CARTIF and ENERGYLAB visit Touro Hydro Power Plant in Spain operated by TASGA

Starting with the work to be done in D-HYDROFLEX project, partners from TASGA hosted CARTIF and ENERGYLAB’s technical partners and guide them through the Touro Hydro Power Plant installations. The visit was of much help to understand the working process of the plant and to develop the IA and control algorithms that will be developed in the project. These algorithms will be of use to increase the knowledge of hybrid power plants in small hydro run-of-river facilities, to increase the of the operation flexibility and to facilitate market penetration of H2 technologies.

One of the tasks in the D-HYDROFLEX project consists of the design of energy and hydrogen production, flow and weather forecasting algorithms. With this objective, the technical partners from CARTIF and EnergyLab made a visit to the hydropowerplant in Salto de Touro, where TASGA, the operator of the powerplant, explained in detail the operation of the plant. 

D-HYDROFLEX is a project financed by the European Commission. The project started the 1st of September of 2023 and aspires to increase the flexibility potential of the existing EU hydro-power fleet and improve the overall annual efficiency of hydroelectric plants based on 3 pillars: flexibility, sustainability, digitization. In it participates seventeen partners from seven different countries and a total of five demonstrators. One of those demonstrators is the hydropowerplant of Salto de Touro, located in the Ulla River (Spain). 

TASGA hosted the visit and showed to CARTIF and EnergyLab teams their management centre, explained the operation of the plant and the current degree of digitalization the plant counts on. All this factor would greatly help the teams to develop the algorithms that will help to increase the plant’s digitalization and help with the planning of the plant operation. The developed solutions will include the analyses of the data coming from the monitoring system, the modelling of the power production using machine learning algorithms and the modelling of the hydrogen and renewable production. 

Share this: