EU Analytics Effort Goes ‘Extreme Scale’
A European Union analytics initiative seeks to forge a new software architecture for what developers dub “extreme-scale” data analytics that would be applied to autonomous transportation and “smart mobility” systems.
As the name suggests, the EU’s ELASTIC (Extreme-ScaLe Big-Data AnalyticS in Fog CompuTIng ECosystems) initiative seeks to develop an agile software architecture in which computing is dynamically distributed to real-time analytics.
Launched in December 2018, the three-year, €5.9 million ($6.4 million) project is being coordinated by the Barcelona Supercomputing Center.
ELASTIC also seeks to address the shortfalls associated with real-time analytics running in the cloud. Program managers note that communications and data movement make real-time analytics difficult.
“In order to provide an improved ecosystem, which considers the full compute continuum, there is a great need for analysis and monitoring tools that support higher-level concerns and non-functional aspects in a comprehensive manner, from the edge to the cloud,” the group said.
A key component of the architecture is a “non-functional requirements” (NFR) tool designed to handle both analytics and service execution. For example, NFR would help transit managers consider “trade-offs between performance, predictability, energy efficiency, communication quality and security,” the group said. “The result of this analysis is a set of possible initial deployment configurations.”
Among the transit applications are obstacle detection and predictive maintenance. The software architecture would combine data from different sensors to help vehicles spot hazards and avoid collisions. The real-time capability would use a platform called the Next Generation Autonomous Positioning system along with the standard Advanced Driving Assistant System.
Project managers announced this week the data analytics platform will be integrated into public trams as part of a smart city effort in Florence, Italy. The goal is a 25 percent reduction in annual incidents on the Tuscan city’s tram system.
Meanwhile, the predictive maintenance capability seeks to track repair needs at an early stage to reduce operational costs and keep transit infrastructure operating for longer periods between overhauls. The predictive analytics tool is expected to result in a 30 percent reduction in standard maintenance costs.
Together, the tools support by the analytics architecture would yield a 5 percent improvement in traffic patterns as measured in terms of interactions between public transit and drivers.