Research
Projects | Publications | Other Groups
The increasing popularity of the cloud for communicating, computing, and storage opens up a host of research opportunities. Research here at Cornell covers the architectural gambit from efficiency, security, reliability, hardware, and software to the social and policy implications of cloud computing on people and organizations.
Projects:
- Antiquity - a wide-area distributed storage system designed to provide a simple storage service for applications
- Elastic Replication - scalable replication techniques for the cloud where configuration management is carefully separated from ordering updates to replicas and replicated objects cooperatively are responsible for each other's configuration. The benefits are that management can be aggressively decentralized for scalability while strong consistency is maintained.
-
- is a federated, distributed system for securely and reliably storing, sharing, and computing information.
- GridControl - Cornell University and Washington State University will join forces to create GridControl, a powerful and comprehensive software platform that will slash the time and difficulty required to prototype and demonstrate new smart-grid control paradigms. GridContrl combines Cornell's Isis2 platform, for high assurance cloud computing with Washington State University's GridStat technology, for smart grid monitoring & control.
- HotOS - a proposed datacenter storage system that is frugal with energy use
- Isis2 - Can we have strong consistency and also high performance in the cloud computing? Isis2 explores this core question and offers a library for replicating data or computing in cloud services coded in standard object oriented languages like Java, C# or C++, and automates such tasks as replicating updates, keeping checkpoints and encrypting data for security.
- RACS: Redundant Array of Cloud Storage - a proxy that transparently spreads the cloud data storage load over many providers.
- SIN - Research in Social and Information Networks
- Science of Cloud-Scale Computing - Support of student experiments in cloud platforms with the goal of contributing towards a scientific foundation for scalable trust in cloud computing.
- Social Dynamics Laboratory - The Social Dynamics Laboratory members study the interplay between network topology and the dynamics of social interaction, using computational models, data from on-line networks, and laboratory experiments with human participants.
- xCloud - a new type of IaaS cloud, an xCloud, that builds on ideas from extensible OSs to give users the flexibility to install custom cloud extensions
Recent Publications
- Kenneth P. Birman, Daniel A. Freedman, Qi Huang and Patrick Dowell. Overcoming CAP with Consistent Soft-State Replication. IEEE Computer Magazine, February 2012.
- Tao Zou, Guozhang Wang, Marcos Vaz Salles, David Bindel, Alan Demers, Johannes Gehrke, and Walker White. Making Time-stepped Applications Tick in the Cloud. SOCC 2011
- Tuan Cao, Benjamin Sowell, Marcos Vaz Salles, Alan Demers, Johannes Gehrke. BRRL: A Recovery Library for Main-Memory Applications in the Cloud (Demonstration Paper). SIGMOD 2011.
- Hakim Weatherspoon, Hugo Miranda, Konrad Iwanicki, Ali Ghodsi, Yann Busnel. GOSSIP: Gossiping Over Storage Systems Is Practical. Appears in ACM Operating Systems Review (OSR), Vol 41, No 5, October 2007, pp 75-81.
- Kenneth P. Birman, Q. Huang, D. Freedman. Overcoming the “D” in CAP: Using Isis2 To Build Locally Responsive Cloud Services. Technical report, Cornell University (April 2011).
- Andrei Agapi, Kenneth P. Birman, Robert Broberg, Chase Cotton, Thilo Kielmann, Martin Millnert, Rick Payne, Robert Surton, and Robbert VanRenesse. Routers for the Cloud. Can the Internet Achieve 5-Nines Availability? IEEE Internet Computing. Volume 15. Issue 5. pp.72 - 77. September, October 2011.
- Lakshmi Ganesh, Hakim Weatherspoon, Kenneth P. Birman. Beyond Power Proportionality: Designing Power-Lean Cloud Storage. IEEE (NCA 2011)August 25 - 27, 2011. Cambridge MA
- Kenneth P. Birman, Lakshmi Ganesh, and Robbert van Renesse. Running Smart Grid Control Software on Cloud Computing Architectures. A Workshop on Computational Needs for the Next Generation Electric Grid, Cornell University, April 19-20, 2011. Ithaca, NY.