Forecast window
Price outlook for the next two weeks, hour by hour.
Hourly Price Calendar
Loading calendar...
Wind Power Outlook
Solar Power Outlook
Consumption Outlook
Residual Load Outlook
Residual Load = Load - Wind - Solar
Forecast History
Default view shows how the forecast has evolved over the past couple of days. Use a date range to inspect older archived day-ahead forecasts against actual prices.
How the Forecast Works
The forecasts on this site are generated with a machine learning pricing model based on gradient-boosted decision trees, estimating hourly electricity prices from weather, generation, demand, interconnector capacity, calendar effects, and recent price patterns. Each hour is evaluated independently, which lets the model adapt to changing conditions across the forecast horizon.
The price model is trained on historical data starting from 2023. Weather data is based on ECMWF, using historical weather together with forward forecasts for each area. The site first produces separate wind, solar, and load forecasts, which are then fed into the downstream price model.
Key Inputs Considered by the Model
- Area-specific weather history and forecasts based on ECMWF
- Regional wind context from neighboring countries
- Forecast electricity demand
- Renewable generation availability, including wind and solar
- Nuclear generation where applicable
- Cross-border transfer capacities for the forecast area
- Hydrology state features for Finland and Norway
- Calendar effects such as year, weekday, hour, and holidays
- Recent price context, including prior-week prices
Model Logic and Interpretation
The model learns statistical relationships between input variables and price outcomes. High wind or solar output, mild temperatures, and stronger import capacity are often associated with lower prices, while low renewable output, cold weather, tighter hydro conditions, stronger demand, or reduced import capacity tend to push prices higher.
Geographic Scope and Development
The current implementation covers:
- Austria (AT)
- Belgium (BE)
- Czechia (CZ)
- Denmark (DK1, DK2)
- Estonia (EE)
- Finland (FI)
- France (FR)
- Germany (DE)
- Netherlands (NL)
- Norway (NO1–NO5)
- Poland (PL)
- Sweden (SE1–SE4)
Limitations of the Forecast
The model only considers variables included in its training data. It does not directly account for unexpected geopolitical events or rare structural shocks with limited historical precedent. Extreme price spikes and negative-price events can also be difficult to predict reliably, because similar cases are relatively rare in the historical data.
The model includes hydrology-state features for Finland and Norway, but it does not explicitly model hydro dispatch decisions or full hydro-system dynamics. Swedish hydrology is not currently included.
Treat forecasts as data-driven estimates, not future outcomes.