Probabilistic Net-Load Forecasting for Power Systems with Variable Solar and Wind Generation

Authors

  • Sokip Anam Sekolah Tinggi Teknologi Nusantara Lampung
  • Nambi Anasta Sekolah Tinggi Teknologi Nusantara Lampung

Keywords:

net load, probabilistic forecasting, solar and wind generation, quantile gradient boosting, conformal calibration

Abstract

Variable solar and wind generation changes both the level and the uncertainty of the residual demand that power-system operators must anticipate. This study evaluates probabilistic net-load forecasting using the original Open Power System Data hourly package for Germany over 2016–2019. A chronological design separates model fitting, validation, calibration, and a full 2019 test year. Forecasts for 1-, 6-, and 24-hour horizons use only completed-hour observations and known calendar information. Eight specifications compare empirical and Gaussian benchmarks, direct quantile gradient boosting, component forecasts with paired or independently resampled calibration errors, and static or rolling conformal quantile calibration. The independent component specification achieves the lowest weighted interval score among the primary specifications at every horizon: 0.430, 1.692, and 3.162 GW, respectively. Rolling calibration increases the direct model’s nominal 90% interval coverage from 86.3%, 75.7%, and 77.5% to 90.2%, 89.7%, and 88.9%, while improving its weighted interval score by only 0.44%, 4.80%, and 2.96%. Preserving calibration-period component dependence reduces residual variance by up to 21.3% but does not improve out-of-sample probabilistic scores relative to independent resampling. Coverage deteriorates during high renewable contribution and large realized ramps; at 24 hours, rolling-calibrated coverage falls to 63.3% for the latter subset. These findings support separating forecast accuracy, marginal calibration, and operational stress performance. The experiment establishes an observation-based benchmark rather than a weather-informed operational optimum, and it identifies component error drift and conditional tail reliability as priorities for subsequent forecasting and scheduling research.

Downloads

Download data is not yet available.

References

Hong, T.; Pinson, P.; Wang, Y.; Weron, R.; Yang, D.; Zareipour, H. (2020). Energy Forecasting: A Review and Outlook. IEEE Open Access Journal of Power and Energy, 7, 376-388. https://doi.org/10.1109/OAJPE.2020.3029979

van der Meer, D.; Widén, J.; Munkhammar, J. (2018). Review on probabilistic forecasting of photovoltaic power production and electricity consumption. Renewable and Sustainable Energy Reviews, 81, 1484-1512. https://doi.org/10.1016/j.rser.2017.05.212

Bazionis, I. K.; Karafotis, P. A.; Georgilakis, P. S. (2022). A review of short‐term wind power probabilistic forecasting and a taxonomy focused on input data. IET Renewable Power Generation, 16(1), 77-91. https://doi.org/10.1049/rpg2.12330

Xu, C.; Sun, Y.; Du, A.; Gao, D. c. (2023). Quantile regression based probabilistic forecasting of renewable energy generation and building electrical load: A state of the art review. Journal of Building Engineering, 79, 107772. https://doi.org/10.1016/j.jobe.2023.107772

van der Meer, D.; Munkhammar, J.; Widén, J. (2018). Probabilistic forecasting of solar power, electricity consumption and net load: Investigating the effect of seasons, aggregation and penetration on prediction intervals. Solar Energy, 171, 397-413. https://doi.org/10.1016/j.solener.2018.06.103

van der Meer, D.; Shepero, M.; Svensson, A.; Widén, J.; Munkhammar, J. (2018). Probabilistic forecasting of electricity consumption, photovoltaic power generation and net demand of an individual building using Gaussian Processes. Applied Energy, 213, 195-207. https://doi.org/10.1016/j.apenergy.2017.12.104

Wang, Y.; Zhang, N.; Chen, Q.; Kirschen, D. S.; Li, P.; Xia, Q. (2018). Data-Driven Probabilistic Net Load Forecasting With High Penetration of Behind-the-Meter PV. IEEE Transactions on Power Systems, 33(3), 3255-3264. https://doi.org/10.1109/TPWRS.2017.2762599

Browell, J.; Fasiolo, M. (2021). Probabilistic Forecasting of Regional Net-Load With Conditional Extremes and Gridded NWP. IEEE Transactions on Smart Grid, 12(6), 5011-5019. https://doi.org/10.1109/TSG.2021.3107159

Berk, K.; Hoffmann, A.; Müller, A. (2018). Probabilistic forecasting of industrial electricity load with regime switching behavior. International Journal of Forecasting, 34(2), 147-162. https://doi.org/10.1016/j.ijforecast.2017.09.006

Bracale, A.; Caramia, P.; De Falco, P.; Hong, T. (2020). A Multivariate Approach to Probabilistic Industrial Load Forecasting. Electric Power Systems Research, 187, 106430. https://doi.org/10.1016/j.epsr.2020.106430

Sun, M.; Zhang, T.; Wang, Y.; Strbac, G.; Kang, C. (2020). Using Bayesian Deep Learning to Capture Uncertainty for Residential Net Load Forecasting. IEEE Transactions on Power Systems, 35(1), 188-201. https://doi.org/10.1109/TPWRS.2019.2924294

Xu, C.; Chen, G. (2024). Interpretable transformer-based model for probabilistic short-term forecasting of residential net load. International Journal of Electrical Power & Energy Systems, 155, 109515. https://doi.org/10.1016/j.ijepes.2023.109515

Feng, W.; Deng, B.; Chen, T.; Zhang, Z.; Fu, Y.; Zheng, Y.; et al. (2024). Probabilistic net load forecasting based on sparse variational Gaussian process regression. Frontiers in Energy Research, 12, 1429241. https://doi.org/10.3389/fenrg.2024.1429241

van der Meer, D. (2021). A benchmark for multivariate probabilistic solar irradiance forecasts. Solar Energy, 225, 286-296. https://doi.org/10.1016/j.solener.2021.07.010

Mashlakov, A.; Kuronen, T.; Lensu, L.; Kaarna, A.; Honkapuro, S. (2021). Assessing the performance of deep learning models for multivariate probabilistic energy forecasting. Applied Energy, 285, 116405. https://doi.org/10.1016/j.apenergy.2020.116405

Angelopoulos, A. N.; Bates, S. (2023). Conformal Prediction: A Gentle Introduction. Foundations and Trends® in Machine Learning, 16(4), 494-591. https://doi.org/10.1561/2200000101

Lei, J.; G’Sell, M.; Rinaldo, A.; Tibshirani, R. J.; Wasserman, L. (2018). Distribution-Free Predictive Inference for Regression. Journal of the American Statistical Association, 113(523), 1094-1111. https://doi.org/10.1080/01621459.2017.1307116

Barber, R. F.; Candès, E. J.; Ramdas, A.; Tibshirani, R. J. (2023). Conformal prediction beyond exchangeability. The Annals of Statistics, 51(2), 816–845. https://doi.org/10.1214/23-AOS2276

Yang, D. (2019). A guideline to solar forecasting research practice: Reproducible, operational, probabilistic or physically-based, ensemble, and skill (ROPES). Journal of Renewable and Sustainable Energy, 11(2), 022701. https://doi.org/10.1063/1.5087462

Doubleday, K.; Van Scyoc Hernandez, V.; Hodge, B. M. (2020). Benchmark probabilistic solar forecasts: Characteristics and recommendations. Solar Energy, 206, 52-67. https://doi.org/10.1016/j.solener.2020.05.051

Gneiting, T.; Lerch, S.; Schulz, B. (2023). Probabilistic solar forecasting: Benchmarks, post-processing, verification. Solar Energy, 252, 72-80. https://doi.org/10.1016/j.solener.2022.12.054

Bracher, J.; Ray, E. L.; Gneiting, T.; Reich, N. G. (2021). Evaluating epidemic forecasts in an interval format. PLOS Computational Biology, 17(2), e1008618. https://doi.org/10.1371/journal.pcbi.1008618

Hewamalage, H.; Ackermann, K.; Bergmeir, C. (2023). Forecast evaluation for data scientists: common pitfalls and best practices. Data Mining and Knowledge Discovery, 37(2), 788-832. https://doi.org/10.1007/s10618-022-00894-5

Wiese, F.; Schlecht, I.; Bunke, W. D.; Gerbaulet, C.; Hirth, L.; Jahn, M.; et al. (2019). Open Power System Data – Frictionless data for electricity system modelling. Applied Energy, 236, 401-409. https://doi.org/10.1016/j.apenergy.2018.11.097

Open Power System Data (2020). Data Package Time series. Version 2020-10-06. Open Power System Data. https://doi.org/10.25832/time_series/2020-10-06

Published

2026-10-30

How to Cite

Anam, S., & Anasta, N. (2026). Probabilistic Net-Load Forecasting for Power Systems with Variable Solar and Wind Generation. Journal of Electrical Engineering and Informatics (JEEI), 1(3). Retrieved from https://jurnal.sttnlampung.ac.id/index.php/jeei/article/view/205