Short-term load forecasting based on MOCS-RBFNN calculation model
International Journal of Modern Physics C · 18.06.2026
DOI: 10.1142/s0129183126420040 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Modern Physics C, online erschienen am 18.06.2026. Verfasst von Xilong Qu und 3 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Gefördert von: 2025 Hunan Province Teaching Reform Research Project, Scientific Research Key Project of Hunan Education Department, Changsha Municipal Natural Science Foundation.
Abstract (Originalsprache)
In the increasingly complex domain of power systems, where load demand fluctuates due to renewable energy adoption and shifting consumption patterns, accurate short-term electric power load forecasting is essential for grid stability. Traditional forecasting models often fail to address the dynamic and nonlinear nature of load data. This study introduces a novel approach utilizing a Radial Basis Function Neural Network (RBFNN) optimized by the Multi-Objective Cuckoo Search (MOCS) algorithm. The MOCS algorithm combines the Levy flight search strategy with Pareto optimization, effectively navigating the optimization landscape to enhance the RBFNN’s forecasting accuracy while maintaining computational efficiency. The experimental results demonstrate that the MOCS-optimized RBFNN model significantly outperforms traditional models, achieving lower prediction errors and faster convergence. This advancement in forecasting methodology underscores the potential of integrating multi-objective optimization techniques in neural network models for improving the accuracy and efficiency of short-term load forecasting.
Förderung
- 2025 Hunan Province Teaching Reform Research Project
- Scientific Research Key Project of Hunan Education Department
- Changsha Municipal Natural Science Foundation
- Provincial Natural Science Foundation of Hunan
Zitieren
APA
Qu, X., Li, Y., Yi, L., & Tan, X. (2026). Short-term load forecasting based on MOCS-RBFNN calculation model. International Journal of Modern Physics C. https://doi.org/10.1142/s0129183126420040
Vancouver
Qu X, Li Y, Yi L, Tan X. Short-term load forecasting based on MOCS-RBFNN calculation model. International Journal of Modern Physics C. 2026. doi:10.1142/s0129183126420040
BibTeX
@article{Qu2026,
author = {Qu, Xilong and Li, Yuanling and Yi, Lizhi and Tan, Xiao},
title = {Short-term load forecasting based on MOCS-RBFNN calculation model},
journal = {International Journal of Modern Physics C},
year = {2026},
doi = {10.1142/s0129183126420040}
}
EUVIMED