From Grid5000
Jump to: navigation, search

keynote 1 - Self-organizing Virtual Private Networks and Applications


Virtualization technologies have witnessed a renaissance in the recent past, fueling the development of Infrastructure-as-a-Service (IaaS) systems that provide the foundation for on-demand provisioning and cloud computing. While virtual machine (VM) technologies decouple and isolate processing within the scope of a single physical computer, virtual networking provide the basis for decoupling and isolating communication among virtualized resources, enabling cloud infrastructures that can seamlessly span geographically-dispersed data centers (possibly across multiple institutions), and providing end-to-end private communication among peers constrained by network address translation (NAT) and firewall devices which are increasingly common in the Internet. In this talk I will overview research efforts from my group on the use of self-organizing peer-to-peer (P2P) techniques to address challenges in network virtualization, where the P2P overlay and virtual network devices are used as a basis for capture, encapsulation, and resilient and scalable routing of virtual network packets, as well as in the support for the assignment of network addresses and their mappings. In particular, I will overview the IP-over-P2P (IPOP) system architecture, virtual appliances for distributed computing on virtual private clusters across multiple cloud infrastructures, and some of its applications in projects including FutureGrid.

Dr. Renato J. Figueiredo is Associate Professor of Electrical and Computer Engineering at the University of Florida. He is also affiliated with the Advanced Computing and Information Systems (ACIS) Laboratory, and with the NSF I/UCRC Center for Autonomic Computing (CAC). Further information on

keynote 2 - Data Mining and Knowledge Discovery in Databases


<<Customers Who Bought This Item Also Bought...>>. This sentence has became usual in e-business. Generally, it comes with recommendations that have been built by specific analyses on customers' behaviours. Transforming data into actionable knowledge is the main goal of KDD, or Knowledge Discovery in Databases. KDD is actually the process of knowledge extraction from very large amounts of data. In this talk, I will show the basis of this domain and give details about some well known problems of data mining. These problems are related to pattern extraction in databases, where a pattern might correspond to different definitions such as frequent correlation, frequent sequences or clustering. I will discuss potential applications for these techniques and eventually give current research tracks for data mining in highly distributed environments such as cloud and P2P networks.

Dr. Florent Masseglia is currently a researcher for INRIA (Sophia Antipolis, France). He did research work in the Data Mining Group at the LIRMM ( Montpellier , France ) from 1998 to 2002 and received a Ph.D. in computer science from Versailles University , France in 2002. His research interests include data mining (particularly sequential patterns and applications such as Web Usage Mining), data streams and databases. He is one of the 5 persons in charge for the French working group on mining complex data. He has co-edited a special issue of the RNTI journal (Cépaduès ed.) about mining complex data, co-chaired the 2nd French workshop on mining complex data, and co-chaired the 6th and 7th editions of the international workshop on “Multimedia Data Mining” in conjunction with the KDD conference. He is one of the guest editors of two special issues on this topic in the IEEE TMM and the MTAP journal. Florent Masseglia is co-editor of two books on data mining ("Data Mining Patterns: New Methods and Applications" and "Successes and New Directions in Data Mining"). He is reviewer for a dozen of major international journals. Further information on

keynote 3 - Autonomic application management on a federated cloud using CometCloud


Cloud computing has emerged as a dominant paradigm that has been widely adopted by enterprises. Clouds provide on-demand access to computing utilities, an abstraction of unlimited computing resources, and support for on-demand scale up, scale down and scale out. Clouds are also rapidly joining high-performance computing system, clusters and Grids as viable platforms for scientific exploration and discovery. As a result, understanding application formulations and usage modes that are meaningful in such a hybrid infrastructure, and how application workflows can effectively utilize it, is critical. In this talk, I will l explore the role of clouds in science and engineering. I will also explore how science and engineering applications can benefit from clouds and how the cloud abstraction can lead to new paradigms and practices with the focus on Cloud federation. This talk is based on research that is part of the CometCloud autonomic cloud-computing project at the NSF Center for Cloud and Autonomic Computing at Rutgers.

CometCloud is an autonomic framework for enabling real-world applications on dynamically federated, hybrid infrastructure integrating (public & private) clouds, data-centers and Grids. Further information on the CometCloud website.

Dr. Ivan Rodero is currently a Research Associate at the Cloud and Autonomic Computing Center (CAC) and at Rutgers Discovery Informatics Institute (RDI2) lead by Prof. Manish Parashar at Rutgers, the State University of New Jersey. He received an integrated BS and MS degree in Computer Science and Engineering in 2004 and a PhD degree in February 2009 from Technical University of Ca talonia (UPC). His research interests are in the broad area of parallel and distributed computing and include high performance computing, autonomic computing, Grid computing, Cloud computing, virtualization, data analytics and green computing. His current research activities are in the extremely important area of Green Computing with a specific focus on energy-efficient High Performance Computing (GreenHPC) and virtual machine management...

keynote 4 - Cloud Resource Management: an Experimental View from TU Delft



Dr. Alexandru Iosup is Assistant Professor (Universitair Docent) with the Parallel and Distributed Systems (PDS) Group of the Faculty of Engineering, Mathematics and Computer Science (EWI), TU Delft. Further information on"