vegas, Nevada, USA, September 19-23,2011.
[103]Vallina-Rodriguez N, Hui P, Crowcroft J, et al. Exhausting battery statistics:un-derstanding the energy demands on mobile handsets [C]. In Proceedings of the 2nd ACM SIGCOMM Workshop on Networking, Systems, and Applications on Mobile Handhelds, New York, NY, USA,2010:9-14.
[104]Ferreira D, Dey A, Kostakos V. Understanding human-smartphone concerns:a s-tudy of battery life [J]. Pervasive Computing,2011:19-33.
[105]Qian F, Wang Z, Gerber A, et al. Characterizing radio resource allocation for 3G networks [C]. In Proceedings of the 10th Annual Conference on Internet Measure-ment, New York, NY, USA,2010:137-150.
[106]Liu H, Zhang Y, Zhou Y. TailTheft:leveraging the wasted time for saving energy in cellular communications [C]. In Proceedings of the 6th International Workshop on MobiArch,2011:31-36.
[107]Ristanovic N, Le Boudec J-Y, Chaintreau A, et al. Energy Efficient Offloading of 3G Networks [C]. In Proceedings of the 2011 IEEE 8th International Conference on Mobile Ad-Hoc and Sensor Systems, Washington, DC, USA,2011:202-211.
[108]Wang L, Manner J. Energy Consumption Analysis of WLAN,2G and 3G interfaces [C]. In Proceedings of the 2010 IEEE/ACM International Conference on Green Computing and Communications & International Conference on Cyber, Physical and Social Computing, Washington, DC, USA,2010:300-307.
[109]Peng C, Lee S-B, Lu S, et al. Traffic-driven power saving in operational 3G cellu-lar networks [C]. In Proceedings of the 17th Annual International Conference on Mobile Computing and Networking, New York, NY, USA,2011:121-132.
[110]Ra M-R, Paek J, Sharma A B, et al. Energy-delay tradeoffs in smartphone applica-tions [C]. In Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services, New York, NY, USA,2010:255-270.
[111]Sklavos N, Touliou K. A System Level Analysis of Power Consumption and Opti-mization in 3G Mobile Devices [C]. In Proceedings of the 1st Intenational Confer-ence on New Technologies, Mobility, and Security,2007.
[112]Narayanan D, Flinn J, Satyanarayanan M. Using History to Improve Mobile Ap-plication Adaptation [C]. In Proceedings Of The 3rd IEEE Workshop On Mobile Computing Systems And Applications, New York, NY, USA,2000:30-41.
[113]Liang R, et al. A Survey of Human Face Detection [J]. Chinese Journal of Com-puters,2002:141-146.
[114]Bradski G. The opencv library [J]. Doctor Dobbs Journal,2000,25 (11):120-126.
[115]Savage S. Sting:A TCP-based Network Measurement Tool [C]. In USENIX Sym-posium on Internet Technologies and Systems,1999.
[116]Prasad R, Dovrolis C, Murray M, et al. Bandwidth estimation:metrics, measure-ment techniques, and tools [J]. Network, IEEE,2003,17 (6):27-35.
[117]Jain M, Dovrolis C. End-to-end available bandwidth:measurement methodology, dynamics, and relation with TCP throughput [J]. IEEE/ACM Transaction on Net-working,2003,11 (4):537-549.
[118]Zhang D-Y, Hu M-Z, Fang D-H. Analysis and evaluation of link capacity esti-mation tools [C]. In Proceedings of the 4th WSEAS International Conference on Electronics, Control and Signal Processing, Stevens Point, Wisconsin, USA,2005: 175-180.
[119]Kalyanaraman R S, Xiao Y, Yla-Jaaski A. Network Prediction for Adaptive Mobile Applications [C]. In Proceedings of the 3rd International Conference on Mobile U-biquitous Computing, Systems, Services and Technologies, Washington, DC, US-A,2009:141-146.
[120]Nicholson A J, Noble B D. BreadCrumbs:forecasting mobile connectivity [C]. In Proceedings of the 14th ACM International Conference on Mobile computing and Networking, New York, NY, USA,2008:46-57.
[121]Guo S. Android Power Management [R].2010.
[122]Terrenghi L, Lang T, Lehner B. Elastic mobility:stretching interaction [C]. In Proceedings of the 11 th International Conference on Human-Computer Interaction with Mobile Devices and Services, New York, NY, USA,2009:46:1-46:4.
[123]Higgins B D, Reda A, Alperovich T, et al. Intentional networking:opportunistic exploitation of mobile network diversity [C]. In Proceedings of the 16th Annual International Conference on Mobile Computing and Networking, New York, NY, USA,2010:73-84.
[124]Microsoft. Windows Remote Management Specification, v1.1 [R].2008.
[125]Narayanan D, Satyanarayanan M. Predictive Resource Management for Wearable Computing [C]. New York, NY, USA,2003:113-128.
[126]CSDN. Introduction of JPEG Coding Technique [R].
[127]Walther P. Adaptiver Chariot Server [D]. Institute for Computer Systems, ETH Zurich,1997.
[128]Chandra S, Ellis C S. JPEG compression metric as a quality-aware image transcod-ing [C]. In Proceedings of the 2nd Conference on USENIX Symposium on Internet Technologies and Systems-Volume 2, Berkeley, CA, USA,1999:8-8.
[129]Bolliger J. A framework for network-aware applications [D]. Swiss Federal Insti-tute of Technology Zurich,2000.
[130]Marinelli E. Hyrax:cloud computing on mobile devices using MapReduce [D]. School of Computer Science, Carnegie Mellon University,2009.