Skip to main content

Cross-functional AI-based predictive analytics to support integrated DSOs asset management and network operation

The aim is to support a condition-based and risk-based maintenance of both existing and innovative power components, as well as for the new digital environment.


Business Category

What is the challenge that is being addressed?

ASM multi-utility operates electricity and water networks in Terni (Italy). As DSO operating MV/LV power network, ASM faces already several network stability problems to the power distribution grid, due to the increasing share of intermittent generation from renewable energy and to the new loads as energy storage and electric mobility which are modifying the operating conditions of the assets originally designed for almost steady and unidirectional power flow. In the municipality of Terni (Italy), 65,000 LV users are supplied by means of about 600 secondary substations, with a total installed capacity of about 250 MW; the average daily energy distributed is about 890 MWh, a notable amount of embedded generation is also connected to the grid. The embedded generation is increasing year by year and it has changed the energy paradigm, from the traditional unidirectional flow of energy and communication to a bidirectional power flow.

The available pilot infrastructure consists of more than 150 next generation IoT- smart meters which provides near real time digital energy consumption measurement from business and residential consumers, two concentrator-level PMUs deployed within the H2020 SUCCESS project, two secondary substations equipped with RTUs and other digital sensors, deployed with a view to increase the LV network observability.


What is the AI solution the project plans to implement?

Data-driven predictive analytics will be used for the anticipated prediction of transformer asset failures in the secondary substations and lines at LV level, and will support the efficient management of the infrastructure to increase the lifetime of equipment and reduce service interruption times, hence supporting optimised grid operation. Near real time smart meters installed at different type of customers (e.g., domestic, commercial public services, industries) and low-cost PMUs deployed at concentrator level will be leveraged and integrated with off-grid data. Secondly predictive analytics capabilities for optimal grid operation will be deployed through cross-functional integration of finer-grained digital smart meters data with smart substation failure prediction and district-level existing PMUs monitoring device with a view to predict network loads in Low Voltage branches of the network and support optimal grid network operation.


Who will help implement this solution?

This pilot is implemented within the framework of the “I-NΕRGΥ: Artificial Intelligence for Next Generation Energy” Project. The I-NERGY Project has received funding from the European Union's Horizon 2020 Research and Innovation programme under grant agreement No. 101016508.


The responsible partner for this Use Case is ASM (


Learn more about I-NERGY pilots here: