Methodology for predicting sequences of mean monthly clearness index and daily solar radiation data in remote areas: Application for sizing a stand-alone PV system

In this paper, a suitable adaptive neuro-fuzzy inference system (ANFIS) model is presented for estimating sequences of mean monthly clearness index (K¯t) and total solar radiation data in isolated sites based on geographical coordinates. The magnitude of solar radiation is the most important parameter for sizing photovoltaic (PV) systems. The ANFIS model is trained by using a multi-layer perceptron (MLP) based on fuzzy logic (FL) rules. The inputs of the ANFIS are the latitude, longitude, and altitude, while the outputs are the 12-values of mean monthly clearness index K¯t. These data have been collected from 60 locations in Algeria. The results show that the performance of the proposed approach in the prediction of mean monthly clearness index K¯t is favorably compared to the measured values. The root mean square error (RMSE) between measured and estimated values varies between 0.0215 and 0.0235 and the mean absolute percentage error (MAPE) is less than 2.2%. In addition, a comparison between the results obtained by the ANFIS model and artificial neural network (ANN) models, is presented in order to show the advantage of the proposed method. An example for sizing a stand-alone PV system is also presented. This technique has been applied to Algerian locations, but it can be generalized for any geographical position. It can also be used for estimating other meteorological parameters such as temperature, humidity and wind speed.

[1]  K. R. Agha,et al.  On the sizing parameters for stand-alone solar-energy systems , 2000 .

[2]  Adel Mellit,et al.  An adaptive artificial neural network model for sizing stand-alone photovoltaic systems: application for isolated sites in Algeria , 2005 .

[3]  Madan M. Gupta,et al.  Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory , 2003 .

[4]  Jorge Aguilera,et al.  Generation of hourly irradiation synthetic series using the neural network multilayer perceptron , 2002 .

[5]  J. M. Pinazo,et al.  Methodology for generating daily clearness index index values Kt starting from the monthly average daily value K̄t. Determining the daily sequence using stochastic models , 2003 .

[6]  G. Mihalakakou,et al.  The total solar radiation time series simulation in Athens, using neural networks , 2000 .

[7]  Mariano Sidrach-de-Cardona,et al.  A simple model for sizing stand alone photovoltaic systems , 1998 .

[8]  Junhong Nie.  Nonlinear time-series forecasting: A fuzzy-neural approach , 1997, Neurocomputing.

[9]  L. Umanand,et al.  Estimation of global radiation using clearness index model for sizing photovoltaic system , 2005 .

[10]  Francesco Masulli,et al.  Building a neuro-fuzzy system to efficiently forecast chaotic time series , 1997 .

[11]  M. Collares-Pereira,et al.  Simple procedure for generating sequences of daily radiation values using a library of Markov transition matrices , 1988 .

[12]  Soteris A. Kalogirou,et al.  Application of Neural Networks and Genetic Algorithms for Predicting the Optimal Sizing Coefficient of Photovoltaic Supply (PVS) Systems , 2006 .

[13]  Tom Markvart,et al.  PV system sizing using observed time series of solar radiation , 2006 .

[14]  Georgios Dounias,et al.  Decision making on noisy time-series data under a neuro-genetic fuzzy rule-based system approach , 1999 .

[15]  Jorge Aguilera,et al.  An application of the multilayer perceptron: Solar radiation maps in Spain , 2005 .

[16]  Peter P. Groumpos,et al.  An optimal sizing method for stand-alone photovoltaic power systems , 1987 .

[17]  A. Mellit,et al.  An ANFIS-based Forecasting for Solar Radiation Data from Sunshine Duration and Ambient Temperature , 2007, 2007 IEEE Power Engineering Society General Meeting.

[18]  M. Collares-Pereira,et al.  TAG: A time-dependent, autoregressive, Gaussian model for generating synthetic hourly radiation , 1992 .

[19]  S. Mercy Shalinie,et al.  Modeling Connectionist Neuro-Fuzzy network and Applications , 2005, Neural Computing & Applications.

[20]  Athanasios V. Vasilakos,et al.  ASAFES2: a novel, neuro-fuzzy architecture for fuzzy computing, based on functional reasoning , 1996, Fuzzy Sets Syst..

[21]  Soteris A. Kalogirou,et al.  An adaptive wavelet-network model for forecasting daily total solar-radiation , 2006 .

[22]  L. Goel,et al.  A study on optimal sizing of stand-alone photovoltaic stations , 1998 .

[23]  Miguel Ángel Egido,et al.  The sizing of stand alone PV-system: A review and a proposed new method , 1992 .

[24]  Adel Mellit,et al.  A simplified model for generating sequences of global solar radiation data for isolated sites: Using artificial neural network and a library of Markov transition matrices approach , 2005 .

[25]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[26]  Nils J. Nilsson,et al.  Artificial Intelligence: A New Synthesis , 1997 .

[27]  Rudolf Kruse,et al.  DESIGNING NEURO-FUZZY SYSTEMS THROUGH BACKPROPAGATION , 1996 .

[28]  Shuanghua Cao,et al.  Forecast of solar irradiance using recurrent neural networks combined with wavelet analysis , 2005 .

[29]  Adnan Sözen,et al.  Forecasting based on neural network approach of solar potential in Turkey , 2005 .

[30]  Jorge Aguilera,et al.  A new approach for sizing stand alone photovoltaic systems based in neural networks , 2005 .

[31]  Zhengxin Chen.  Computational intelligence for decision support , 1999 .

[32]  Ali Naci Celik,et al.  A critical review on the estimation of daily global solar radiation from sunshine duration , 2006 .

[33]  Georgios Dounias,et al.  Hybrid Computational Intelligence Schemes in Complex Domains: An Extended Review , 2002, SETN.

[34]  A. Mellit,et al.  Artificial neural network model for prediction solar radiation data: application for sizing stand-alone photovoltaic power system , 2005, IEEE Power Engineering Society General Meeting, 2005.

[35]  L. Mora-López,et al.  Multiplicative ARMA models to generate hourly series of global irradiation , 1998 .

[36]  Mohamed Mohandes,et al.  USE OF RADIAL BASIS FUNCTIONS FOR ESTIMATING MONTHLY MEAN DAILY SOLAR RADIATION , 2000 .