Descrizione del progetto
Una nuova piattaforma che consentirà l’elaborazione in prossimità dei dati
L’elaborazione in prossimità dei dati (near-data), ovvero il posizionamento della potenza di elaborazione vicino ai dati anziché l’invio dei dati al processore, attenua le sfide associate al costoso spostamento di volumi estremamente elevati di dati. Il progetto NEARDATA, finanziato dall’UE, progetterà una piattaforma di elaborazione in prossimità dei dati per consentire il consumo, l’estrazione e l’elaborazione di dati distribuiti e federati. La piattaforma prevista eliminerà la necessità di ottimizzare la logistica dell’accesso ai dati tra sedi e pool di dati eterogenei. Ospiterà un servizio dati intermedio che fornirà connettori serverless per ottimizzare le operazioni di gestione dei dati e le query interattive. Saranno supportati flussi video ed eventi in tempo reale. In definitiva, la piattaforma ospiterà un servizio di intermediazione di dati, che consentirà la condivisione di dati affidabili e l’orchestrazione di canali di dati attraverso il continuum informatico.
Obiettivo
The main goal is to design an Extreme near-data platform to enable consumption, mining and processing of dis-
tributed and federated data without needing to master the logistics of data access across heterogeneous data
locations and pools. We go beyond traditional passive or bulk data ingested from storage systems towards next
generation near-data processing platforms both in the Cloud and in the Edge. In our platform, Extreme Data in-
cludes both metadata and trustworthy data connectors enabling advanced data management operations like data
discovery, mining, and filtering from heterogeneous data sources.
The three core objectives are:
O-1 Provide high-performance near-data processing for Extreme Data Types: The first objective is to create a
novel intermediary data service (XtremeDataHub) providing serverless data connectors that optimize data management operations
(partitioning, filtering, transformation, aggregation) and interactive queries (search, discovery, matching,
multi-object queries) to efficiently present data to analytics platforms. Our data connectors facilitate a elas-
tic data-driven process-then-compute paradigm which significantly reduces data communication on the
data interconnect, ultimately resulting in higher overall data throughput.
O-2 Support real-time video streams but also event streams that must be ingested and processed very fast to
Object Storage: The second objective is to seamlessly combine streaming and batch data processing for
analytics. To this end, we will develop stream data connectors deployed as stream operators offering very
fast stateful computations over low-latency event and video streams.
O-3 The third objective is to create a Data Broker service enabling trustworthy data sharing and confidential orchestration of data pipelines across the Compute Continuum. We will provide secure data orchestration, transfer, processing and access thanks to Trusted Execution Environments (TEEs) and federated learning architectures.
Programma(i)
Argomento(i)
Meccanismo di finanziamento
HORIZON-RIA - HORIZON Research and Innovation ActionsCoordinatore
43003 Tarragona
Spagna