The novel ELASTIC software architecture, designed to satisfy the performance requirements of extreme-scale analytics through a novel elasticity concept that distributes workloads across the compute continuum, has been tested in a smart mobility use case deployed in the metropolitan area of Florence (Italy).

Specifically, ELASTIC provides the required scalable computing infrastructure to the Florence tramway network, enhancing the tramway public transportation services as well as its interaction with the private vehicle transportation. The new elasticity concept enables the efficient processing, through extreme-scale analytics, of multiple and heterogeneous streams of data collected from an extensive deployment of Internet of Things (IoT) sensors, located on board the tram vehicles, along the tramway lines, as well as on specific urban spots around the tram stations (e.g., traffic lights). At the same time, the proposed architecture guarantees additional properties, known as non-functional requirements, which are inherited by the tramway system. In this specific use case, the desired non-functional requirements refer to the system operation with real-time guarantees, enhanced energy efficiency, high communication quality and security.


The ELASTIC smart city use case


The output of the real-time, secure and energy efficient extreme-scale analytics solutions enabled by ELASTIC is, in turn, used to improve the overall Florence transportation network performance, thus enhancing the quality of life of citizens in terms of safe mobility and service availability. Furthermore, the fulfilment of the non-functional properties is a significant step towards fully autonomous, highly reliable and efficient public transportation systems.


Screenshot of smart sensor video used in ELASTIC


As the project aims at developing the challenging software architecture needed to implement the next-generation urban mobility applications supporting extreme-scale analytics, three specific applications have been carefully identified to assess and highlight the benefits of ELASTIC technology for newly conceived tramway solutions:

Next Generation Autonomous Positioning (NGAP) and Advanced Driving Assistant System (ADAS)

The first use case application is a combination of two complementary functionalities, namely the NGAP and the ADAS, aiming to provide accurate information on the tram position and assist drivers in critical situations by informing them in real-time on the presence of obstacles along the rail, thus enhancing the passengers’ and citizens’  safety.

The NGAP enables the accurate and real-time detection of the tram position along the rail through data collected only from on-board sensors: inertial measurement units (IMU), satellite positioning information (GNSS) and RADAR. The positioning information are estimated on-board of the tram and can be sent, through a reliable connection, to ground systems.
The ADAS implements the obstacle detection and collision avoidance functionalities based on an innovative data fusion algorithm, combining the outputs of multiple sensors including RADARs, cameras and Light Detection And Ranging (LiDAR) detectors. Data processing also includes complex algorithms for homography, data association, multi-target tracking, unscented Kalman filters and collision checking. Deep Neural Network methods are also applied, taking benefit of data collected by sensors installed on tram vehicle on service.

In ELASTIC, data from additional sources, such as fixed sensors placed at strategic positions (e.g., road crossings), has also been integrated to increase the reliability of the system


Predictive maintenance

Defective assets on the rail track represent a significant cause of hold ups on most rail and tram networks, causing one third of the delays and sometimes trams’ suspensions, thus impacting citizens’ expectations and the normal operation of cities. Therefore, the early detection of symptoms associated with possible rail track wear is fundamental in order to resolve such problems as soon as possible, and even completely prevent them if possible.

The predictive maintenance application monitors the rail track status and profile, enabling the identification of changes in equipment behavior that foreshadow failures. The application also provides recommendations, enabling maintenance teams to carry out remedial work before the asset starts to fail and allowing for proper planning for restoring the rails to the best environmental conditions for any weld overlays. Finally, the power consumption profile of the trams also is monitored, in order to potentially minimize consumption and have an environmentally positive impact.


Predictive Maintenance

Interaction between the public and private transport in the City of Florence

In urban areas, public and private transport are continuously interacting, and high capacity public transport is typically granted a higher priority. However, such policies do not take into account the specific traffic dynamics of different scenarios. The increasing deployment of IoT solutions is providing cities with a dense network of sensors collecting different types of data that can be used to monitor performance of mobility services and their impact (traffic flows, travel times, air quality, etc.). ELASTIC uses this information to enhance the quality of the city traffic management through the application of extreme data analytics, providing valuable outputs for both users and operators that enables them to:

(1) identify critical situations (e.g., vehicles crossing the intersection with the tram line despite having a red traffic light),

(2) optimize the local traffic regulation strategies (e.g., reduce the waiting time of cars at tram crossings through improved light priority management, or slow down trams to reduce a queue of waiting vehicles under traffic congestion, etc.)

The ELASTIC framework for enhancing the interaction between different transportation networks (i.e., public and private) through real-time analytics has been used as a reference for the Florence tramway system for the implementation of new features and mobility services in the future.

Interaction tram and pedestrian