PILOT : A SMART CITY USE-CASE OF CITY-PRIVATE CARS INTERACTION, DEVELOPED ON TOP OF THE CLASS SOFTWARE ARCHITECTURE

The CLASS software architecture framework allows to: (1) develop data-analytics and AI workloads combining different methods such as deep neural networks and extended kalman filters; and (2) efficiently execute them across the compute continuum, i.e., using the edge and cloud computing facilities provided by the city and the vehicles. With this innovative capabilities, our framework allows to collect, process, analyse and store vast amount of geographically-distributed data sources.

The software architecture framework is being evaluated in the Modena Automotive Smart Area (MASA), a real urban laboratory of 1 square kilometer located in the city of Modena. The main objective of the pilot is to enhance the sensing capabilities of the vehicles, i.e., the connected cars, and the city, by fusing multiple data-sources. Upon this, advanced mobility applications are being developed: digital traffic sign, smart parking, air pollution estimation and obstacle detection.

The pilot includes two connected cars equipped with sensors. The data collected from the different sources (e.g. sensors located in the MASA area and the vehicles) is used to generate in real-time, a map of the traffic conditions of the city incorporating the speed, acceleration and trajectory of the vehicles in the MASA.

See the short CLASS videos here: https://class-project.eu/media/videos

The CLASS project has received funding from the European Union’s Horizon 2020 research and innovation program under the grant agreement No 780622.

The objectives of the pilot are to use the CLASS software architecture framework in a real life urban mobility use case in Modena in order to:

• achieve interaction between the city and private vehicles,
• enhance the sensing capabilities of vehicles, while providing sound real-time guarantees,
• conceive a safer and smarter urban mobility environment, with limited road accidents, optimized traffic and parking conditions, and controlled air pollution indicators.

The expected results of the CLASS software architecture are:

• the coordination of edge and cloud computing resources,
• the distribution of big-data workloads with real-time requirements along the compute continuum,
• the combination of data-in-motion and data-at rest analytics,
• the increased productivity in terms of programmability, portability/scalability and (guaranteed) performance.

The KPIs of the employment of the CLASS architecture in the smart city use-case pilot in the City of Modena are:

• 20% increase in the overall traffic management
• 30% increase in the response time of emergency vehicles
• 20% decrease in pollution
• 30% decrease in number of accidents
• 40% decrease in time spent on looking for a parking space