In this work, genetic algorithms (GA) and particle swarm optimization (PSO) are used to make an automated choice of hyperparameters of the MLP-NARX, ELM-NARX, and ESNNARX neural models applied to the identification of two photovoltaic systems: one installed in Teresina, in Brazil, and another in Hamburg, Germany. The automatic optimization process results showed that the PSO algorithm presents superior performance compared to the GA algorithm. Likewise, the identification carried out aimed to estimate the power generated by photovoltaic systems from two different approaches: linear mathematical models and neural identification models. Thus, the neural models implemented are more efficient and accurate than the linear mathematical models compared. From accuracy, the neural models ESNNARX and MLP-NARX were considered the best in identifying Hamburg and Teresina's photovoltaic systems, respectively.
The use of alternative sources of energy has been growing in recent years, in this context, photovoltaic solar energy has a great presence in this market, having been a great source of world energy. Consequently, new methods of identifying models of photovoltaic solar generation need to be implemented in search of an adequate energy program. Artificial neural networks have been used for computational solar incidents based on meteorological and environmental parameters. However, the use of Multiple Input Single Output (MISO) models for photovoltaic generation has been little explored by the researchers. In this work I use artificial neural networks with multiple linear layers and regression to estimate a generation of photovoltaic solar energy for a photovoltaic system to a series of variables of direct horizontal solar radiation, wind velocity and ambient temperature. Resumo: O uso de fontes alternativas de energia vem crescendo consideravelmente nos últimos anos, neste âmbito, a energia solar fotovoltaica tem apresentado grande participação nesse mercado, aumentado a sua participação na matriz energética mundial. Consequentemente, novos métodos de identificação de modelos de geração solar fotovoltaica precisam ser implementados em busca de um planejamento energético adequado. Nesse sentido, redes neurais artificiais têm sido usadas para calcular a radiação solar incidente baseado em parâmetros meteorológicos e ambientais. Entretanto, a utilização de modelos Multiple Input Single Output (MISO) para geração em sistemas fotovoltaicos tem sido pouco explorada pelos pesquisadores. Neste trabalho utilizou-se redes neurais artificiais de múltiplas camadas e regressão linear múltipla para estimar a geração solar fotovoltaica para um sistema fotovoltaico conectado à rede elétrica baseado em variáveis de radiação solar direta horizontal, velocidade do vento e temperatura ambiente.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.