Abstract: Modelling and simulation of stand-alone photovoltaic (SAPV) systems (PV module, battery, regulator, etc.) in real time is crucial for the control, the supervision, the diagnosis and for studying their performances. In this paper, an intelligent simulator for stand-alone PV system was developed. Firstly, a multilayer perceptron (MLP) has been used for modelling and simulating each component of the system, after that the optimal architecture for each component has been implemented and simulated by using the very high-speed description language (VHDL) and the ModelSim. Subsequently, the developed architectures for each component have been implemented under the Xilinx® Virtex-II Pro FPGA (XC2V1000) (field programmable gate array). The obtained results showed that good accuracy is found between predicted and experimental data (signal) in a specific location (south of Algeria). The designed intelligent components (PV-MLP generator, MLP-battery and MLP-regulator) of the SAPV system can be used with success for simulating the system in real time (under a specific climatic condition) by predicting the different output signals for each component constituting the system.
Abstract: In this paper, an adaptive model for predicting hourly global, diffuse and direct solar irradiance is described. A dataset of measured air temperature, relative humidity, direct, diffuse and global horizontal irradiance for Jeddah site (Saudi Arabia) were used in this study. Several combinations have been proposed, and the best performance is obtained by using sunshine duration, air temperature and relative humidity as inputs of the developed adaptive [alpha]-model. A good agreement between measured and predicted data is obtained. In fact, the correlation coefficient is more than 97% and the mean bias error is less than 0.8. A comparison between a Feed-Forward Neural Network (FFNN) and the adaptive proposed model is presented in order to demonstrate his performance.
Abstract: Recent advances in artificial intelligence techniques have allowed the application of such technologies in real engineering problems. In this paper, an artificial neural network-based genetic algorithm (ANN-GA) model was developed for generating the sizing curve of stand-alone photovoltaic (SAPV) systems. Due to the high computing time needed for generating the sizing curves and complex architecture of the neural networks, the genetic algorithm is used in order to find the optimal architecture of the ANN (number of hidden layers and the number of neurons within each hidden layer). Firstly, a numerical method is used for generating the sizing curves for different loss of load probability (LLP) corresponding to 40 sites located in Algeria. The inputs of ANN-GA are the geographical coordinates and the LLP while the output is the sizing curve represented by CAÂ =Â f(CS) (i.e., 30-points were taken from each sizing curve). Subsequently, the proposed ANN-GA model has been trained by using a set of 36 sites, whereas data for 4 sites (randomly selected) which are not included in the training dataset have been used for testing the ANN-GA model. The results obtained are compared and tested with those of the numerical method in order to show the effectiveness of the proposed approach.
Abstract: Artificial intelligence (AI) techniques are becoming useful as alternate approaches to conventional techniques or as components of integrated systems. They have been used to solve complicated practical problems in various areas and are becoming more and more popular nowadays. AI-techniques have the following features: can learn from examples; are fault tolerant in the sense that they are able to handle noisy and incomplete data; are able to deal with non-linear problems; and once trained can perform prediction and generalization at high speed. AI-based systems are being developed and deployed worldwide in a myriad of applications, mainly because of their symbolic reasoning, flexibility and explanation capabilities. AI have been used and applied in different sectors, such as engineering, economics, medicine, military, marine, etc. They have also been applied for modeling, identification, optimization, prediction, forecasting, and control of complex systems. The main objective of this paper is to present an overview of the AI-techniques for sizing photovoltaic (PV) systems: stand-alone PVs, grid-connected PV systems, PV-wind hybrid systems, etc. Published literature presented in this paper show the potential of AI as a design tool for the optimal sizing of PV systems. Additionally, the advantage of using an AI-based sizing of PV systems is that it provides good optimization, especially in isolated areas, where the weather data are not always available.
Abstract: In this paper, an artificial neural network (ANN) models for estimating and modelling of daily global solar radiation have been developed. The data used in this work are the global irradiation HG, diffuse irradiation HD, air temperature T and relative humidity Hu. These data are available from 1998 to 2002 at the National Renewable Energy Laboratory (NREL) website. We have developed six ANN-models by using different combination as inputs: the air temperature, relative humidity, sunshine duration and the day of year. For each model, the output is the daily global solar radiation. Firstly, a set of 4 × 365 points (4 years) has been used for training each networks, while a set of 365 points (1 year) has been used for testing and validating the ANN-models. It was found that the model using sunshine duration and air temperature as inputs, gives good accurate results since the correlation coefficient is 97.65%. A comparative study between developed ANN-models and conventional regression models is presented in this study.
Abstract: In this paper, a suitable adaptive neuro-fuzzy inference system (ANFIS) model is presented for estimating sequences of mean monthly clearness index () 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 . 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 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.
Abstract: Artificial intelligence (AI) techniques are becoming useful as alternate approaches to conventional techniques or as components of integrated systems. They have been used to solve complicated practical problems in various areas and are becoming more popular nowadays. They can learn from examples, are fault tolerant in the sense that they are able to handle noisy and incomplete data, are able to deal with nonlinear problems and once trained can perform prediction and generalization at high speed. AI-based systems are being developed and deployed worldwide in a wide variety of applications, mainly because of their symbolic reasoning, flexibility and explanation capabilities. AI has been used in different sectors, such as engineering, economics, medicine, military, marine, etc. They have also been applied for modeling, identification, optimization, prediction, forecasting and control of complex systems. The paper outlines an understanding of how AI systems operate by way of presenting a number of problems in photovoltaic systems application. Problems presented include three areas: forecasting and modeling of meteorological data, sizing of photovoltaic systems and modeling, simulation and control of photovoltaic systems. Published literature presented in this paper show the potential of AI as design tool in photovoltaic systems.
Abstract: This paper presents an adaptive artificial neural network (ANN) for modeling and simulation of a Stand-Alone photovoltaic (SAPV) system operating under variable climatic conditions. The ANN combines the Levenberg-Marquardt algorithm (LM) with an infinite impulse response (IIR) filter in order to accelerate the convergence of the network. SAPV systems are widely used in renewable energy source (RES) applications and it is important to be able to evaluate the performance of installed systems. The modeling of the complete SAPV system is achieved by combining the models of the different components of the system (PV-generator, battery and regulator). A global model can identify the SAPV characteristics by knowing only the climatological conditions. In addition, a new procedure proposed for SAPV system sizing is presented in this work. Different measured signals of solar radiation sequences and electrical parameters (photovoltaic voltage and current) from a SAPV system installed at the south of Algeria have been recorded during a period of 5-years. These signals have been used for the training and testing the developed models, one for each component of the system and a global model of the complete system. The ANN model predictions allow the users of SAPV systems to predict the different signals for each model and identify the output current of the system for different climatological conditions. The comparison between simulated and experimental signals of the SAPV gave good results. The correlation coefficient obtained varies from 90% to 96% for each estimated signals, which is considered satisfactory. A comparison between multilayer perceptron (MLP), radial basis function (RBF) network and the proposed LM-IIR model is presented in order to confirm the advantage of this model.
Abstract: In this paper, we investigate using an adaptive radial basis function (RBF) network with infinite impulse response (IIR) filter in order to find a suitable model for sizing coefficients of the stand-alone photovoltaic (PV) systems, based on minimum of input data. These sizing coefficients allow to the users of stand-alone PV systems to determine the number of solar panel and storage batteries necessary to satisfy a given consumption, especially in isolated sites where the global solar radiation data is not always available. Obtained results by feed-forward MLP, RBF and an adaptive RBF-IIR model have been compared with real sizing coefficients. The adaptive RBFIIR has been trained by using 200 known sizing coefficients values corresponding to 200 locations in Algeria. In this way, the adaptive model was trained to accept and even handle a number of unusual cases. The unknown validation sizing coefficients set produced very set accurate estimation with the correlation coefficient between the actual and the RBF-IIR model estimated data of 97% was obtained. This result indicates that the proposed method can be successfully used for estimating of optimal sizing coefficients of PV systems for any locations in Algeria, but the methodology can be generalized using different locations in the world.
Notes: The Ninth Arab International Conference on Solar Energy (AICSE-9), Kingdom of Bahrain
Abstract: The combination of wavelet theory and neural networks has lead to the development of wavelet networks. Wavelet-networks are feed-forward networks using wavelets as activation functions. Wavelet-networks have been used successfully in various engineering applications such as classification, identification and control problems. In this paper, the use of adaptive wavelet-network architecture in finding a suitable forecasting model for predicting the daily total solar-radiation is investigated. Total solar-radiation is considered as the most important parameter in the performance prediction of renewable energy systems, particularly in sizing photovoltaic (PV) power systems. For this purpose, daily total solar-radiation data have been recorded during the period extending from 1981 to 2001, by a meteorological station in Algeria. The wavelet-network model has been trained by using either the 19 years of data or one year of the data. In both cases the total solar radiation data corresponding to year 2001 was used for testing the model. The network was trained to accept and handle a number of unusual cases. Results indicate that the model predicts daily total solar-radiation values with a good accuracy of approximately 97% and the mean absolute percentage error is not more than 6%. In addition, the performance of the model was compared with different neural network structures and classical models. Training algorithms for wavelet-networks require smaller numbers of iterations when compared with other neural networks. The model can be used to fill missing data in weather databases. Additionally, the proposed model can be generalized and used in different locations and for other weather data, such as sunshine duration and ambient temperature. Finally, an application using the model for sizing a PV-power system is presented in order to confirm the validity of this model.
Abstract: The purpose of this work is to develop a hybrid model which will be used to predict the daily global solar radiation data by combining between an artificial neural network (ANN) and a library of Markov transition matrices (MTM) approach. Developed model can generate a sequence of global solar radiation data using a minimum of input data (latitude, longitude and altitude), especially in isolated sites. A data base of daily global solar radiation data has been collected from 60 meteorological stations in Algeria during 1991-2000. Also a typical meteorological year (TMY) has been built from this database. Firstly, a neural network block has been trained based on 60 known monthly solar radiation data from the TMY. In this way, the network was trained to accept and even handle a number of unusual cases. The neural network can generate the monthly solar radiation data. Secondly, these data have been divided by corresponding extraterrestrial value in order to obtain the monthly clearness index values. Based on these monthly clearness indexes and using a library of MTM block we can generate the sequences of daily clearness indexes. Known data were subsequently used to investigate the accuracy of the prediction. Furthermore, the unknown validation data set produced very accurate prediction; with an RMSE error not exceeding 8% between the measured and predicted data. A correlation coefficient ranging from 90% and 92% have been obtained; also this model has been compared to the traditional models AR, ARMA, Markov chain, MTM and measured data. Results obtained indicate that the proposed model can successfully be used for the estimation of the daily solar radiation data for any locations in Algeria by using as input the altitude, the longitude, and the latitude. Also, the model can be generalized for any location in the world. An application of sizing PV systems in isolated sites has been applied in order to confirm the validity of this model.
Abstract: In this paper we investigate, the possibility of using an adaptive Artificial Neural Network (ANN), in order to find a suitable model for sizing Stand-Alone Photovoltaic (SAPV) systems, based on a minimum of input data. The model combines Radial Basis Function (RBF) network and Infinite Impulse Response (IIR) filter in order to accelerate the convergence of the network. For the sizing of a photovoltaic (PV) systems, we need to determine the optimal sizing coefficients (KPV, KB). These coefficients allow us to determine the number of solar panels and storage batteries necessary to satisfy a given consumption, especially in isolated sites where the global solar radiation data is not always available. These coefficients are considered the most important parameters for sizing a PV system. Results obtained by classical models (analytical, numerical, analytical-numerical, B-spline function) and new models like feed-forward (MLP), radial basis function (RBF), MLP-IIR and RBF-IIR are compared with experimental sizing coefficients in order to illustrate the accuracy of the new developed model. This model has been trained by using 200 known optimal sizing coefficients corresponding to 200 locations in Algeria. In this way, the adaptive model was trained to accept and handle a number of unusual cases. The unknown validation sizing coefficients set produced very accurate estimation with a correlation coefficient of 98%. This result indicates that the proposed method can be successfully used for the estimation of optimal sizing coefficients of SAPV systems for any locations in Algeria. The methodology proposed in this paper however, can be generalized using different locations of the world.
