Title: The Information Centric Networking Challenge

Speakers: 

• Ioannis Psaras (University College London, UK)
• Dirk Trossen (University of Cambridge, UK) 

Abstract: In this tutorial, we will start off with a short summary on the evolution of content-based networking through the years, which is necessary in order to understand the foundations of the Information Centric Networking (ICN) pyramid; then we will dive into the details of specific research challenges in ICN. These challenges span from network layer naming and addressing to in-network caching and resource management and further to application layer issues. The open issues in this area far outweigh the solved ones and hence, our discussion and presentation will focus on research directions for future ICN investigations. The tutorial will finish with a hands-on/demo session from the EU PURSUIT project, where initial steps on the actual deployment of ICNs have already been investigated.

Ioannis Psaras received a diploma in Electrical and Computer Engineering from Democritus University of Thrace, Greece in 2004, and the Ph.D. degree from the same institute in 2008. He is currently working as a senior researcher at the Electronic and Electrical Engineering Department of University College London (UCL). His research interests are in the areas of Congestion/Flow Control, Transport-layer Protocols, Space and DeepSpace Communications, Delay-/Disruption-Tolerant Networks (DTNs), User-Provided and User-Centric Networks and Content-Centric Networks (CCNs). Further information can be found at: www.ee.ucl.ac.uk/~uceeips/.

Dirk Trossen, Senior Researcher in the Computer Laboratory at Cambridge University, has more than ten years of experience in network architectures and wireless technology. He is one of the main drivers of the EIFFEL think tank. Dirk held prior positions as a Chief Researcher with BT Research and as a Principal Scientist at Nokia Research. He is also a research affiliate with the Advanced Network Architecture group at MIT CSAIL. He holds a Ph.D. degree in Computer Science from Technical University of Aachen, Germany. He published more than 60 peer-reviewed papers in international conferences and journals and has currently 25 international patents.

TM-2 Morning, September 7, 2012: 09:00-12:30h

Title: Dynamic Workflow Composition in Service Oriented Architecture

Speakers:

• Rob van der Mei (CWI and VU University of Amsterdam, NL)
• Miroslav Zivkovic (TNO, NL)

Abstract: Future Internet has emerged as a novel infrastructure linked to objects and things of the real world to meet the changing global needs of business and society. Future Internet applications should be able to handle dynamic and continuous changes, e.g. in the provisioning of services, availability of things and contents, connectivity of networks, diversity of user devices and so on. Service Oriented Architecture (SOA) and Cloud Computing will without any further doubt play a very significant role in such a Future Internet infrastructure. In this tutorial we will first give an overview of main concepts within SOA and Cloud Computing. We will then focus on the issue of services composition and QoS control within SOA, and will survey methods and algorithms for QoS--aware workflow composition. We will address the static and dynamic  service composition, as well as revenue optimization for service providers. We will also cover emerging aspects and future challenges within the SOA QoS control.

Bios

Rob van der Mei received his M.Sc. degrees in Mathematics and in Econometrics, both from the Free University Amsterdam. After having obtained his Ph.D. degree from University of Tilburg, The Netherlands, in 1995, he had several research positions in the USA, and became a senior technical staff member at AT&T Labs, Department of Performance Analysis and Network Planning, Holmdel, NJ, USA, in 1996. In 1999 he moved back to his home country to join KPN Research (TNO ICT, since 2002) as Senior Innovator. In 2004, he joined the Centre for Mathematics and Computer Science (CWI) heading the research cluster Probability, Networks and Algorithms. His research interests include performance modeling and analysis of communication networks and distributed ICT systems, queueing theory, stochastic scheduling, grid computing, logistics and revenue management.

Miroslav Zivkovic received the engineering degree in electronics and telecommunications from the Faculty of Electrical Engineering, University of Belgrade, Serbia. He was with Bell Labs, The Netherlands, where he contributed significantly to the area of dynamic spectrum management for DSL systems and to the area of intelligent service platforms. He is currently with TNO, Delft, The Netherlands. His current research interests include performance analysis of service-oriented architecture systems and composite web services.

TA-1 Afternoon, September 7, 2012: 13:30-17:00h

Title: Recent Advances in Age and Size-based Scheduling

Speakers: Samuli Aalto (Aalto University, Finland)

Abstract: We will start the tutorial by presenting a selection of classical scheduling results for single-server and multi-server queues. Challenges brought by modern communications systems have inspired researchers to develop scheduling theory beyond the classical models and results. One example of the need for more sophisticated scheduling schemes is given by the highly varying service requirement distributions, such as Pareto, used to describe, e.g., flow sizes in the Internet. In such a case, size and age-based scheduling policies are essential when optimizing the system performance. Unfortunately, the optimal non-anticipating policy for a single-server queue, the Gittins index policy, is defined in a highly implicit way. In this tutorial, we illustrate the properties of the Gittins index itself, and then utilize these properties to characterize the age-based Gittins index policy for various service requirement distribution classes. Finally, we consider opportunistic scheduling policies and present one approach to determine the optimal trade-off between size-based and opportunistic scheduling.

Bio

Samuli Aalto received the M.Sc. and Ph.D. degrees in mathematics from University of Helsinki in 1984 and 1998, respectively. From 1984 to 1997, he was with VTT Technical Research Centre of Finland as a research scientist in the area of telecommunications. Since 1997, he has been with TKK Helsinki University of Technology, which is now part of Aalto University in Finland. Currently he acts as a professor (pro tem) leading the Performance Analysis research group in the Department of Communications and Networking. Prof. Aalto has published more than 60 papers in refereed international scientific journals and conference proceedings. His current research interests include queueing theory, scheduling theory, and performance analysis of modern communications networks.