Clark School Home UMD

ISR News Story

Barg receives NSF grant to develop better methods of storing large amounts of data

Professor Alexander Barg (ECE/ISR) is the principal investigator for a new NSF Communication and Information Foundations grant, “Efficient Codes and their Performance Limits for Distributed Storage Systems.” The three-year, $300K grant addresses the efficient means of storing the huge amount of data being generated and collected. This research will develop more efficient data management procedures for large-scale distributed storage systems.

Large data centers and distributed storage systems have become more widespread, playing an ever-increasing role in everyday computational tasks. While a data center should never lose data, industry statistics confirm that disk failures occur on a daily basis. Barg will develop methods and ideas about error correcting codes that will enable systems to provide better guarantees against data loss and reduce the amount of data that needs to be moved to enable recovery of information lost due to disk failures.

Barg also will use algebraic methods of constructing data encoding procedures as well as novel algorithms of data exchange and recovery to reduce the storage overhead needed to support the recovery procedures. This will enable tradeoffs between overhead and repair bandwidth, based on the concept of local recovery. Barg will study both the case of recovering from a single disk loss, which is the most frequent problem in systems, as well as failure of multiple disks. This will address the problem of correcting one erasure as well as multiple erasures in data encoding. New bounds on the distance of codes with the locality requirement derived in this research will be developed, as well as new constructions of optimal locally recoverable codes equipped with simple recovery procedures.

The project also addresses the problem of simultaneous recovery of data from multiple locations, enhancing data availability in the large-scale distributed storage systems that are a key backbone component of the 21st century economy.

Related Articles:
Alexander Barg receives NSF grant to study theoretic aspects of local data recovery
Alum Ara Mazumdar begins position at University of Minnesota
Alexander Barg receives NSF grant for polar code research
Alexander Barg awarded NSF grant to develop genotyping theory
Arya Mazumdar wins information theory student paper prize
Alexander Barg receives NSF grant for improving error-correcting coding

September 5, 2014


Prev   Next

 

 

Current Headlines

University of Maryland School of Engineering Announces Unprecedented Investment from A. James & Alice B. Clark Foundation

Alumni Naomi Leonard and Xiaobo Tan part of public lecture on underwater robotics

Clark School Spinout Developing Pediatric Cancer Drug Delivery System to Prevent Hearing Loss from Chemotherapy

UMD Solar Decathlon team takes 1st place in the U.S., 2nd place in the world

UMD Researchers Develop Stable, Robust Li-ion Battery Chemistry

Five ISR faculty part of $8 million NIH grant to combat hearing loss in older people

Building Together Announcement Garners Extensive Media Coverage

Maryland Power Electronics Laboratory participates in Maryland Manufacturing Day

The Home of the Future

Espy-Wilson's technology included in new Alcatel MOVE TIME smart watch

News Resources

Return to Newsroom

Search News

Archived News

Events Resources

Events Calendar