Hourly Price Calendar

Wind Power Outlook

Solar Power Outlook

Consumption Outlook

Residual Load Outlook

Residual Load = Load - Wind - Solar

Forecast History

How the Forecast Works

The forecasts on this site are generated with an XGBoost-based machine learning pricing model (gradient-boosted decision trees) that estimates hourly electricity prices from weather, generation, demand, and market features. Each hour is evaluated independently based on its expected conditions, which lets the model react to changes in wind, imports, generation availability, solar output, and seasonal demand.

The price model is trained on historical market data starting from 2023. Weather data comes from ECMWF, using recent historical weather together with forward forecasts for each area. The site also produces separate wind, solar, and load forecasts that feed into the downstream price view.

Key Inputs Considered by the Model

• Area-specific weather history and forecasts from ERA5 and ECMWF
• Regional wind context from neighboring countries
• Forecast load / consumption for the price area
• Renewable generation availability, including wind and solar, plus nuclear where applicable
• Cross-border transfer capacities for the forecast area
• Area solar output built from irradiance features and capacity-aware solar forecasting
• Hydrology state features for Finland and Norway
• Calendar effects such as year, weekday, hour, and holidays, plus prior-week price context

Wind Forecasting

Recent ENTSO-E actuals are used to anchor the wind picture. The raw wind-power model is built from area-specific weather features, historical production, and installed capacity. Finland remains a special case on the power side: Fingrid real-time data and Fingrid's operational wind-power forecast are used directly where available, with model inference filling remaining gaps.

Load Forecasting

Recent ENTSO-E load actuals are used first whenever they are available. For the nearest future window, the pipeline uses ENTSO-E day-ahead load forecast. Beyond that, a local XGBoost load model extends the horizon using calendar, weather, irradiance, holiday, and recent load-history features.

Model Logic and Interpretation

The model learns statistical relationships between explanatory variables and price outcomes. High wind or solar, 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 Finland (FI), Sweden (SE1-SE4), Norway (NO1-NO5), Denmark (DK1-DK2), Germany (DE), Estonia (EE), France (FR), and Poland (PL). The same weather model is used across these areas, while power, transmission, and market data come from ENTSO-E and JAO. Additionally, SYKE and NVE are utilized to capture hydology in Finland and Norway, respectively.

Limitations of the Forecast

The model only considers variables included in its training data. It does not directly account for unexpected geopolitical events, sudden market interventions, or rare structural shocks with limited historical precedent. It includes hydrology-state features for Finland and Norway, but it does not explicitly model hydro dispatch decisions or full hydro-system dynamics, and Swedish hydrology is not currently included. Treat forecasts as data-driven estimates, not future outcomes.