Artificial Neural Network and Wavelet Decomposition in the Forecast of Global Horizontal Solar Radiation

Júnior, Luiz Albino Teixeira; Souza, Rafael Morais de; Menezes, Moisés Lima de; Cassiano, Keila Mara; Pessanha, José Francisco Moreira; Souza, Reinaldo Castro

doi:10.1590/0101-7438.2015.035.01.0073

Cited by 14 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An artificial neural network can be understood as a parallel processor that tends to preserve the knowledge gained through learning for its future use. They represent an artificial model of the human brain [53]. Knowledge is acquired by neurons during supervised learning, where the relationships between inputs and outputs are mapped.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Comparison of Heat Demand Prediction Using Wavelet Analysis and Neural Network for a District Heating Network

et al. 2021

View full text Add to dashboard Cite

Short-Term Load Prediction (STLP) is an important part of energy planning. STLP is based on the analysis of historical data such as outdoor temperature, heat load, heat consumer configuration, and the seasons. This research aims to forecast heat consumption during the winter heating season. By preprocessing and analyzing the data, we can determine the patterns in the data. The results of the data analysis make it possible to form learning algorithms for an artificial neural network (ANN). The biggest disadvantage of an ANN is the lack of precise guidelines for architectural design. Another disadvantage is the presence of false information in the analyzed training data. False information is the result of errors in measuring, collecting, and transferring data. Usually, trial error techniques are used to determine the number of hidden nodes. To compare prediction accuracy, several models have been proposed, including a conventional ANN and a wavelet ANN. In this research, the influence of different learning algorithms was also examined. The main differences were the training time and number of epochs. To improve the quality of the raw data and remove false information, the research uses the technology of normalizing raw data. The basis of normalization was the technology of the Z-score of the data and determination of the energy‒entropy ratio. The purpose of this research was to compare the accuracy of various data processing and neural network training algorithms suitable for use in data-driven (black box) modeling. For this research, we used a software application created in the MATLAB environment. The app uses wavelet transforms to compare different heat demand prediction methods. The use of several wavelet transforms for various wavelet functions in the research allowed us to determine the best algorithm and method for predicting heat production. The results of the research show the need to normalize the raw data using wavelet transforms. The sequence of steps involves following milestones: normalization of initial data, wavelet analysis employing quantitative criteria (energy, entropy, and energy‒entropy ratio), optimization of ANN training with information energy–entropy ratio, ANN training with different training algorithms, and evaluation of obtained outputs using statistical methods. The developed application can serve as a control tool for dispatchers during planning.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Comparison of Heat Demand Prediction Using Wavelet Analysis and Neural Network for a District Heating Network

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Contrary to many linear statistical forecasting models, stationarity is not required by ANN methods (see e.g. TEIXEIRA JR. et al, 2015).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Time Series Forecasting by Using a Neural Arima Model Based on Wavelet Decomposition

Pereira

Scarpin

Júnior

2016

Ind. Jour. Man. & Prod.

View full text Add to dashboard Cite

In the prediction of (stochastic) time series, it has been common to suppose that an individual predictive method-for instance, an Auto-Regressive Integrated Moving Average (ARIMA) model-produces residuals like a white noise process. However, mainly due to the structures of auto-dependence not mapped by a given individual predictive method, this assumption might be easily violated, in practice, as pointed out by Firmino et al. (2015). In order to correct it

show abstract

“…Dentre as diversas técnicas usadas na análise, modelagem e previsão de séries temporais é possível citar: a teoria Wavelet, a metodologia de Box e Jenkins, o método Support Vector Regression e a combinação de previsões. Maiores detalhes sobre estas aplicações são encontrados nos seguintes trabalhos: (HAAR, 1911), (MALLAT, 2009), (BOX;REINSEL, 2008b), (VAPNIK, 2005), (SMOLA; SCHÖLKOPF, 1998), (BATES;GRANGER, 2001) e (TEIXEIRA JR et al, 2015).…”

Section: Introductionunclassified

Previsão de Deslocamentos Verticais Medido por Extensômetros de um Bloco da Barragem da Usina Hidrelétrica de Itaipu

Rodrigues

Hickmann

Corrêa

et al. 2018

Cereus

View full text Add to dashboard Cite

RESUMOEste artigo apresenta a modelagem de séries temporais provenientes dos extensômetros EM-I-7-1 e EM-I-9-1 instalados na fundação e localizados no bloco I10 da Barragem da Usina de Itaipu. Para tanto foi utilizado o método híbrido para previsões de séries temporais chamada SARIMA Support Vector Regression Wavelet de Múltiplos Núcleos (SSVRWMN) para a projeção dos deslocamentos verticais de um bloco da barragem da usina hidrelétrica de Itaipu. A projeção dos deslocamentos verticais consiste em uma das observações mais importantes na supervisão do comportamento da estrutura da barragem. Todos os resultados estatísticos alcançados por SSVRWMN são mais acurados que outras técnicas tradicionais (usadas aqui como benchmark), encorajando a sua adoção para tal finalidade. ABSTRACTThis paper presents the modeling of time series from extensometers EM-I-7-1 and EM-I-9-1 installed in the foundation and located in the block I10 of the Itaipu Dam by hybrid methodology for time series forecasts called SARIMA Support Vector Regression Wavelet of Multiple Kernel (SSVRWMN) for the projection of the vertical displacements of a dam block of the Itaipu hydroelectric power plant, which consist of one of the most important observations in the supervision of the behavior of the dam structure. All the statistical results achieved by SSVRWMN are more accurate than other traditional techniques (used here as benchmark), encouraging their adoption for this purpose.

show abstract

Artificial Neural Network and Wavelet Decomposition in the Forecast of Global Horizontal Solar Radiation

Cited by 14 publications

References 9 publications

Comparison of Heat Demand Prediction Using Wavelet Analysis and Neural Network for a District Heating Network

Comparison of Heat Demand Prediction Using Wavelet Analysis and Neural Network for a District Heating Network

Time Series Forecasting by Using a Neural Arima Model Based on Wavelet Decomposition

Previsão de Deslocamentos Verticais Medido por Extensômetros de um Bloco da Barragem da Usina Hidrelétrica de Itaipu

Contact Info

Product

Resources

About