Project description
Reducing energy consumption in data operations
Big data analytics collects, examines and analyses large amounts of data. To extract insights from this data, it must flow seamlessly between edges and clouds across a broad range of work locations and environments. This process consumes a lot of energy. As a result, national grids generate considerable carbon emissions. The EU-funded GLACIATION project aims to develop a novel distributed knowledge graph that stretches across the edge-core-cloud architecture. Knowledge graphs are a flexible means to represent interlinked information about almost anything. GLACIATION will optimise the location where analytics are performed to significantly reduce power consumption. Its metadata framework will deliver tools that ensure privacy and trust in data operations.
Objective
From edge to cloud, big data analytics is growing fast, and its energy consumption has become a reason of concern for national grids and they generate significant carbon emissions. The GLACIATION project aims to address this issue through energy-efficient privacy preserving data operations. By developing a novel Distributed Knowledge Graph (DKG) that stretches across the edge-core-cloud architecture, reduction in the energy consumption for data processing will be achieved through AI enforced minimal data movement operations. GLACIATION will achieve significant power consumption reduction through optimizing the location where analytics are carried out and where data is placed. The projects Metadata framework will provide tools that incorporate privacy and trust aspects in the data operations. GLACIATION is demonstrated on three relevant industry settings which benefit from optimized data movement and power consumption reduction. More specifically, GLACIATION use cases cover public-service, manufacturing, energy and enterprise data analytics.
Fields of science
Keywords
Programme(s)
Funding Scheme
HORIZON-RIA - HORIZON Research and Innovation ActionsCoordinator
00187 Roma
Italy