Solar Irradiance Forecasting to Short-Term PV Power: Accuracy Comparison of ANN and LSTM Models

• Published in: Energies (Basel) Vol. 15; no. 7; p. 2457
• Main Authors: Wentz, Victor Hugo, Maciel, Joylan Nunes, Gimenez Ledesma, Jorge Javier, Ando Junior, Oswaldo Hideo
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.04.2022
• Subjects: Accuracy; Algorithms; Alternative energy sources; Artificial intelligence; artificial neural networks; Climate change; Consumption; Deep learning; Energy consumption; Energy industry; Horizon; Humidity; Irradiance; long-term short memory; Machine learning; Methods; Neural networks; Photovoltaic cells; Photovoltaics; Predictions; Renewable resources; Solar energy; solar irradiance forecasting; Solar power; Time series; Weather; Brazil
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en15072457

The use of renewable energies, such as Photovoltaic (PV) solar power, is necessary to meet the growing energy consumption. PV solar power generation has intrinsic characteristics related to the climatic variables that cause intermittence during the generation process, promoting instabilities and insecurity in the electrical system. One of the solutions for this problem uses methods for the Prediction of Solar Photovoltaic Power Generation (PSPPG). In this context, the aim of this study is to develop and compare the prediction accuracy of solar irradiance between Artificial Neural Network (ANN) and Long-Term Short Memory (LSTM) network models, from a comprehensive analysis that simultaneously considers two distinct sets of exogenous meteorological input variables and three short-term prediction horizons (1, 15 and 60 min), in a controlled experimental environment. The results indicate that there is a significant difference (p < 0.001) in the prediction accuracy between the ANN and LSTM models, with better overall prediction accuracy skill for the LSTM models (MAPE = 19.5%), except for the 60 min prediction horizon. Furthermore, the accuracy difference between the ANN and LSTM models decreased as the prediction horizon increased, and no significant influence was observed on the accuracy of the prediction with both sets of evaluated meteorological input variables.