The joint kick-off meeting of eXtreme Data Cloud e DEEP-Hybrid DataCloud projects, both funded by the European Commission in the framework of the Horizon 2020 programme on big data and distributed computing, was recently held in Bologna. The National Institute for Nuclear Physics (INFN) plays a fundamental role in both projects which, together with the EOSC-hub European project, represent the follow-on and extension of the INDIGO-DataCloud project, successfully ended in September 2017 and evaluated by the EC as “outstanding” .
During the kick-off meeting, interactions among the three initiatives were discussed and investigated, with the aim of joining forces and realizing all the possible synergies. The goal is to provide useful and efficient services towards the implementation of the European Open Science Cloud (EOSC), a large e-infrastructure - strongly promoted by the European Commission - for all researchers to store, manage, analyse and re-use their data.
Within the EOSC framework, the INDIGO-DataCloud project, led by INFN, developed many software components for an easy and optimal usage of an hybrid Cloud infrastructure by many and diverse scientific communities. The great success of INDIGO-DataCloud is shown by both the "exceptional results" stated in the project review report issued by the European Commission experts, and by the fact that its follow-on projects were all approved in the H2020 calls, thus allowing to continue its activities and exploit its results.
The EOSC-hub project, coordinated by the EGI Foundation, started on January 1st 2018. With a consortium of 100 partners from more than 50 countries, EOSC-hub brings together an extensive group of national and international service providers to create an integration and management system of the future European Open Science Cloud, called the "Hub". The Hub acts as a central contact point for European researchers and innovators to discover, access, use and reuse a broad spectrum of resources for advanced data-driven research.
With the explicit purpose of reducing the fragmentation of IT facilities and digital tools in Europe, several providers from the EGI Federation, EUDAT CDI, INDIGO-DataCloud and other major European research infrastructures will deliver a common catalogue of research data, services and software for research. For researchers, this will mean a broader access to services supporting their scientific discovery and collaboration across disciplinary and geographical boundaries.
INFN is a key partner of the project; besides supporting many components developed within the INDIGO-DataCloud project, it will contribute to several strategic activities, among which the responsibility of technical coordination.
The eXtreme Data Cloud project (XDC), is coordinated by INFN. Its consortium brings together technology providers with long-standing experience in software development and large research communities belonging to a broad spectrum of data-intensive scientific disciplines, such as Life Science, Biodiversity, Clinical Research, Astrophysics, High Energy Physics and Photon Science. The different research communities provide concrete use cases and heterogeneous requirements for the access to and management of data volumes at an unprecedented, extreme scale. Continuing the efforts of INDIGO-DataCloud in the direction of providing user-friendly, web-based and mobile interfaces, XDC will integrate some “intelligence” on top of data management functionalities to meet the specific needs of scientific communities and implement a more flexible, efficient and scalable computing and storage infrastructure at the European level.
In particular, the XDC mission is to develop scalable technologies for federating storage resources and managing data in both already existing and next generation highly distributed computed environments deployed in Europe, such as the European Open Science Cloud (EOSC), the European HTC Infrastructure (EGI) and the Worldwide LHC Computing Grid (WLCG).
The DEEP-Hybrid DataCloud (DEEP) project, led by the largest public research institution in Spain - the Consejo Superior de Investigaciones Cientìficas (CSIC), will develop and implement the technologies which allow an easy and transparent access to heterogeneous resources in both Cloud and High Performance Computing environments. DEEP will focus on the outcomes of INDIGO-DataCloud for what concerns the tools supporting the analysis of huge amount of data, which currently take place primarily in HPC systems with many difficulties and low portability. In particular, the support for GPUs and low-latency interconnects will be addressed. Moreover, the DEEP project has the ambitious goal of automating the development and delivery of tools for Deep Learning and Machine Learning in several applications.
INFN will coordinate the work package which takes care of the implementation of the Platform as a Service (PaaS) layer, but it will also contribute to the implementation of the Infrastructure as a Service (IaaS) layer. Finally, INFN will be deeply involved in the activities aiming at the exploitation of the frameworks for the analysis of big data through Machine Learning and Deep Learning techniques.
[Fabio Pisa Photography]
