Forecasting of preprocessed daily solar radiation time series using neural networks

Abstract

Abstract. In this paper, we present an application of Artificial Neural Networks (ANNs) in the renewable energy domain. We particularly look at the Multi-Layer Perceptron (MLP) network which has been the most used of ANNs architectures both in the renewable energy domain and in the time series forecasting. We have used a MLP and an ad-hoc time series preprocessing to develop a methodology for the daily prediction of global solar radiation on a horizontal surface. First results are promising with nRMSE ~ 21% and RMSE ~ 3.59 MJ/m². The optimized MLP presents predictions similar to or even better than conventional and reference methods such as ARIMA techniques, Bayesian inference, Markov chains and k-Nearest-Neighbors.Moreover we found that the data preprocessing approach proposed can reduce significantly forecasting errors of about 6% compared to conventional prediction methods such as Markov chains or Bayes inferences. The simulator proposed has been obtained using 19 years of available data from the meteorological station of Ajaccio (Corsica Island, France, 41°55'N, 8°44'E, 4 m above mean sea level). The predicted whole methodology has been validated on a 1.175 kWc mono-Si PV power grid. Six prediction methods (ANN, clear sky model, combination …) allow to predict the best daily DC PV power production at horizon d+1.The cumulated DC PV energy on a 6-months period shows a great agreement between simulated and measured data (R² > 0.99 and nRMSE < 2%). Keywords

K-NN Decomposition Artificial Neural Network Models for Global Solar

“…Solar radiation forecasting with multiple parameters neural networks have been proposed in [22]. The authors of [23] have presented about estimation of hourly global solar irradiation on tilted absorbers from horizontal one using ANN have been proposed in [24]. However, all of the aforementioned only consider one station and do not consider the station its surround.…”

Solar Irradiance Forecasting Using Intelligent Technology

“…The accuracy of solar irradiance forecasting is the basis of solar power forecasting [1][2][3][4][5][6]. There are many intelligent approaches to forecast solar irradiance, such as neural networks [7][8][9][10][11][12][13]. …”

Photovoltaic power forecasting with a rough set combination method

“…Various approaches can be categorized into two types: physical methods and statistical methods. The physical models are based on numerical weather prediction (NWP) to predict solar radiation and then input into PV power output models to obtain the PV output power [2]- [6]. In [6], AR and AR with exogenous input models are implemented, using as input the NWP to forecast the hourly values of the PV power of a system installed in Denmark.…”