Enhancing Solar Power Forecasting Accuracy Using HMPCS and Machine Learning Techniques: An Applied Study

This dataset contains simulated input data, parameter settings, source code, and experimental results supporting the article“Enhancing Solar Power Forecasting Accuracy Using HMPCS and Machine Learning Techniques: An Applied Study” (F1000Research, Article ID: 172121). The data were synthetically generated through computational modeling to evaluate and validate the proposed Hybrid Metaheuristic and Machine Learning (HMPCS–ML) framework for solar power forecasting.No real-world or confidential data were used in this study. Specifically, the dataset includes:• Simulated meteorological and irradiance variables (GHI, temperature, humidity, wind speed, etc.) used for training and testing.• Configuration files and parameter values used in the hybrid optimization algorithm.• Source code implementing the HMPCS–ML model for forecasting and optimization.• Numerical results, including MAE, RMSE, and R² metrics, as well as convergence statistics.• Supporting data used to generate all figures and tables presented in the manuscript. All files are provided in open formats (CSV, TXT, XLSX, PY) to ensure full reproducibility and transparency.The dataset is distributed under the Creative Commons Attribution (CC BY 4.0) license, allowing reuse and adaptation with proper citation. Keywords: Solar Power, Forecasting, Machine Learning, HMPCS, Metaheuristics, Optimization, Renewable Energy, Open Data. This dataset was uploaded by the corresponding author and academic supervisor in accordance with the postgraduate regulations of the University of Baghdad. All listed creators are manuscript authors and approved the data release.