Load and generation forecasting
Forecasts of demand and renewable output to plan networks and trading.
The problem
Variable renewables and new demand make traditional forecasts less reliable.
Data we need
- Meter and SCADA history
- Weather data and forecasts
- Calendar and event data
How it works
- Assemble historical load and generation
- Build forecasting models by region and horizon
- Backtest against past seasons
- Publish forecasts to planning systems
- Monitor accuracy and retrain
What it changes
Targets are agreed with you before we build, and measured on your data before release.
- More accurate short-term planning
- Fewer balancing costs
- Earlier warning of network constraints
Time series and forecasting
Demand, load and failure forecasting from sensors, meters and transaction history.
- Temporal CNNs
- Prophet-style models
- Anomaly detection