Solar Power Prediction using GA & PSO Techniques of Machine Learning

DOI

10.2991/978-94-6463-738-0_34How to use a DOI?

Keywords

solar power forecasting; machine learning; particle swarm optimization (PSO); genetic algorithm (GA); hyper parameter optimization; LSTM networks; random Forest; support vector regression; renewable energy prediction; Solar irradiance; weather parameters; mean absolute error (MAE); root mean square error (RMSE); evolutionary algorithms; Swarm intelligence

Abstract

These results from the Solar Power’s stochastic nature, the forecasting on how much this electricity source will contribute at any particular time is very important in managing the grids. When it comes to the first generation of machine learning models, they are safe and accurate but have limitations when it comes to adjusting them to more accurately predict the new samples. Based on the aforementioned discovery, this paper, proposes a new optimization approach that integrates Particle Swarm Optimization (PSO) and Genetic Algorithms (GA), aimed at bolstering solar power forecast models. By employing GA and PSO to optimize the ML hyperparameters of the LSTM networks, random forests, SVR-based models.

Our goal is to improve its capability of making a more accurate prediction. The models are fed past solar irradiance, temperature and other climatic information while tested using MAE or RMSE as measures of error. The comparative analysis shows that the models tuned by GA and PSO perform better than the models without tuning and can be a viable method in order to achieve a greater and a high level of accuracy in forecasting in the generation of solar power. The paper shows that the use of both evolutionary and swarm intelligence optimization techniques can significantly improve the accuracy and economic viability of renewable energy forecasting and, in particular, solar power generation.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Gautam Kumar
AU  - Suryansh Shukla
AU  - Shrish Joshi
PY  - 2025
DA  - 2025/06/22
TI  - Solar Power Prediction using GA & PSO Techniques of Machine Learning
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 422
EP  - 432
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_34
DO  - 10.2991/978-94-6463-738-0_34
ID  - Kumar2025
ER  -