• data distribution schemes

Instead of naive data mirroring or replication, we are studying more generalized data placement schemes using error correcting codes, that provide robust data distribution schemes to maintain high availability of data access, as well as high data security and overall data system performance in terms of throughput and resource utilization. Currently these schemes are being integrated into Hydra ( with some screen shots of a simple demo of the Hydra ), a general platform for secure and survivable networked storage systems.


• data security

Data security, mainly data privacy and integrity, is an important component in virtually all information systems. We are studying novel schemes that are much more computationally efficient than traditional crypto-operations ( such as encryptions ) to ensure data security. Examples include multicast key distribution, distributed data storage.


• data dissemination schemes
  
  Broadcast or multicast, which is inherent in most wireless networks, provides an efficient means to disseminate data to a large group of receivers. We are studying various data dissemination schemes over broadcast/multicast networks, such as video-on-demand and more general broadcast scheduling schemes.
  
  
• data transmission protocols
  
  We study protocols that enable efficient transfer of massive data, especially multimedia streaming data, over high speed networks. Our goals include decreasing network congestions by smoothing and stabilizing source sending rate, reducing data retransmission when packet loss occurs and increasing overall transmission throughput and network resource utilization.
  
  
  
  
  

Recent Technical Reports

• An Efficient XOR-Scheduling Algorithm for Erasure Codes Encoding ( pdf ), Dec. 2008

• A Performance Evaluation and Examination of Open-Source Erasure Coding Libraries For Storage ( pdf ), Sep. 2008

• SCAN: An Efficient Sector Failure Recovery Algorithm for RAID-6 Codes ( pdf ), Dec. 2007

• Quantifying Benefit and Cost of Erasure Code Based File Systems ( pdf ), Dec. 2007

• Efficient Erasure Decoding for Generalized Reed Solomon Codes ( pdf ), Jan. 2007

Past Technical Reports

• On the Erasure Recoverability of MDS Codes under Concurrent Updates(pdf), Jan. 2005,

• Optimal Broadcast Scheduling for Random-Loss Channels ( pdf), Apr. 2004,

• Efficient Fault-tolerant Distributed Storage using Erasure Codes(pdf), Feb. 2004,

• Fast Software Implementations of Finite Field Operations ( pdf), Dec. 2003,

• Reliable and Secure Distributed Data Storage Using Erasure Codes ( pdf), Aug. 2003,

• Efficient FEC Codes for Data Loss Recovery ( ps or pdf), Jun. 2003,

• Efficient Reliable Data Broadcast over Multiple Channels ( ps or pdf), Feb. 2003,

• SRC: Stable Rate Control for Streaming Media ( ps or pdf), Feb. 2003

• Multirate Data Distribution with Channel Subscription Cost ( ps or pdf), Feb., 2003

• Achieving Scalable and Efficient Video-on-Demand Over Multicast ( ps or pdf ), Oct. 2002

• Computation Efficient Multicast Key Distribution ( ps or pdf ), Mar. 2002

• Maximizing Burst Erasure Correction Capability of MDS Codes ( ps or pdf), Aug. 2001

Recent Conferences

• An Efficient XOR-Scheduling Algorithm for Erasure Codes Encoding ( pdf ), Proc. of DSN 2009, June 29 to July 2, 2009, Estoril, Lisbon, Portugal.

• A Performance Evaluation and Examination of Open-Source Erasure Coding Libraries for Storage ( pdf ), Proc. of FAST 2009, Feb. 24 to 27, 2009, San Francisco, CA.
  
  
• HyFS: A Highly Available Distributed File System, ( Abstract ) WiP of FAST 2008, Feb. 26 to 29, 2008, San Jose, CA.
  
  
• Optimizing Cauchy Reed-Solomon Codes for Fault-Tolerant Network Storage Applications ( pdf ) Proc. of The 5th IEEE International Symposium on Network Computing and Applications (IEEE NCA06), Cambridge, MA, July, 2006. ( Best Paper for Network Computing )
  
  
• STAR: An Efficient Coding Scheme for Correcting Triple Storage Node Failures ( pdf ) Proc. of FAST 2005, December 14 to 16, 2005, San Francisco, CA.
  
  
• Hydra: A Platform for Survivable and Secure Data Storage Systems ( pdf ) Proc. of StorageSS 2005, Fair Fax, Virginia, USA, Nov. 2005.
  
  

Past Conferences

• Optimal Broadcast Scheduling for Random-Loss Channels ( pdf ) Proc. of ISIT 05, Adelaide, Australia, Sep. 2005.
  
  
• On the Erasure Recoverability of MDS Codes under Concurrent Updates ( pdf ) Proc. of ISIT 05, Adelaide, Australia, Sep. 2005.
  
  
• Using Erasure Codes Efficiently for Storage in a Distributed System(pdf), Proc. DSN 2005, Yokohama, Japan, June-July 2005.
  
  
• Study of A Practical FEC Scheme for Wireless Data Streaming (pdf), IASTED Internet and Multimedia Systems and Applications, Grindelwald, Switzerland, Feb. 2005.
  
  
• Optimal Coding Rate Control for Scalable Streaming Media (pdf), Proc. International Packet Video Workshop, Irvine, CA, Dec. 2004.
  
  
• Optimal Control of Multiple Bit Rates for Streaming Media (pdf), Proc. Picture Coding Symposium, San Francisco, CA, Dec. 2004.
  
  
• Loss-Resilient On-demand Media Streaming using Priority Encoding (pdf), ACM Multimedia 2004, New York, NY, October 2004,

• Efficient and Flexible Parallel Retrieval using Priority Encoded Transmission(pdf), NOSSDAV 2004, Kinsale, Ireland, June 2004,

• Scheduling for Efficient Data Broadcast over Two Channels ( ps or pdf ), ISIT 2004, Chicago, IL, Jun.-Jul. 2004,

• Layered Priority Encoded Transmission for Video Streaming to Heterogeneous Receivers (pdf), ISIT 2004, Chicago, IL, Jun.-Jul. 2004,

• SRC: Stable Rate Control for Streaming Media ( ps or pdf), Globecom 2003, San Francisco, Dec., 2003

• Maximizing Burst Erasure Correction Capability of MDS Codes ( pdf ) or ( ps ), 41st Annual Allerton Conference on Communication, Control and Computing, Oct., 2003

• A General Encryption Scheme Based on MDS Code ( ps or pdf ), ISIT 2003, Yokohama, Japan, Jun. 2003

• Computation Efficient Multicast Key Distribution ( ps or pdf ), ISIT 2003, Yokohama, Japan, Jun. 2003

• Coding and Scheduling for Efficient Loss-Resilient Data Broadcasting ( ps or pdf ), ISIT 2003, Yokohama, Japan, Jun. 2003

• Scalable and Efficient Multi-rate Data Distribution ( ps or pdf ), ISIT 2003, Yokohama, Japan, Jun. 2003

• Coding for High Density Storage Systems ( pdf ), 40th Annual Allerton Conference on Communication, Control and Computing, Oct., 2002

• Soft Decoding of Several Classes of Array Codes ( ps or pdf ), IEEE ISIT, Lausanne, Switzerland, Jun., 2002

• Fuzzycast: Efficient Video-on-demand over Multicast ( ps or pdf ), IEEE INFOCOM, New York, Jun., 2002

• Efficient and Scalable Data Streaming Using UEP Codes ( ps or pdf ), ACM Multimedia, Ottawa, Canada, Oct. 2001

Journals

• STAR: An Efficient Coding Scheme for Correcting Triple Storage Node Failures

  IEEE Trans. on Computer, July 2008

• Computation Efficient Multicast Key Distribution

  IEEE Trans. on Parallel and Distributed Systems, May 2008

• Maximizing Burst Erasure Correction Capability of MDS Codes

  IEEE Trans. on Communications, Nov. 2006.

• Resource-Efficient Delivery of On-Demand Streaming Data Using UEP Codes

  IEEE Trans. on Communications, Jan. 2003.

• Computing in the RAIN: A Reliable Array of Independent Nodes

  IEEE Trans. on Parallel and Distributed Systems, Feb. 2001

• Low Density MDS Codes and Factors of Complete Graphs

  IEEE Trans. on Information Theory, Sep. 1999

• X-Code: MDS Array Codes with Optimal Encoding

  IEEE Trans. on Information Theory, Jan. 1999

• Deterministic Voting in Distributed Systems Using Error-Correcting Codes

  IEEE Trans. on Parallel and Distributed Systems, Aug. 1998

Book Chapters

• Dynamic Group Key Distribution Using MDS Codes

  Information, Coding and Mathematics, Kluwer Academic Publisher, 2002

• Highly Available Distributed Storage Systems

  Proceedings of Workshop on Distributed High Performance Computing,
  Lecture Notes in Control and Information Sciences, Springer Verlag, 1999