Grant: Engage Grants Program
University of Waterloo
$25,000.00
Practical network codes for distributed storage
FY 2013-14
Summary
The increasing amount of data generated in the growing digital world requires efficient storage solutions. The use of coding techniques has been motivated by effective repair properties over distributed storage systems (DSS), including huge data centres such as Google, Amazon, Facebook and peer-to-peer (P2P) systems such as OceanStore and Total Recall. Coding is traditionally used for communication over noisy channels where redundancy is added to the transmitted messages in order to protect them against errors and erasures. In a similar manner, over distributed storage systems with network connectivity, it is required to design storage codes with low overhead to add loss resilience to the system while optimizing the repair and maintenance process. Repairing the nodes after a physical loss of a data storage unit or encountering network problems and regenerating the inaccessible data over P2P systems are such applications.Features such as reliability and fault-tolerance, consuming power, amount of disk access, computational complexity, network traffic and system maintenance are some of the desirable design parameters.In this proposal, we investigate networked distributed storage systems for multiple failure tolerance with simultaneous repair capabilities. Specifically, we target reducing data transfer with coordinated network codes in regenerating codes and providing improved local repair alternatives in locally repairable codes. We investigate regenerating codes employing network coding to collect data from surviving nodes to regenerate a failed one. Linear combinations are allowed at the intermediate nodes, giving a tradeoff between the amount of storage at each node and the total repair bandwidth. Novel explicit code constructions with parallel repair capabilities will be considered.
Program
Engage Grants Program
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
459127-2013
Name nom
Damen, MohamedOussama
Department département
Electrical & Computer Engineering
Organization id
33
Institution établissement
University of Waterloo
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2013
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
Area of application code
803
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer communications
Area of application fr
Téléinformatique
Research subject code
2507
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Communications systems
Research subject fr
Systèmes de télécommunications
Partie
1
Nb partie
1
Application title
Practical network codes for distributed storage
Keyword
NSERC
Application summary
The increasing amount of data generated in the growing digital world requires efficient storage solutions. The use of coding techniques has been motivated by effective repair properties over distributed storage systems (DSS), including huge data centres such as Google, Amazon, Facebook and peer-to-peer (P2P) systems such as OceanStore and Total Recall. Coding is traditionally used for communication over noisy channels where redundancy is added to the transmitted messages in order to protect them against errors and erasures. In a similar manner, over distributed storage systems with network connectivity, it is required to design storage codes with low overhead to add loss resilience to the system while optimizing the repair and maintenance process. Repairing the nodes after a physical loss of a data storage unit or encountering network problems and regenerating the inaccessible data over P2P systems are such applications.Features such as reliability and fault-tolerance, consuming power, amount of disk access, computational complexity, network traffic and system maintenance are some of the desirable design parameters.In this proposal, we investigate networked distributed storage systems for multiple failure tolerance with simultaneous repair capabilities. Specifically, we target reducing data transfer with coordinated network codes in regenerating codes and providing improved local repair alternatives in locally repairable codes. We investigate regenerating codes employing network coding to collect data from surviving nodes to regenerate a failed one. Linear combinations are allowed at the intermediate nodes, giving a tradeoff between the amount of storage at each node and the total repair bandwidth. Novel explicit code constructions with parallel repair capabilities will be considered.