During the second period, ELASTIC focused on: (1) the refinement and integration of the required SW components into the ELASTIC SA; (2) the development of three advanced mobility applications extreme-scale big-data analytics requirements; and (3) the deployment of the necessary sensing, communication and computing infrastructure for the use cases.
The final release of the ELASTIC SA was delivered, prioritising SW components owned by the members of the ELASTIC consortium or offered as open-source components with a large community behind them, with the objective of reducing the time-to-market and maximize exploitation opportunities. The ELASTIC SA consists of four layers:
1. A Distributed Data Analytics Platform layer, for data accessibility across the compute continuum, supporting data-in-motion and data-at-rest analytics
2. An Orchestration layer, responsible for deploying and distributing extreme-scale big-data analytics workflows across the compute continuum, while guaranteeing their non-functional requirements
3. A Non-functional Requirement Analysis layer, for the continuous monitoring of the compute continuum and analytics execution, informing the Orchestrator about the operational requirements across the dimensions of time, energy, communication quality and security
4. A Fog Computing Platform layer that implements the compute continuum, including the monitoring, communication and data routing capabilities needed by the other layers
The ELASTIC SA has been used to develop, deploy and execute three advanced mobility applications, featuring advanced big-data analytics methods such as deep neural networks for the detection of objects, analytics methods for tracking and GPS object localization, data fusion methods, semantic models for the detection of events of interest, aggregation and learning methods for pattern extraction. The ELASTIC use cases have been deployed into the tram stops of Batoni, Arcipressi and Resistenza, equipped with cameras and distributed GPU-enabled edge computing nodes, connection to a traffic light manager module to receive the real-time status of the traffic lights in the area, and a V2X module for the transmission of real-time alerts to connected cars
For the extraction of data from the tramway network, three tram vehicles have been equipped with sensors (cameras, radars, LiDARs, etc.) for object detection and autonomous position estimation, whereas a maintenance vehicle has been equipped with cameras, GPS and laser scanner to monitor the status of the tracks. The trams have been also equipped with GPU-enabled edge computing platforms, supporting Wi-Fi and 4G connectivity for the transmission of data to the edge/cloud infrastructure
At the cloud, a private cloud server have been setup, for the aggregation of data from the trams (via 4G), the maintenance vehicle (via WiFi) and the edge infrastructure (via fiber)
The project results have been widely disseminated, with participation in a total of 26 public events, including a keynote talk, booths at international and industrial exhibitions (e.g. Smart City Expo), presentations at conferences, 6 scientific publications, over 110 press mentions, etc. A final full-day hybrid event was organized in Florence (combining in-person attendance and live streaming options), presenting the final ELASTIC outcomes to the public and the local authorities
In terms of exploitation, 33 foregrounds have been identified, 10 of those with a TRL above/equal to 6. Joint plans were also identified, mainly to distribute the open-source software foreground and potentially commercialize some software components via the Nuvla marketplace
