First International Workshop on Elasticity Engineering for Big Data Analytics (eBigDaC)

Held in conjunction with IEEE International Conference on Big Data (IEEE BigData 2015)

Oct 29 - Nov 01, 2015 @ Santa Clara, CA, USA

Overview Topics Submission Important Dates Committees


Big data analytics employ different computational models, application models (workflows, MapReduce, etc.), data service resources and computational resources (e.g., machines for computation and humans for evaluating results). The use of such models and resources can be elastic due to changes in user requirements and infrastructure/system availability.While distributed computing infrastructures, such as Cloud computing, possess inherent abilities to support elasticity, big data analytics has not been equipped with sufficient techniques that enable dynamic elasticity for delivering changing quality of analytics as trade offs of performance (e.g., deadline of the analytics), cost (e.g., monetary prices to be paid), quality of data (e.g., data accuracy), and forms of resultant data (e.g., comma-separated values or a chart).On the one hand, big data analytics need to deal with multiple runtime properties from data sources, such as data volume and quality of data, by utilizing different analytics algorithms/processes atop diverse types of resources with different cost and performance models. On the other hand, big data analytics must support trade offs among resources, cost and quality required by the user of the analytics. In most of today’s big data analytics environments, computational resource elasticity is the main focus, while quality of data has not been well studied for executing dynamic data analytics, let alone the combination of multiple elastic metrics. To harvest the benefits of elasticity principles and move towards the realization of elastic big data analytics, it is imperative that automated, multi-dimensional elasticity mechanisms be defined on multiple levels of a big data ecosystem.

The goal of the 1st International Workshop on Elasticity Engineering for Big Data Analytics(eBigDac) will be to bring together researchers and practitioners from both academia and industry to explore, discuss and possibly redefine the state of the art in elasticity relative to modeling,methods and tools applied over any part of services and computing infrastructures as well as use-cases and applications that relate to big data analytics.

Concretely, the workshop is expected to provide insight into:

  • modeling: theoretical work into modeling elasticity relative to big data analytics

  • control: methods or tools for efficient control of multi-dimensional elasticity and its trade-offs for big data analytics

  • testing: methods and techniques for testing and benchmarking elasticity for big data analytics

  • applications: new or existing big data applications or platforms that exploit elastic mechanisms and display adaptive cost and quality characteristics

Workshop topics

This workshop will solicit original research work on fundamental aspects of elastic computing and the notion of big data analytics as well as the design, implementation and evaluation of novel tools, methods and applications for optimizing a big data computing system (in parts or as a whole).

Topics of interest include, but not limited to:

  • Elasticity modelling frameworks for big data

  • Intelligent data quality measurement and control for big data analytics

  • Elasticity algorithms for distributed, large-scale data stores (e.g., NoSQL databases) and data processing engines (Hadoop, Spark, etc)

  • Monitoring and analysis of multi-dimensional elasticity in big data systems

  • Benchmarking and testing of elasticity of big data systems

  • Techniques and methods for engineering elastic decision making in large scale distributed systems (Cloud, Fog, HPC, IoT, Grid, P2P)

  • Applications and use cases that perform or require data elasticity


We seek for both full and demo papers. Full papers will be submitted as PDF files, using the IEEE Computer Society proceedings format (two column, 10 point, single-spaced, US Letter, no margin smaller than one inch) with a page limit of 8 pages. Demo paper should be limited with 2 pages. All papers will be reviewed by at least 3 technical committee members. Accepted papers will be published by IEEE. You can submiss the paper through EasyChair using this link:

Important dates:

  • Manuscript submission due: Aug 20, 2015

  • Author notification: Sept 20, 2014

  • Camera ready due: Oct 5, 2015


Workshop co-chair:

  • Marios Dikaiakos, University of Cyprus, Cyprus

  • Hong-Linh Truong, TU Wien, Austria (main contact)

  • Dimitrios Tsoumakos, Ionian University, Greece

Technical program committee (tentative):

  • Mehmet Aktas, Yildiz Technical University, Turkey

  • David Bermbach, TU Berlin, Germany

  • Alex Delis, Univ. of Athens, Greece

  • Schahram Dustdar, TU Wien, Austria

  • Vincenzo Gulisano, Chalmers University of Technology, Sweden

  • Verena Kantere, University of Geneva

  • Nectarios Koziris, National Technical University of Athens, Greece

  • Chandra Krintz, UC Santa Barbara, USA

  • Manolis Marazakis, Instutute of Computer Science, FORTH, Greece

  • Daniel Moldovan, TU Wien, Austria

  • George Pallis, University of Cyprus, Cyprus

  • Erica Yang, STFC, UK

  • Petros Zerfos, IBM Research, USA