Speaker
Description
Modern scientific projects generate a huge amount of data that needs to be stored, processed and analyzed. It is often impossible to solve such tasks within a single scientific center. Therefore, distributed resources are combined into a single infrastructure using communication channels and specialized software. One of the important preliminary steps in building such an infrastructure is to study existing solutions and select a suitable model and algorithms for distributed data storage, processing and analysis. Building a distributed infrastructure requires software capable of solving tasks such as authentication and authorization; creation of an information system and monitoring tools; management of computing tasks, data storage and transmission. To create a CERN-JINR-INP-KazNU center for large data volumes storage, processing and analysis, a study of existing solutions was carried out and a particular model was selected
