Cloud-native infrastructure for big data and energy efficiency

· Fondo europeo di sviluppo regionale ·

HelioSwitch leverages cloud-native technologies to modernize its energy data infrastructure, integrating advanced analytics and secure automation to support its long-term strategic growth.

HelioSwitch is introducing cloud-native solutions for the management and processing of energy big data, leveraging a robust cloud ecosystem. A scalable OLAP database serves as the central hub for real-time analysis, supported by object storage for archiving and backup, identity and access management (IAM) for secure access control, and comprehensive observability tools for continuous performance oversight. Customer data is being acquired through standardized, reliable, and modular connectors. These technologies, selected for their scalability, security, integration capabilities, and cost-efficiency, are modernizing the existing infrastructure and establishing the foundation for the automation and future self-service platform outlined in the strategic plan.

Generation of hydro inflow datasets

· ENTSO-E ·

The aim of the project was to generate a consistent hydro inflow dataset that could be used by ENTSO-E in all power systems studies, for more than 30 countries.

HelioSwitch developed algorithms for regression and analysis of hydroelectric power plant production and river discharge data. The tool developed involves the following 3 main steps:

processing of hydroelectric generation data which includes, on top of standard quality check and anomaly detection, an advanced frequency analysis to detect spurious signal in the data provided;
extraction of location-specific river discharge data coupled with a latent space analysis, highlighting the physical phenomenon underlying the raw data;
generation of nonlinear transfer functions for each hydroelectric power plant between river discharge data, and the water inflow at the power plants, inferred from their production.

Hydroelectric run-of-river generation forecasting

· Terna ·

HelioSwitch developed high-scalability probabilistic machine learning models for Terna, aimed at forecasting the generation of Italy's run-of-river hydroelectric power plants.

Our team successfully developed a scalable algorithm that predicts power production from run-of-river hydropower plants, utilizing minimal registry information (location, size, plant type), weather data, and historical generation data. The algorithm provided hourly forecasts for a one-week prediction horizon and evaluated the possibility of extending the horizon to two weeks.

Delta-PRA reconstruction algorithms

· Illumia ·

HelioSwitch developed and tested algorithms to reconstruct the hourly values of PODs leaving PRA aggregation from their monthly integrals.

We developed and tested machine learning methodologies with Illumia to infer the hourly dynamics of PODs in the delta-PRA, starting from their monthly integral, in order to improve PRA forecast accuracy.