solar_energy_12_cities_Amazon_Basin

Citation Author(s):
andre
marques
universidade de sao paulo
Submitted by:
Andre Luis Marques
Last updated:
Mon, 07/08/2024 - 15:58
DOI:
10.21227/pc86-zn24
Data Format:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

Data from NASA Power Project, aiming the study of solar irradiance in the Amazon Basin, focusing 12 cities in the Amazonas State, Brazil. The data is daily basis, the target variable is the solar irradiance, and the input variables are the local temperature, local air humidity, local wind speed at 10m, local wind direction at 10m, percentage of the sky coverture, the total precipitation corrected. The time span covers 2017 to 2023. Deep learning has grown among the prediction tools used within renewable energy options. Solar energy belongs to the options with the lowest atmosphere impact after considering their limitations. In the last five years, Brazil has seen the expansion of wind and solar options almost all over the country, and to preserve the Amazon rainforest, the use of solar energy has helped large and small cities towards a greener future. The novelty of this research covers the use of Deep Learning with data from twelve cities in the state of Amazonas to forecast solar irradiation (W.h/m2) within 30 days. The data input came from ground stations, as much as possible, and NASA satellite models, with a daily time aggregation. The types of neural networks considered are Long Short-Term Memory (LSTM), a Multi-Layer Perceptron (MLP), and a LSTM Gated Recurrent Unit (GRU). Among the metrics used to check the algorithm´s performance, the Mean Absolute Percentage Error (MAPE) indicates that the values of this research are coherent with other scenarios to forecast solar energy; the boundary conditions were not the same, however. The lowest MAPE was observed in the city of Labrea with the LSTM GRU.

Instructions: 

The dataset is related to Jupyter Notebooks to run forecasting models with different deep learning architectures. The target variable is the solar irradiance. The input variables vary depending the feature engineering associated.