GridMind: Issue-Time-Safe Cross-Country Load Forecasting with Conformal Uncertainty and Operator-Aware Model Selection

Sohaib Ayad Jasim; Shuaib Ayad Jasim

doi:10.67047/tepes.2009644

GridMind: Issue-Time-Safe Cross-Country Load Forecasting with Conformal Uncertainty and Operator-Aware Model Selection

Abstract

Operational electricity forecasting must be accurate, uncertainty-aware, and protected against future-information leakage. This study presents GridMind, an operator-oriented champion-challenger framework combining a forecast-origin feature ledger, Light Gradient Boosting Machine point forecasts, rolling split-conformal intervals, reproducible feature evidence, and an explicit retain-or-replace decision. The framework was evaluated on complementary national datasets from Panama and Spain. For Panama, the exact 14 published 168-hour test weeks and the prescribed 72-hour unseen gap were reproduced. Target-week realized weather was excluded, and only completed-week load lags and known calendar variables were used. The model achieved 4.193% pooled MAPE, 63.796 MWh RMSE, and a 28.26% reduction in mean weekly MAPE relative to a safe 336-hour seasonal-naive benchmark. It improved 11 of 14 weeks; the mean paired improvement was 1.652 percentage points (bootstrap 95% CI 0.670-2.903; one-sided Wilcoxon p=0.002625). Nominal 90% split-conformal intervals attained 89.97% pooled coverage. For Spain, the public operator forecast remained the champion: H2-2018 MAPE was 0.8855%, compared with 0.8947% after forecast-origin-safe residual correction. GridMind therefore provides an auditable pattern for feature availability, accuracy, calibrated uncertainty, and operational model governance without assuming that a machine-learning challenger must replace the incumbent.

Keywords

Supporting Institution

None. No external grant or financial support was received for this study.

Ethical Statement

Ethical approval was not required because the study used openly accessible, non-personal electricity and weather time-series data. Data and code availability are described in the manuscript.

Thanks

The authors acknowledge the providers of the openly accessible electricity and meteorological datasets cited in the manuscript.

References

H. S. Hippert, C. E. Pedreira, and R. C. Souza, “Neural networks for short-term load forecasting: A review and evaluation,” IEEE Trans. Power Syst., vol. 16, no. 1, pp. 44–55, 2001, doi: 10.1109/59.910780.
T. Hong and S. Fan, “Probabilistic electric load forecasting: A tu¬torial review,” Int. J. Forecast., vol. 32, no. 3, pp. 914–938, 2016, doi: 10.1016/j.ijforecast.2015.11.011.
C. Bergmeir and J. M. Benítez, “On the use of cross-validation for time series predictor evaluation,” Inf. Sci., vol. 191, pp. 192– 213, 2012, doi: 10.1016/j.ins.2011.12.028.
T. Gneiting and A. E. Raftery, “Strictly proper scoring rules, pre¬diction, and estimation,” J. Amer. Stat. Assoc., vol. 102, no. 477, pp. 359–378, 2007, doi: 10.1198/016214506000001437.
E. Aguilar Madrid and N. Antonio, “Short-term electricity load forecasting with machine learning,” Information, vol. 12, no. 2, art. 50, 2021, doi: 10.3390/info12020050.
E. Aguilar Madrid, “Short-term electricity load forecasting (Panama case study), Version 1,” Mendeley Data, 2021, doi: 10.17632/byx7sztj59.1.
European Network of Transmission System Operators for Elec¬tricity, “ENTSO-E Transparency Platform.” https://transparency. entsoe.eu/
European Commission, “Commission Regulation (EU) No 543/2013 on submission and publication of data in electricity markets,” Off. J. Eur. Union, 2013. https://eur-lex.europa.eu/eli/ reg/2013/543/oj

L. Hirth, J. Mühlenpfordt, and M. Bulkeley, “The ENTSO-E Trans¬parency Platform—A review of Europe’s most ambitious elec¬tricity data platform,” Appl. Energy, vol. 225, pp. 1054–1067, 2018, doi: 10.1016/j.apenergy.2018.04.048.
G. Ke et al., “LightGBM: A highly efficient gradient boosting de¬cision tree,” in Adv. Neural Inf. Process. Syst., vol. 30, pp. 3146– 3154, 2017.
Y. Romano, E. Patterson, and E. J. Candès, “Conformalized quan¬tile regression,” in Adv. Neural Inf. Process. Syst., vol. 32, pp. 3543–3553, 2019.
S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Adv. Neural Inf. Process. Syst., vol. 30, 2017.
B. Lim, S. Ö. Arık, N. Loeff, and T. Pfister, “Temporal Fusion Transformers for interpretable multi-horizon time series fore¬casting,” Int. J. Forecast., vol. 37, no. 4, pp. 1748–1764, 2021, doi: 10.1016/j.ijforecast.2021.03.012.
R. J. Hyndman and A. B. Koehler, “Another look at measures of forecast accuracy,” Int. J. Forecast., vol. 22, no. 4, pp. 679–688, 2006, doi: 10.1016/j.ijforecast.2006.03.001.
F. Wilcoxon, “Individual comparisons by ranking meth¬ods,” Biometrics Bull., vol. 1, no. 6, pp. 80–83, 1945, doi:10.2307/3001968.
F. X. Diebold and R. S. Mariano, “Comparing predictive accura¬cy,” J. Bus. Econ. Stat., vol. 13, no. 3, pp. 253–263, 1995, doi:10.1080/07350015.1995.10524599.
R. Gelaro et al., “The Modern-Era Retrospective Analysis for Re¬search and Applications, Version 2 (MERRA-2),” J. Climate, vol.30, no. 14, pp. 5419–5454, 2017, doi: 10.1175/JCLI-D-16-0758.1.
T. Chen and C. Guestrin, “XGBoost: A scalable tree boost¬ing system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl¬edge Discovery Data Mining, pp. 785–794, 2016, doi:10.1145/2939672.2939785.
J. W. Taylor and P. E. McSharry, “Short-term load forecastingmethods: An evaluation based on European data,” IEEE Trans.Power Syst., vol. 22, no. 4, pp. 2213–2219, 2007, doi: 10.1109/TPWRS.2007.907583.

Details

Primary Language

English

Subjects

Electrical Energy Transmission, Networks and Systems

Journal Section

Research Article

Authors

Sohaib Ayad Jasim
0009-0007-0494-8818
Türkiye

Shuaib Ayad Jasim ^*
0009-0000-5574-7302
Türkiye

Publication Date

October 27, 2026

Submission Date

August 2, 2026

Acceptance Date

September 7, 2026

Published in Issue

Year 2026 Volume: 6 Number: 3

DOI

https://doi.org/10.67047/tepes.2009644

IZ

https://izlik.org/JA66WW96CG

Cite

RIS / Bibtex

APA

Jasim, S. A., & Jasim, S. A. (2026). GridMind: Issue-Time-Safe Cross-Country Load Forecasting with Conformal Uncertainty and Operator-Aware Model Selection. Turkish Journal of Electrical Power and Energy Systems, 6(3), 231-240. https://doi.org/10.67047/tepes.2009644

AMA

1.Jasim SA, Jasim SA. GridMind: Issue-Time-Safe Cross-Country Load Forecasting with Conformal Uncertainty and Operator-Aware Model Selection. TEPES. 2026;6(3):231-240. doi:10.67047/tepes.2009644

Chicago

Jasim, Sohaib Ayad, and Shuaib Ayad Jasim. 2026. “GridMind: Issue-Time-Safe Cross-Country Load Forecasting With Conformal Uncertainty and Operator-Aware Model Selection”. Turkish Journal of Electrical Power and Energy Systems 6 (3): 231-40. https://doi.org/10.67047/tepes.2009644.

EndNote

Jasim SA, Jasim SA (October 27, 2026) GridMind: Issue-Time-Safe Cross-Country Load Forecasting with Conformal Uncertainty and Operator-Aware Model Selection. Turkish Journal of Electrical Power and Energy Systems 6 3 231–240.

IEEE

[1]S. A. Jasim and S. A. Jasim, “GridMind: Issue-Time-Safe Cross-Country Load Forecasting with Conformal Uncertainty and Operator-Aware Model Selection”, TEPES, vol. 6, no. 3, pp. 231–240, Oct. 2026, doi: 10.67047/tepes.2009644.

ISNAD

Jasim, Sohaib Ayad - Jasim, Shuaib Ayad. “GridMind: Issue-Time-Safe Cross-Country Load Forecasting With Conformal Uncertainty and Operator-Aware Model Selection”. Turkish Journal of Electrical Power and Energy Systems 6/3 (October 27, 2026): 231-240. https://doi.org/10.67047/tepes.2009644.

JAMA

1.Jasim SA, Jasim SA. GridMind: Issue-Time-Safe Cross-Country Load Forecasting with Conformal Uncertainty and Operator-Aware Model Selection. TEPES. 2026;6:231–240.

MLA

Jasim, Sohaib Ayad, and Shuaib Ayad Jasim. “GridMind: Issue-Time-Safe Cross-Country Load Forecasting With Conformal Uncertainty and Operator-Aware Model Selection”. Turkish Journal of Electrical Power and Energy Systems, vol. 6, no. 3, Oct. 2026, pp. 231-40, doi:10.67047/tepes.2009644.

Vancouver

1.Sohaib Ayad Jasim, Shuaib Ayad Jasim. GridMind: Issue-Time-Safe Cross-Country Load Forecasting with Conformal Uncertainty and Operator-Aware Model Selection. TEPES. 2026 Oct. 27;6(3):231-40. doi:10.67047/tepes.2009644