Nordpool Predict FI
This experimental, privately-made (no relation to Nordpool) machine learning model estimates the consumer price of electricity in Finland (VAT 25.5%) for about a week ahead. The model reflects, among other things, the predicted weather and electricity production to previous periods where these factors were similar.
Although the model can be surprisingly accurate in normal situations, the forecast should be taken with caution. It may not correctly predict the price effects of exceptional situations. The wind forecast has a significant impact on price spikes, especially if there are maintenance outages at the same time.
The model is trained and the forecast is updated automatically several times a day. Below the graph is a language model's interpretation of the forecast.
Forecast for the coming days
Wind power forecast
Based on data and forecasts from FMI weather stations on the coast of the Gulf of Bothnia. Wind over 2...3 gigawatts is favorable for the electricity price, and with wind below 1 gigawatt, the price can rise high if there are maintenance outages or it is cold at the same time.
Historical forecasts
The graph shows a 30-day history of previous forecasts. Major changes of mind can occur, for example, if the weather forecast changes significantly, if there is an unexpected production outage, if the cause of the price disturbance is historically new or rare, or if the model has been recently updated. See the change log below.
The orange line is the final Nordpool price. The fading blue lines are the forecast ensemble from previous days, before the Nordpool price was known.
What does the forecast consider?
This is a machine learning model that seeks correlations between different variables and learns what price each combination leads to based on history. This is not a time series forecast, but each hour gets its value independently based on this data:
Forecasts for wind power areas in Finland: FMI weather stations, i.e., indirectly the amount of wind power
Wind forecasts for the Baltic Sea region: Open-Meteo: Sweden, Denmark, Germany, and Estonia
Temperature forecasts: FMI weather stations, i.e., indirectly heating demand and season
Nuclear power production: Fingrid (model training) and ENTSO-E REMIT UMM (maintenance schedules)
Transmission capacity: JAO: transmission capacity from Sweden and Estonia to Finland
Solar energy: Open-Meteo: solar radiation at ground level
Year: 2023, 2024, ...
Day of the week: Mon-Sun
Time of day: 0-23
Holidays: On national holidays, energy demand may be lower than usual
The source code is open, and you are welcome to try different options in addition to or instead of these.
Change log
The model has been online since February 2024. The following changes have been made since then.
August 11, 2024:
Removed ENTSO-E REMIT UMM production variable because according to the interface, OL3 would be under maintenance until 2025. Fortunately, this is not true, but it messes up the forecast. We are investigating the issue and will return the nuclear power forecast to training if the cause of the error is found. The nuclear power forecast now assumes that the latest known production figure remains for the next 5 days.
Monthly data (January-December) has been removed from model training because the monthly averages of previous years can be very different from this year due to market conditions. The seasonal price effect is also evident in training from the weather when temperatures drop below freezing and consumption increases.
August 19, 2024:
Added transmission capacities towards Finland: Northern Sweden, Central Sweden, and Estonia. This should refine the forecast during maintenance periods. The calculation assumes that the announced capacity for tomorrow remains the same for the 5-day forecast period.
August 31, 2024:
Changed the forecast model type from Random Forest to XGBoost based on Optuna comparison.
September 16, 2024:
Implemented a custom XGBoost wind power model based on historical and forecast data from 20 weather stations.
September 22, 2024:
Planned transmission capacity (Fingrid) is now considered in the transmission forecast.
Wind power data included in the language model's explanation.
Wind power model tuned.
October 17, 2024:
Reported maintenance outages and future production capacities of nuclear power plants (ENTSO-E) returned to the forecast.
Price forecast changed to a bar chart.
October 20, 2024:
The language model now sees advance information on transmission connections and nuclear power plant maintenance.
November 10, 2024:
Fingrid no longer reports transmission capacity forecasts. The new JAO data source used in flow-based calculation only reports realized capacity. The forecast now assumes (again) that the latest realized transmission capacity remains for the forecast period.
November 17, 2024:
The language model now sees unplanned production outages of nuclear power plants.
Language model changed to GPT-4o. The previous one was GPT-4o-mini. This should produce clearer Finnish.
November 23, 2024:
Wind power forecast now experimenting with a neural network model (PyTorch).
December 24, 2024:
Information about holidays is now included in model training.
December 25, 2024:
The history graph no longer shows old forecasts where the realized Nordpool price for tomorrow was already known to the model.
History extended to 30 days.
December 30, 2024:
The model now estimates the impact of solar energy on the price.
Wind power forecast uses XGBoost again.
January 4, 2025:
The forecast now extends 7 days ahead.
Swedish and Estonian import connections are now handled separately in the model, not just as a sum. An outage in the Estonian connection typically lowers the price, while the Swedish one raises it.
January 12, 2025:
Fingrid, wind power capacity: data was missing from the interface for the beginning of the year. Open-Meteo, solar radiation: the provided forecast values (W/m²) were negative for the coming days, by half a million Watts. Checks added for such situations.
Baltic Sea wind power areas added to the pricing model. Low wind abroad can raise the price in Finland, even if domestic production is strong.
January 18, 2025:
Wind power model tuned. Fingrid's continuously updated forecast provides the first 36 hours from the update time, and the rest are estimated from the weather data of the Baltic Sea region and Finland. The realization is now updated retrospectively.
The language model now sees intra-day data and potential price spike risks. Language model changed to DeepSeek-V3.
January 30, 2025:
The main page is now available in Finnish and English.
A Markdown-formatted version can be found on GitHub in Finnish and in English. See also the bilingual JSON version. These may be useful, for example, for those building home automation systems.
The DeepSeek API has recently been quite jammed, and it doesn't always agree to generate texts. If this situation continues for a longer period, we'll revert to the GPT-4o model, although in that case we'll likely only provide a single language version.
February 5, 2025:
The language model may change without notice between DeepSeek-V3, GPT-4o and Gemini 2.0 Pro.
Planned:
More accurate prediction of hourly price volatility may require its own model and method in addition to/on top of the current one. The current method works better for estimating the daily price level than the dynamics of individual peak prices in the morning and evening. However, the language model already comments on price spikes if the conditions for them exist, e.g., high predicted price and low wind at the same time.
What does the forecast not consider?
The forecast does not see anything other than what is mentioned above. The data used in training starts from the beginning of 2023.
Although the model can "predict" the past and historically familiar types of the future, price estimates in new and exceptional situations can be off. So do not, for example, adjust your house heating based on these numbers if you are not at home.
