Statistical modeling for global solar radiation forecasting in Bogot&amp;#x00E1;

Perdomo, R.; Banguero, Edison; Gordillo, G.

doi:10.1109/pvsc.2010.5614388

Cited by 19 publications

(9 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Time series approaches primarily aim at the modeling of long-term solar irradiance forecast, which includes Moving Average (MA), Autoregressive (AR) [20], Autoregressive Moving Average (ARMA) [21], and Autoregressive Integrated Moving Average (ARIMA) [22] models. The time series forecasting model only requires historical irradiance data, in which the relevant meteorological factors are not involved.…”

Section: Literature Reviewmentioning

confidence: 99%

Wavelet Decomposition and Convolutional LSTM Networks Based Improved Deep Learning Model for Solar Irradiance Forecasting

et al. 2018

View full text Add to dashboard Cite

Solar photovoltaic (PV) power forecasting has become an important issue with regard to the power grid in terms of the effective integration of large-scale PV plants. As the main influence factor of PV power generation, solar irradiance and its accurate forecasting are the prerequisite for solar PV power forecasting. However, previous forecasting approaches using manual feature extraction (MFE), traditional modeling and single deep learning (DL) models could not satisfy the performance requirements in partial scenarios with complex fluctuations. Therefore, an improved DL model based on wavelet decomposition (WD), the Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) is proposed for day-ahead solar irradiance forecasting. Given the high dependency of solar irradiance on weather status, the proposed model is individually established under four general weather type (i.e., sunny, cloudy, rainy and heavy rainy). For certain weather types, the raw solar irradiance sequence is decomposed into several subsequences via discrete wavelet transformation. Then each subsequence is fed into the CNN based local feature extractor to automatically learn the abstract feature representation from the raw subsequence data. Since the extracted features of each subsequence are also time series data, they are individually transported to LSTM to construct the subsequence forecasting model. In the end, the final solar irradiance forecasting results under certain weather types are obtained via the wavelet reconstruction of these forecasted subsequences. This case study further verifies the enhanced forecasting accuracy of our proposed method via a comparison with traditional and single DL models.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Wavelet Decomposition and Convolutional LSTM Networks Based Improved Deep Learning Model for Solar Irradiance Forecasting

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Among these, the most effective in producing hour-ahead predictions are based on empirical regression, neural networks [6] and time-series models (e.g., ARMA, ARIMA) [7] [8].…”

Section: Politecnico DI Milanomentioning

confidence: 99%

Statistical models approach for solar radiation prediction

Ferrari

Lazzaroni

Piuri

et al. 2013

2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)

View full text Add to dashboard Cite

It is well known that the knowledge of solar radiation represents a key for managing photovoltaic (PV) plants. In a smart grid scenario to predict the energy production can be considered a milestone. However, the unsteadiness of the weather phenomena makes the prediction of the energy produced by the solar radiation conversion process a difficult task. Starting from this considerations, the use of the data collected in the past represents only the first step in order to evaluate the variability both in a daily and seasonal fashion. In order to have a stronger dataset a multi-year observation is mandatory. In his paper, several autoregressive models are challenged on a two-year ground global horizontal radiation dataset measured in Milan,and the results are compared with those of simple predictor

show abstract

“…Several forecasting approaches have been used in literature. Among these, the most effective in producing hour-ahead predictions are based on empirical regression, neural networks [9] and time-series models (e.g., ARMA, ARIMA) [10,11]. However, day/month/year ahead forecast has been carried out by several researchers.…”

Section: Introductionmentioning

confidence: 99%

Time Series and Empirical Orthogonal Transformation Using Meteorological Parameters across the Climatic Zones in Nigeria

Akpootu

Tijjani

Gana

2019

IJECC

View full text Add to dashboard Cite

Time series and empirical orthogonal transformation analysis was carried out for four (4) selected tropical sites, which are situated across the four different climatic zones, viz. Sahelian, Midland, Guinea savannah and Coastal region in Nigeria using measured monthly average daily global solar radiation, maximum and minimum temperatures, sunshine hours, rainfall, wind speed, cloud cover and relative humidity meteorological data during the period of thirty one years (1980-2010). Seasonal Auto Regressive Integrated Moving Average (ARIMA) models were developed along with their respective statistical indicators of coefficient of determination (R2), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE). The results indicated that the models were found suitable for one step ahead global solar radiation forecast for the studied locations. Furthermore, the results of the time series analysis revealed that the model type for all the meteorological parameters show a combination of simple seasonal with one or more of either ARIMA, winter’s additive and winter’s multiplicative with the level been more significant as compared to the trend and seasonal variations for the exponential smoothing model parameters in all the locations. The results of the correlation matrix revealed that the global solar radiation is more correlated to the mean temperature except for Akure where it is more correlated to the sunshine hours; the mean temperature is more correlated to the global solar radiation; the rainfall is more correlated to the relative humidity and the relative humidity is more correlated to the rainfall in all the locations. The results of the component matrix revealed that three seasons are identified in Nguru located in the Sahelian region namely, the rainy, the cool dry (harmattan) and the hot dry seasons while in Zaria, Makurdi and Akure located in the Midland, Guinea savannah and Coastal zones two distinct seasons are identified namely, the rainy and dry seasons.

show abstract

Statistical modeling for global solar radiation forecasting in Bogotá

Cited by 19 publications

References 3 publications

Wavelet Decomposition and Convolutional LSTM Networks Based Improved Deep Learning Model for Solar Irradiance Forecasting

Wavelet Decomposition and Convolutional LSTM Networks Based Improved Deep Learning Model for Solar Irradiance Forecasting

Statistical models approach for solar radiation prediction

Time Series and Empirical Orthogonal Transformation Using Meteorological Parameters across the Climatic Zones in Nigeria

Contact Info

Product

Resources

About