Smart Energy Grid Active Monitoring/Control Living Lab

This use case is expected to implement a smart energy pilot implemented by ASM, the Terni municipal electricity and gas distribution network operator, and EMOT in Terni (Italy). The trial will demonstrate a) the capability of smart grid asset performance management and b) creating human-centred smart micro-contracts and micro-payments in a fully distributed energy marketplace. The use case will be hosted in the real ASM Smart Grid Active Network in the region of Umbria. The pilot will include smart meters, photovoltaic cell controllers, energy customers (i.e. ASM offices), Electric Vehicles (EV) and EV Chargers in the area of Terni (Italy). The Terni pilot will utilize 4 substations and focus on the Medium Voltage/Low Voltage network branch managed by the SCOV secondary substation, which serves a 200 kW Photovoltaic local generation plant, which often has an electricity surplus, generated from fluctuating renewable energy sources (RES). Moreover, a fleet of six leased EVs (Renault Zone), offered by EMOT will be part of the pilot infrastructure together with at least 3 smart EV chargers (one 52 kW fast charger and two 22 kW ones).

Use case Applications

  • Move from Passive to Active Smart Grid Monitoring & Control:ASM aims to offer breakthrough features in smart grid protection including voltage quality analysis functions (power quality), micro synchro phasor measurement for advanced grid monitoring. It will be based on an innovative high-tech power sensor, which realises advanced protection for MV/LV substation breakers.
  • Driver-friendly dispatchable EV charging:In this scenario, EMOT will realise driver-friendly scenarios for dispatchable charging of EVs based on energy demand-response due to renewable energy sources along with human-centred smart micro-contracts and micro-payments.In both use cases, we will investigate advanced AI/ML-based analytics to train models tracking the health of the grid along with urban traffic scenario and traffic predictions to provide timely alarms when the system is approaching unstable operational boundaries, which could lead to failures. The stream of data will be used at different levels at the same time:
    • At IoT level, for identifying potential local discrepancies using already trained ML models
    • At Edge cloud, for applications such as protection, power quality and partial discharge detection
    • At cloud level, transmitting electricity voltage patterns in real time to enable functionalities that can be performed only by elaborating streams of elemental or pre-elaborated data coming from different locations


Both use cases will be based on the concept of Digital Twin for electrical distribution network and Electrical Vehicles, significantly useful for the grid operation, along with latest cybersecurity requirements.

IoT-NGIN as Differentiator at Smart Grid Active Monitoring/Control Living Lab

  • Smart Grid Active Monitoring/Control using federated ML hosted on the IoT nodes, in the edge and at the cloud
  • Deal with several thousands of nodes using the digital twin concept
  • Use advanced AI/ML-based analytics to create models that indicate that maintenance is required before obvious performance degradation or even failure takes place
  • Use advanced AI/ML-based analytics to create models that indicate the health of the grid and provide timely alarms when the system is approaching unstable operational boundaries, which could lead to failures