This paper focuses on the study of the strategic prediction of renewable sources of intermittent energy, using bio-inspired computational models, developed in Python, with the gaim of providing mechanisms that help in the monitoring and control of smart grids. To perform the learning of the neural network, we used the Backpropagation and Feedforwad algorithms. This neural network makes use of hysteresis neurons through the L 2 P model that, therefore, iterates the data to reproduce the prediction curves. To evaluate the model, real data obtained from the National Institute of Meteorology (INMET) was used. Results are presented through the application of the L 2 P model as a neural network and compared to existing structures in neural networks such as the ARIMA method, showing the good performance of the L 2 P neural network. Resumo: Este artigo concentra-se no estudo da predição estratégica de fontes renováveis de energia intermitente, utilizando modelos computacionais baseados em redes neurais artificiais (RNAs), desenvolvidos em linguagem Python, com o intuito de fornecer mecanismos que auxiliem no monitoramento e controle das redes elétricas inteligentes. Para a realização do aprendizado da rede neural, utilizou-se os algoritmos Backpropagation e Feedforwad. A rede neural em questão, faz o uso de neurônios de histerese por meio do modelo L 2 P (Limity Loop Proximity) que, portanto, realiza a iteração dos dados para reproduzir as curvas de previsão de radiação solar e velocidade do vento. Para avaliar o modelo, empregou-se dados reais obtidos no Instituto Nacional de Meteorologia (INMET). Resultados são apresentados por meio da aplicação do modelo L 2 P como rede neural e comparado a estruturas já existentes em redes neurais como o método ARIMA, evidenciando o bom desempenho da rede L 2 P .
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.