Projects

This is a list of research projects (which produced published results) I have been involved in over the past 8 years throughout my graduate career.  The projects are separated into two categories: lead role and participating role.  The lead role projects were projects that eventually lead to multiple publications and even theses and dissertations; in general, I was the first author on most of the publications from these projects.  The participating role projects were mostly supporting work for my main projects, but in general I was not the main author on any of the publications which resulted from those projects.

Lead Role

1. Falkon: a Fast and Light-weight tasK executiON framework

• Dates: December 2006 – Present
• Web Site: http://people.cs.uchicago.edu/~iraicu/projects/Falkon/index.htm
• Globus Incubator Project Site: http://dev.globus.org/wiki/Incubator/Falkon
• People: Ian Foster, Mike Wilde, Yong Zhao, Catalin Dumitrescu, Zhao Zhang
• Contributions: Designed and implemented Falkon, to enable the rapid and efficient execution of many independent jobs on large compute clusters. Falkon combines three techniques to achieve this goal: (1) multi-level scheduling techniques to enable separate treatments of resource provisioning and the dispatch of user tasks to those resources; (2) a streamlined task dispatcher able to achieve order-of-magnitude higher task dispatch rates than conventional schedulers; and (3) performs data caching and uses a data-aware scheduler to leverage the co-located computational and storage resources to minimize the use of shared storage infrastructure. 

2. AstroPortal: A Science Gateway for Large-scale Astronomy Data Analysis

• Dates: June 2005 - Present
• Web Site: http://people.cs.uchicago.edu/~iraicu/projects/Falkon/astro_portal.htm 
• People: Ian Foster, Alex Szalay, Gabriela Turcu
• Contributions: Designed, implemented, and deployed the astronomy gateway to grid resources using the Falkon framework.  The AstroPortal allowed image stacking of objects from the Sloan Digital Sky Survey DR5 to be co-added to aid in finding faint and transient objects.

3. DiPerF: an automated DIstributed PERformance testing Framework

• Dates: September 2003 – May 2005
• Web Site: http://diperf.cs.uchicago.edu
• People: Ian Foster, Catalin Dumitrescu, Matei Ripeanu, Stuart Martin, Jenny Schopf, John Bresnahan
• Contributions: Designed and implemented DiPerF, with the goal to simplify and automate service performance evaluation. DiPerF coordinates a pool of machines that test a target service, collects and aggregates performance metrics, and generates performance statistics. The aggregate data collected provide information on service throughput, on service ‘fairness’ when serving multiple clients concurrently, and on the impact of network latency on service performance. Furthermore, using this data, it is possible to build predictive models that estimate a service performance given the service load.  I performed extensive performance evaluations and scalability studies on the Globus Toolkit.  Specifically, I performed the performance and scalability testing of MDS2 & MDS4, GridFTP, GRAM2, and GRAM4.

4. e3D: energy-efficient Distributed Dynamic Diffusion routing in Wireless Sensor Networks

• Dates: September 2001 – May 2005
• Web Site: http://people.cs.uchicago.edu/~iraicu/projects/wsn.html 
• People: Loren Schwiebert, Scott Fowler, Sandeep K.S. Gupta
• Contributions: One of the limitations of nodes in wireless sensor networks is their inherent limited energy resource.  Besides maximizing the lifetime of the sensor node, it is preferable to distribute the energy dissipated throughout the wireless sensor network in order to minimize maintenance and maximize overall system performance.  We introduce a new algorithm, e3D (energy-efficient Distributed Dynamic Diffusion routing algorithm), and compare it to two other algorithms, namely directed, and random clustering communication.  Our simulation results show that e3D performs comparable to its optimal counterpart while having significantly less overhead. 

• Dates: September 2000 – May 2003
• Web Site: http://people.cs.uchicago.edu/~iraicu/projects/ipv4-6.html  
• People: Sheralli Zeadally, R. Wasseem, Douglas Comer
• Contributions: I investigated the impact of IPv6 on user applications as it compared to IPv4 on various operating systems (Linux, Solaris, and Windows) for TCP and UDP protocols.

Participant Role

6. Swift: Fast, Reliable, Loosely Coupled Parallel Computation

• Dates: December 2006 – Present
• Web Site: http://www.ci.uchicago.edu/swift/
• People: Yong Zhao, Mihael Hategan, Ben Clifford, Ian Foster, Gregor von Laszewski, Tiberiu Stef-Praun, Mike Wilde
• Contributions: Scientific computation often involves thousands or even millions of tasks operating on large quantities of data, such data is often diversely structured and stored in heterogeneous physical formats, and scientists must specify and run such computations over extended periods on collections of compute, storage and network resources that frequently change constantly. Swift is a parallel programming tool specifically designed to address such challenges for concise specification, and fast and reliable execution of large-scale scientific computation.  Specifically, I worked closely with the Swift team to integrate Falkon into Swift and to make Falkon a turn-key solution for the Swift user community.

7. ServMark: an Architecture for Testing Grid Services

• Dates: January 2006 – Present
• Web Site: http://dev.globus.org/wiki/Incubator/ServMark
• People: Catalin Dumitrescu, Alexandru Iosup, H. Mohamed, Dick H.J. Epema, Matei Ripeanu, Nicolae Tapus, Ian Foster
• Contributions: ServMark is the result of the integration of the GrenchMark project and DiPerF.  ServMark addresses two orthogonal research questions: (1) How to test a large-scale, distributed, and (grid-)service-based environment? and (2) How to generate realistic testing traces for a wide-range of testing scenarios? My contributions were primarily in the design and its write-up.

8. HOC-SA: Higher-Order Components-Service Architecture

• Dates: June 2006 – December 2007
• Web Site: http://dev.globus.org/wiki/Incubator/HOC-SA
• People: C. Dumitrescu, J. D¨unnweber, P. Luedeking, S. Gorlatch, I. Foster
• Contributions: HOCs (Higher-Order Components) are application-level components; they provide implementations of typical, recurrently used coordination patterns in parallel applications. HOC users implement only application-specific operations and pass them to the HOCs as code parameters. HOC-SA is the Service Architecture for HOCs.  My contributions were primarily in the design of testing, its comparison with other technologies, and its write-up.

9. DI-GRUBER: A Distributed Grid Resource Broker

• Dates: September 2003 – December 2006
• Web Site: http://people.cs.uchicago.edu/~cldumitr/GRUBER/
• People: Ian Foster, Catalin Dumitrescu
• Contributions: DI-GRUBER, an extension to the GRUBER brokering framework, was developed as a distributed grid UUsage SLA-based resource broker that allows multiple decision points to coexist and cooperate in real-time. DI-GRUBER ultimately addresses issues regarding how usage USLAs can be stored, retrieved, and disseminated efficiently in a large distributed environment.  My contributions were primarily in the design of DI-GRUBER, performance evaluation using the DiPerF framework, and its write-up.