A Multi-Objective Approach to Real-Time In-Situ Processing of Mobile-Application Workflows

Innovative mobile applications that rely on real-time in-situ processing of data collected in the field <italic>need </italic> to tap into the heterogeneous sensing and computing capabilities of sensor nodes, mobile handhelds as well as computing and storage servers in remote datacenters. There is, however, <italic>uncertainty</italic> associated with the <italic>quality</italic> and <italic>quantity</italic> of data from mobile sensors as well as with the <italic> availability</italic> and <italic>capabilities</italic> of mobile computing resources on the field. Data and computing-resource uncertainty, if unchecked, may propagate up the “raw data<inline-formula> <tex-math notation="LaTeX">$\rightarrow$</tex-math><alternatives> <inline-graphic xlink:type="simple" xlink:href="pompili-ieq1-2532864.gif"/></alternatives></inline-formula>information<inline-formula> <tex-math notation="LaTeX">$\rightarrow$</tex-math><alternatives> <inline-graphic xlink:type="simple" xlink:href="pompili-ieq2-2532864.gif"/></alternatives></inline-formula>knowledge” chain and have an adverse effect on the relevance of the generated results. A generalized workflow representation scheme that can represent a wide variety of data- and task-parallel ubiquitous mobile applications is presented. A unified uncertainty-aware framework for data and computing-resource management to enable real-time, in-situ processing of applications is proposed and evaluated. The framework employs a two-phase solution that captures the propagation of data uncertainty up the data-processing chain using interval arithmetic in the first phase and that employs multi-objective optimization for task allocation in the second phase. The results of a case study to assess effectiveness the proposed framework are discussed in detail. Results reaffirm that i) data-uncertainty awareness helps control the uncertainty in the final result and ii) multi-objective combinatorial approach for task allocation significantly outperforms the single-objective approaches in terms of makespan (15 percent improvement), fairness in battery drain (56 percent improvement), and network load (54 percent improvement).

[1]  Kyungyong Lee,et al.  MapReduce on opportunistic resources leveraging resource availability , 2012, 4th IEEE International Conference on Cloud Computing Technology and Science Proceedings.

[2]  Ching-Hsien Hsu,et al.  Scheduling Multiple Scientific and Engineering Workflows through Task Clustering and Best-Fit Allocation , 2012, 2012 IEEE Eighth World Congress on Services.

[3]  Dario Pompili,et al.  An autonomic resource provisioning framework for mobile computing grids , 2012, ICAC '12.

[4]  Mohan Kumar,et al.  Minimum-Delay Service Provisioning in Opportunistic Networks , 2011, IEEE Transactions on Parallel and Distributed Systems.

[5]  Paramvir Bahl,et al.  The Case for VM-Based Cloudlets in Mobile Computing , 2009, IEEE Pervasive Computing.

[6]  Eduardo F. Nakamura,et al.  Information fusion for wireless sensor networks: Methods, models, and classifications , 2007, CSUR.

[7]  Nian-Feng Tzeng,et al.  Peer-to-peer checkpointing arrangement for mobile grid computing systems , 2007, HPDC '07.

[8]  Luiz Fernando Bittencourt,et al.  Towards the Scheduling of Multiple Workflows on Computational Grids , 2010, Journal of Grid Computing.

[9]  Xu Chen,et al.  COMET: Code Offload by Migrating Execution Transparently , 2012, OSDI.

[10]  Marty Humphrey,et al.  Mobile OGSI.NET: grid computing on mobile devices , 2004, Fifth IEEE/ACM International Workshop on Grid Computing.

[11]  Ellen W. Zegura,et al.  Serendipity: enabling remote computing among intermittently connected mobile devices , 2012, MobiHoc '12.

[12]  Martin L. Griss,et al.  Activity-Aware Mental Stress Detection Using Physiological Sensors , 2010, MobiCASE.

[13]  Mohan Kumar,et al.  Opportunities in Opportunistic Computing , 2010, Computer.

[14]  Baozhi Chen,et al.  Research challenges in computation, communication, and context awareness for ubiquitous healthcare , 2012, IEEE Communications Magazine.

[15]  J. C. Hayya,et al.  A Note on the Ratio of Two Normally Distributed Variables , 1975 .

[16]  Farbod Farzan,et al.  Downscaling Radar-Rainfall Data via Ubiquitous Sensing and Data Fusion , 2012 .

[17]  Junseok Hwang,et al.  Middleware services for P2P computing in wireless grid networks , 2004, IEEE Internet Computing.

[18]  Bruno Schulze,et al.  Peer-to-peer resource discovery in mobile Grids , 2005, MGC '05.

[19]  Alec Wolman,et al.  MAUI: making smartphones last longer with code offload , 2010, MobiSys '10.

[20]  Jörg Roth,et al.  Using Handheld Devices in Synchronous Collaborative Scenarios , 2001, Personal and Ubiquitous Computing.

[21]  Behrooz Shirazi,et al.  DFRN: a new approach for duplication based scheduling for distributed memory multiprocessor systems , 1997, Proceedings 11th International Parallel Processing Symposium.

[22]  Ramesh Govindan,et al.  Odessa: enabling interactive perception applications on mobile devices , 2011, MobiSys '11.

[23]  E. Hall.  Clinical Biochemistry: Metabolic and Clinical Aspects , 2009 .

[24]  J. Rokne.  Interval arithmetic and interval analysis: an introduction , 2001 .

[25]  Kathrin Klamroth,et al.  Generalized multiple objective bottleneck problems , 2012, Oper. Res. Lett..

[26]  Dario Pompili,et al.  Uncertainty-Aware Autonomic Resource Provisioning for Mobile Cloud Computing , 2015, IEEE Transactions on Parallel and Distributed Systems.

[27]  Dario Pompili,et al.  Enabling Real-Time In-Situ Processing of Ubiquitous Mobile-Application Workflows , 2013, 2013 IEEE 10th International Conference on Mobile Ad-Hoc and Sensor Systems.

[28]  Xike Xie,et al.  Cleaning uncertain data with quality guarantees , 2008, Proc. VLDB Endow..

[29]  Luca Calderoni,et al.  From Sensing to Action: Quick and Reliable Access to Information in Cities Vulnerable to Heavy Rain , 2014, IEEE Sensors Journal.

[30]  Douglas Thain,et al.  Distributed computing in practice: the Condor experience , 2005, Concurr. Pract. Exp..

[31]  Yolanda Gil,et al.  Pegasus: Planning for Execution in Grids , 2002 .

[32]  Helen D. Karatza,et al.  Scheduling multiple task graphs in heterogeneous distributed real-time systems by exploiting schedule holes with bin packing techniques , 2011, Simul. Model. Pract. Theory.

[33]  Eugene Marinelli,et al.  Hyrax: Cloud Computing on Mobile Devices using MapReduce , 2009 .

[34]  Michael Zink,et al.  Capturing Data Uncertainty in High-Volume Stream Processing , 2009, CIDR.

[35]  Jeff Weber,et al.  Workflow Management in Condor , 2007, Workflows for e-Science, Scientific Workflows for Grids.

[36]  Javier Guerra-Casanova,et al.  Real-Time Stress Detection by Means of Physiological Signals , 2011 .

[37]  Jennifer Widom,et al.  Working Models for Uncertain Data , 2006, 22nd International Conference on Data Engineering (ICDE'06).

[38]  Byung-Gon Chun,et al.  CloneCloud: elastic execution between mobile device and cloud , 2011, EuroSys '11.