Barbara

ACCIONA spent significant time and resources manually testing water samples in a laboratory to determine chemical concentrations. Due to the time it took to obtain these results, they were often outdated and unreliable. This resulted inadditional costs related to chemical supply and regulatory penalties.By implementing real-time optimized Machine Learning control algorithms at each of its desalination plants, ACCIONA was able to minimize the use of reactive chemicals, eliminate associated regulatory penalties, and provide an efficient edge infrastructure to implement new applications for predictive maintenance, energy efficiency, sensing, optimization or reinforcement learning.

Cuerva a Spanish Grip Operator, was seeking to enhance grid knowledge through the implementation of the AI Energy Forecasting Model to obtain precise forecasts of user demand and energy generation.Cuerva’s grid encompasses over 16,000 diverse supply points, making cloud-based operations intricate and susceptible to issues such as connectivity loss, delays in information transmission, and reliance on centralized infrastructure, which can result in the loss of critical data.To tackle these challenges, the Edge technology has proven to be the sole alternative capable of addressing these issues effectively. It ensures real-time data access and operates in a decentralized manner, minimizing the impact of device failures on the overall functionality of the network.In this successful case, we illustrate how with Barbara DSOs can implement AI directly in substations to accurately predict the demand and production values of consumers linked to the transformation center where an Edge node run by Barbara has been deployed.

Cuerva Distribution needed to have real-time data (<1 minute) from the line cells of its substations and fault detectors in order to obtain instant alerts regarding supply quality: surges or drops in voltages or intensity, neutral currents, etc. Traditionally, all these data are processed through SCADA, a rather rigid system which does not allow for custom events and alarms to be configured. Due to software limitations, it took around 15 minutes for the data to transfer from SCADA to a database.