MBDS: Management of Big Data Systems

Important Dates

• Paper submissions due: March 31, 2014, 11:59 p.m. PDT
• Notification to authors: April 9, 2014
• Final paper files due: May 20, 2014

Management of Big Data Systems Organizers

Program Vice-Chairs

Karsten Schwan, Georgia Institute of Technology
Vanish Talwar, HP Labs

Publicity Chair

Dani Abel Rayan, CrowdChat

Program Committee

Hrishikesh Amur, Google
Adhyas Avasthi, Cisco
Surendar Chandra, EMC
Yuan Chen, HP Labs
Renato Figueiredo, University of Florida
Matthew Jacobs, Cloudera
Dinesh A. Joshi , Yahoo
Michael A. Kozuch, Intel
Aravind Menon, Facebook
Dani Rayan, CrowdChat
Vasily Tarasov, IBM
Chengwei Wang, AT&T Labs

Overview

Data is growing at an exponential rate and several systems have emerged to store and analyze such large amounts of data. These systems, termed "Big Data systems" are fast-evolving. Examples include the NoSQL storage systems, Hadoop Map-Reduce, data analytics platforms, search and indexing platforms, and data streaming infrastructures. These systems address needs for structured and unstructured data across a wide spectrum of domains such as Web, social networks, enterprise, cloud, mobile, sensor networks, multimedia/streaming, cyberphysical systems, and high performance applications including for experiment data generated by high end devices; and for multiple application verticals such as biosciences, healthcare, transportation, public sector, energy utilities, oil and gas, and scientific computing.

With increasing scale and complexity, managing these Big Data systems to cope with failures and performance problems is becoming non-trivial. New resource management and scheduling mechanisms are also needed for such systems, as are mechanisms for tuning and support from platform layers. Several open source and proprietary solutions have been proposed to address these requirements, with extensive contributions from industry and academia. However, there remain substantial challenges, including those that pertain to such systems' autonomic and self-management capabilities.

The objective of the MBDS track at ICAC '14 is to bring together researchers, practitioners, system administrators, system programmers, and others interested in sharing and presenting their perspectives on the effective management of Big Data systems. The focus of the track is on novel and practical systems-oriented work. MBDS offers an opportunity for researchers and practitioners from industry, academia, and the National Labs to showcase the latest advances in this area and also to discuss and identify future directions and challenges in all aspects on autonomic management of Big Data systems.

Two types of contributions are solicited on all aspects of Big Data management: (1) short papers and (2) panel presentations. Short papers should be no more than 6 pages, including the abstract, and will appear in the ICAC '14 conference proceedings. Proposed panel presentations require only an abstract. Topics of interest include but are not limited to the following:

• Autonomic and self-managing techniques to deal with failures, load imbalance, etc.
• Application-level resource management and scheduling mechanisms
• System tuning/auto-tuning and configuration management
• APIs and interactions between application- and system-level management or more generally, holistic management across software and hardware
• Performance management, fault management, and power management
• Scalability challenges
• Complexity challenges, as for composite, cross-tier systems with multiple control loops
• Unified/joint management of "data in motion" and "data at rest"
• Dealing with structured or with unstructured data, or both
• Monitoring, diagnosis, and automated behavior detection
• System-level principles and support for resource management
• Implications of emerging hardware technologies such as non-volatile memory
• Domain specific challenges in Web, cloud, social networks, mobile, sensor networks, streaming analytics, and cyber-physical systems
• System building and experience papers for specific industry verticals

Submissions

Submissions to the MBDS track follow the same guidelines as described in the main ICAC '14 Call for Papers; in addition, submissions should be a maximum of 6 pages in length. In order to submit your work to the MBDS track, please do so via the Web submission form for this special track, as opposed to the submission form for the general ICAC '14 track. Questions? Contact the Program Vice-Chairs of the track.

Past Events

This track is a continuation of the previous Workshop on Management of Big Data Systems held at ICAC 2012, and the Management of Big Data Systems Track held at ICAC '13.