End User
UTBM
Description
The Multi-Energy Demand Forecasting service delivers AI-driven forecasts of electricity and hydrogen demand using time-series data from integrated energy systems. Based on advanced deep learning architectures (LSTM, TCN, Transformers), the service models interdependencies between electricity and hydrogen demand across coupled systems such as microgrids, industrial facilities, and energy hubs, supporting operational planning and resource allocation.
Core Capabilities
Predictive & Prescriptive Analytics
Business Need
Multi-energy systems require coordinated management of electricity and hydrogen demand, but conventional forecasting tools address each energy carrier independently and cannot capture cross-carrier dependencies. Accurate coupled forecasting enables improved coordination, reduced imbalance, and more efficient resource allocation across energy system operators managing both electricity and hydrogen.
Key Performance Indicators
MSE, RMSE, MAE, and R² for electricity and hydrogen demand predictions separately
Visual comparison of predicted vs. observed demand profiles for pattern quality assessment
Robustness across short-term operational and longer-term planning horizons
Data Provided
Time-indexed forecasts of electricity demand and hydrogen consumption over predefined horizons
Note: Service currently in development (wish list status); not yet fully implemented
Inputs: electrical load profiles from Building F platform + hydrogen demand data or proxy datasets
TEF
TEF H2