Finland aFRR Energy Market and Weather Data (Hourly, June 2024 – March 2025)

This dataset contains hourly data from the Automatic Frequency Restoration Reserve (aFRR) energy market in Finland, covering the period from June 20, 2024, to March 16, 2025 (UTC). The data integrates both market operations and meteorological parameters, enabling analysis of the relationship between electricity balancing mechanisms and weather conditions. The dataset includes the following key variables: Market indicators: Up-regulation (Up), Down-regulation (Down), Setpoint (sp), and associated capacity values (Up_Cap, Down_Cap). Weather attributes: Cloud amount, wind speed, precipitation amount, atmospheric pressure, air temperature, relative humidity, and wind direction. Electricity consumption: Total electricity consumption, Finnish network consumption, and forecasted consumption values. Temporal and contextual factors: Hourly timestamps (datetime) and a binary indicator for public holidays in Finland (is_public_holiday). This dataset is designed for research in: Electricity market analysis and balancing dynamics. Energy demand forecasting. Weather–energy correlation modeling. Renewable integration and grid stability studies. Data frequency: HourlyGeographic coverage: FinlandTime coverage: 2024-06-20 22:00:00 UTC – 2025-03-16 22:00:00 UTC When using this dataset, please cite this Zenodo record and the associated publication: https://doi.org/10.1016/j.egyai.2026.100724 Abu Saleh, Aruzhan Amangeldina, Tesfay W. Tesfay, Sébastien Lafond, Hergys Rexha, Olena Izhak,Forecasting Finnish aFRR energy reserve market prices using deep learning and tree-based models,Energy and AI, 2026, 100724, ISSN 2666-5468. https://www.sciencedirect.com/science/article/pii/S2666546826000509 Bibtext entry: @article{SALEH2026100724,title = {Forecasting Finnish aFRR energy reserve market prices using deep learning and tree-based models},journal = {Energy and AI},pages = {100724},year = {2026},issn = {2666-5468},doi = {https://doi.org/10.1016/j.egyai.2026.100724},url = {https://www.sciencedirect.com/science/article/pii/S2666546826000509},author = {Abu Saleh and Aruzhan Amangeldina and Tesfay W. Tesfay and Sébastien Lafond and Hergys Rexha and Olena Izhak},keywords = {aFRR energy market, Energy price forecasting, Frequency regulation, Time series modeling, Feature engineering, Deep learning, Tree-based models},abstract = {With the increased integration of renewable energy sources, electricity systems face growing challenges due to the intermittency and volatility of weather-dependent generation. To maintain grid stability, reserve mechanisms such as the Automatic Frequency Restoration Reserve (aFRR) play a critical role by balancing supply and demand in real-time. However, the high volatility of aFRR energy prices complicates the decision-making of reserve providers and market operators. To address this challenge, this paper aims to forecast 48-hour aFRR marginal energy prices in the Finnish electricity market under both Down- and Up-regulations. We implement and compare two tree-based models, LightGBM and XGBoost, with two deep learning approaches, the Temporal Fusion Transformer and the Time-series Dense Encoder. The models are trained using historical Finnish aFRR energy prices, complemented by relevant market and weather variables, and evaluated across three cross-validation strategies. The models achieved mean absolute errors of 17.5–17.8 for Down-regulation and 55.7–60.1 for Up-regulation, with LightGBM delivering the most consistent performance under limited data availability. To our knowledge, this is the first study to systematically compare data-driven forecasting models for aFRR energy prices in the Finnish electricity market, providing an early-stage comparative baseline and economic relevance for a diverse array of stakeholders.}}