Management of solar energy availability estimation using machine learning models
Keywords:
management, availability, solar energy, estimation, machine learning.Abstract
Due to factors of different nature, energy upon arrival at the surface of the earth may appear intermittent, creating an obstacle to its use. Motivated by the need for greater profitability of solar energy, primarily for the production of photovoltaic energy. An estimate of the availability of solar energy was managed on a short measurement scale, to understand the real behavior of solar energy in the town of Pomene. Solar energy was collected in 2014, for 12 months, with a daily period and a 10-minute measurement interval. Using machine learning models such as random forest, regressive Kriking, and artificial neutral networks, solar energy was predicted. The predicted energy management shows the predominance of full sun with intermediate classification, and of course, the power of the existence of energy for use, in addition, it was concluded that the random forest model presents lower prediction error and enhances the APM models. for greater analysis, more energy production efficiency.
Downloads
References
A Machine Learning Technique for Spatial Interpolation of Solar Radiation Observations. ([s.d.]). Recuperado 22 de março de 2024, de https://agupubs.onlinelibrary.wiley.com/doi/epdf/10.1029/2020EA001527
Mucomole, F. V., Silva, C. A. S., & Magaia, L. L. (2023). Temporal Variability of Solar Energy Availability in the Conditions of the Southern Region of Mozambique. American Journal of Energy and Natural Resources, 2(1), Artigo 1. https://doi.org/10.54536/ajenr.v2i1.1311
Mucomole, F. V., Silva, C. S. A., & Magaia, L. L. (2024). Quantifying the Variability of Solar Energy Fluctuations at High–Frequencies through Short-Scale Measurements in the East–Channel of Mozambique Conditions. American Journal of Energy and Natural Resources, 3(1), Artigo 1. https://doi.org/10.54536/ajenr.v3i1.2569
Puga-Gil, D., Astray, G., Barreiro, E., Gálvez, J. F., & Mejuto, J. C. (2022). Global Solar Irradiation Modelling and Prediction Using Machine Learning Models for Their Potential Use in Renewable Energy Applications.
Mathematics, 10(24), Artigo 24. https://doi.org/10.3390/math10244746
Sridharan, M. (2023). Generalized Regression Neural Network Model Based Estimation of Global Solar Energy Using Meteorological Parameters. Annals of Data Science, 10(4), 1107–1125. https://doi.org/10.1007/s40745-020-00319-4
