CLASS aims to develop a novel software architecture to help programmers and big data practitioners to combine data-in-motion and data-at-rest analysis, by efficiently distributing data and process mining along the compute continuum, while providing real-time guarantees.
Moreover, CLASS aims to take full advantage of novel parallel hardware and software architectures for an efficient usage of computing resources to achieve the level of performance required by future smart systems. To demonstrate the feasibility of such architecture, a heterogeneous set of big data analytics tools are planned to be deployed, providing integrated services to consumers.
The vision of CLASS is that the pressure that the newest smart systems requiring big data analytics and realtime requirements will put on the compute continuum, can be efficiently addressed by devising a full distributed system architectures in which a combined data-in-motion and data-at-rest analytics can be efficiently performed by coordinating edge and cloud computing resources.
CLASS aims to implement its innovative framework on a use-case based on a real Smart City scenario for nextgeneration automotive applications, adopting innovative distributed architectures from the high-performance computing (HPC) domain, as well as highly-parallel and energy efficient hardware platforms from the embedded domain. In order to do so, it plans to combine multi-dimensional and multidisciplinary contexts, from artificial intelligence, data storage and data mining, to address the big data challenge of future smart cities.