End User
Veolia
Description
The Heating Demand Forecasting service uses AI-based models (LSTM and XGBoost) to forecast short-term thermal energy demand in the Torrelago district heating network. By integrating historical consumption patterns with external temperature forecast datasets, the service enables proactive decision-making and improved planning of heat production and distribution across the network.
Core Capabilities
Predictive & Prescriptive Analytics
Business Need
Proactive heat production and distribution planning requires advance knowledge of expected thermal demand. Without reliable short-term forecasts, the DHN operator cannot pre-adjust heat generation, anticipate peak periods, or reduce response times to demand variations — all of which affect energy efficiency, comfort, and operational costs.
Key Performance Indicators
Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R²
Validation stability across different seasons
Ability to anticipate peak demand periods
Comparison against baseline persistence models to demonstrate added value
Data Provided
Short-term thermal demand forecast time-series for operational planning
Identification of expected peak demand periods
Scenario analysis outputs for different weather conditions or consumption patterns
Performance accuracy indicators for model reliability monitoring
TEF
TEF DHN