Session 5 "e-Infrastructure Challenges"
Session Chair: Hrachya Astsatryan (ASNET-AM)
The QUANTICOL project : Understanding Collective Adaptive Systems
Presenter: Nicolas Gast (INRIA, France)
INDIGO-DataCloud, an open solution for the exploitation of distributed Cloud resources.
Presenter: Davide Salomoni (INFN-CNAF, Italy)
ESiWACE: Centre of Excellence in Simulation of Weather and Climate in Europe
Presenter: Kim Serradell Maronda (Barcelona Supercomputing Centre, Spain)
Smart urban transport systems and smart grids are two examples of collective adaptive systems. They consist of a large number of heterogeneous entities with decentralized control and varying degrees of complex autonomous behaviour. The QUANTICOL project has sought to support designers and operators of collective adaptive systems (CAS) through the construction and analysis of models. In this talk, I will present the theoretical and practical tools that we developed during the project and I will present some of the applications of our work to develop a smarter and more robust electrical distribution network.
Helvetica Light is an easy to read font, with tall and narrow letters, that works well on almost every site.
Helvetica Light is an easy to read font, with tall and narrow letters, that works well on almost every site.
In this talk we will present the main goals, structure and first results of the ESiWACE Centre of Excellence. ESiWACE wants to substantially improve efficiency and productivity of numerical weather and climate simulation on high-performance computing platforms by supporting the end-to-end workflow of global Earth system modelling in HPC environment. Moreover, ESiWACE will address a wide range of challenges, from the development of specific software products to the deployment of user facing services for both, computing and storage. Besides, with regard to the upcoming exascale era, ESiWACE will establish demonstrator simulations, which will be run at highest affordable resolutions (target 1km). This will yield insights into the computability of configurations that will be sufficient to address key scientific challenges in weather and climate prediction.
Current e-infrastructures face multiple challenges. Users increasingly need to exploit and integrate multiple, distributed resources, be they related to compute or data; they want to do this regardless of the actual resource providers, which can be public, private or both; users also typically want to avoid proprietary solutions, which can lead to lock-ins and/or to privacy concerns. And, while in the past the focus of e-infrastructures was on providing simple physical or virtual resources, the Cloud paradigm requires a shift away from the infrastructural layer (which can and should be interchangeable) to the application domain, through open, programmable and scalable Platform-as-a-Service and Software-as-a-Service stacks.
This talk will discuss the solutions to these problems offered by INDIGO-DataCloud, an H2020 project with a Consortium of 26 European academic and industrial partners. INDIGO developed an open source platform tailored to science, but applicable to other domains as well.
Examples of concrete usage of INDIGO solutions in applications belonging to multiple scientific communities will be presented, together with cases of adoption of INDIGO components by commercial companies. The talk will end with the description of three recently approved H2020 projects that substantially derive, adopt or extend components, know-how and results coming from INDIGO-DataCloud, and that will concretely contribute to building a European Open Science Cloud.
