End User
Veolia
Description
Energy demand forecasting is a critical AI service that predicts future energy consumption patterns in DHCN networks. It uses historical data, weather forecasts, and building usage patterns to optimize energy distribution and reduce operational costs while maintaining user comfort levels.
Core Capabilities
Monitoring & Anomaly Detection
Predictive & Prescriptive Analytics
Optimization & Decision Support
Automation & Control Systems
Data Integration & Interoperability
User Interface & Visualization
Business Need
To reduce costs efficience and improve efficiency in district heating systems.
Key Performance Indicators
Forecast accuracy (Mean error % between simulated data and real demand data)
Effective prediction time horizon (hours/days)
Data Provided
Real-time data streams through Hubgrade, SQL databases storing historical data.
Over 700 variables collected every 15 minutes.
Variables map
Data collected at 15-minute intervals at both district level (boiler rooms) and building level (substations).
TEF
TEF DHN