Improved artificial neural network method for predicting photovoltaic output performance

To ensure the safety and stability of power grids with photovoltaic (PV) generation integration, it is necessary to predict the output performance of PV modules under varying operating conditions. In this paper, an improved artificial neural network (ANN) method is proposed to predict the electrical characteristics of a PV module by combining several neural networks under different environmental conditions. To study the dependence of the output performance on the solar irradiance and temperature, the proposed neural network model is composed of four neural networks, it called multi- neural network (MANN). Each neural network consists of three layers, in which the input is solar radiation, and the module temperature and output are five physical parameters of the single diode model. The experimental data were divided into four groups and used for training the neural networks. The electrical properties of PV modules, including I–V curves, P– V curves, and normalized root mean square error, were obtained and discussed. The effectiveness and accuracy of this method is verified by the experimental data for different types of PV modules. Compared with the traditional single-ANN (SANN) method, the proposed method shows better accuracy under different operating conditions.     

Neural network based estimation of maximum power generation from PVmodule using environmental information

This paper presents an application of an artificial neural network for the estimation of maximum power generation from PV module. The output power from a PV module depends on environmental factors such as irradiation and cell temperature. For the operation planning of power systems, the prediction of the power generation is inevitable for PV systems. For this purpose, irradiation, temperature and wind velocity are utilized as the input information to the proposed neural network. The output is the predicted maximum power generation under the condition given by those environmental factors. The efficiency of the proposed estimation scheme is evaluated by using actual data on daily, monthly and yearly bases. The proposed method gives highly accurate predictions compared with predictions using the conventional multiple regression model     

Insolation-oriented model of photovoltaic module using Matlab/Simulink

This paper presents a novel model of photovoltaic (PV) module which is implemented and analyzed using Matlab/Simulink software package. Taking the effect of sunlight irradiance on the cell temperature, the proposed model takes ambient temperature as reference input and uses the solar insolation as a unique varying parameter. The cell temperature is then explicitly affected by the sunlight intensity. The output current and power characteristics are simulated and analyzed using the proposed PV model. The model verification has been confirmed through an experimental measurement. The impact of solar irradiation on cell temperature makes the output characteristic more practical. In addition, the insolation-oriented PV model enables the dynamics of PV power system to be analyzed and optimized more easily by applying the environmental parameters of ambient temperature and solar irradiance.     

On the investigation of photovoltaic output power reduction due to dust accumulation and weather conditions

Certain environmental conditions such as accumulation of dust and change in weather conditions affect the amount of solar radiation received by photovoltaic (PV) panel surfaces and thus have a significant effect on panel efficiency. This study conducted an experimental investigation in Surabaya, Indonesia, on the effect of these factors on output PV power reduction from the surface of a PV module. The module was exposed to outside weather conditions and connected to a measurement system developed using a rule-based model to identify different environmental conditions. The rule-based model, a clear sky solar irradiance model that included solar position, and a PV temperature model were then used to estimate the PV output power, and tests were also conducted using an ARM Cortex-M4 microcontroller STM32F407 as a standalone digital controller equipped with voltage, current, temperature, and humidity sensors to measure real time PV output power. In this system, humidity was monitored to identify dusty, cloudy, and rainy conditions. Validated test results demonstrate that the prediction error of PV power output based on the model is 3.6% compared to field measurements under clean surface conditions. The effects of dust accumulation and weather conditions on PV panel power output were then analyzed after one to four weeks of exposure. Results revealed that two weeks of dust accumulation caused a PV power output reduction of 10.8% in an average relative humidity of 52.24%. Results of the experiment under rainy conditions revealed a decrease in PV output power of more than 40% in average relative humidity of 76.32%, and a decrease in output power during cloudy conditions of more than 45% in an average relative humidity of 60.45% was observed. This study reveals that local environmental conditions, i.e., dust, rain, and partial cloud, significantly reduce PV power output.     

Concentrating solar module with horizontal reflectors

A non-sun-tracking concentrating solar module is described that is designed to achieve photovoltaic (PV) systems with higher generation power density. The proposed concentrating module consists of a solar panel having a higher tilt angle than that of a conventional one and with a solar reflector placed in front of the solar panel on a downward inclination angle towards the panel. As a result of this configuration, the solar panel receives reflected as well as direct sunlight so that maximum irradiance and short-circuit current were increased. This configuration is expected to reduce the area required for solar panels, resulting in lower cost PV system.     

Performance of Si-based PV rooftop systems operated under distinct four seasons

We have investigated the electrical energy yield of hydrogenated amorphous silicon (a-Si:H) single-junction and crystalline (c-Si) photovoltaic (PV) rooftop systems operated under distinct four seasons. The impact of the module type and installed tilt angle on the annual electrical energy yield has been monitored and then compared with the data predicted by the computer simulation. Despite a good temperature coefficient and less shading effect of a-Si:H single-junction modules, the energy output gain of the a-Si:H single-junction PV generator is only 2.7% compared to the c-Si PV generator installed using c-Si PV modules. It is inferred that a nominal rated power of the a-Si:H single-junction modules determined by an indoor light soaking test is not suitable for the design of PV systems operated under distinct four seasons. Thus, the nominal rated power of the a-Si:H single-junction PV modules should be determined through a proper outdoor exposure test considering thermal annealing and light soaking effects under various seasonal weather conditions. In addition, it is found that the performance of the Si-based PV rooftop systems operated under distinct four seasons could be improved by simply toggling the tilt angle considering the plane-of-array irradiance and snowfall effect.     

Short term solar irradiance forecasting using a mixed wavelet neural network

In modern smart grids and deregulated electricity markets, accurate forecasting of solar irradiance is critical for determining the total energy generated by PV systems. We propose a mixed wavelet neural network (WNN) in this paper for short-term solar irradiance forecasting, with initial application in tropical Singapore. The key advantage of using wavelet transform (WT) based methods is the high signal compression ability of wavelets, making them suitable for modeling of nonstationary environmental parameters with high information content, such as short timescale solar irradiance. In this WNN, a combination of the commonly known Morlet and Mexican hat wavelets is used as the activation function for hidden-layer neurons of a feed forward artificial neural network (ANN). To demonstrate the effectiveness of the proposed approach, hourly predictions of solar irradiance, which is an aggregate sum of irradiance value observed using 25 sensors across Singapore, are considered. The forecasted results show that WNN delivers better prediction skill when compared with other forecasting techniques.     

Estimation of the maximum power and normal operating power of a photovoltaic module by neural networks

This paper presents an application of the neural networks for identification of the maximum power (MP) and the normal operating power (NOP) of a photovoltaic (PV) module. Two neural networks are developed; the first is the maximum power neural network (MPNN) and the second is the normal operating power neural network (NOPNN). The two neural networks receive the solar radiation and the PV module surface temperature as inputs, and estimate the MP and the NOP of a PV module as outputs. The training process for the two neural networks used a series of input/output data pairs. The training inputs are the solar radiation and the PV module surface temperature, while the outputs are the PV module MP for the MPNN and the PV module NOP for the NOPNN. The results showed that, the proposed neural networks introduced a good accurate prediction for the PV module MP and NOP compared with the measured values.     

Validation of the Sandia model with indoor and outdoor measurements for semi-transparent amorphous silicon PV modules

This paper presents a set of indoor and outdoor measurement methods and procedures to determine the empirical coefficients of the Sandia Array Performance Model (SAPM) for a semi-transparent amorphous silicon (a-Si) PV module. After determining and inputting the total 39 parameters into the SAPM, the dynamic power output of the a-Si PV module was predicted. In order to validate the accuracy of using SAPM for simulating the energy output of the a-Si PV module, a long-term outdoor testing campaign was conducted. The results indicated that the SAPM with indoor and outdoor measured coefficients could accurately simulate the energy output of the a-Si PV module on sunny days, but it didn't work well on overcast days due to the inappropriate spectral correction as well as the equipment measuring error caused by the intense fluctuation of solar irradiance on overcast days. Specifically, all the errors between the simulated daily energy output and the measured one were less than 4% on sunny days. In order to achieve a better prediction performance for a-Si PV technologies, the SAPM was suggested to incorporate a more comprehensive spectral correction function to correct the impact of solar spectrum on overcast days in future.     

Calculation of the polycrystalline PV module temperature using a simple method of energy balance

The performance of a photovoltaic module is studied versus environmental variables such as solar irradiance, ambient temperature and wind speed. Two types of simplified models are studied in this paper: a PV module temperature model and a PV module electrical efficiency model. These models have been validated utilizing experimental data from two experiments: a 850 Wp grid connected photovoltaic system and a p-Si module with eight temperature sensors integrated into the module. Both models have been coupled to determine the PV array output power versus the three meteorological parameters. This simple model using a simple energy balance and neglecting the radiation effects is in good agreement with the experimental data.     

A novel multi-model neuro-fuzzy-based MPPT for three-phase grid-connected photovoltaic system

This paper presents a novel methodology for Maximum Power Point Tracking (MPPT) of a grid-connected 20 kW photovoltaic (PV) system using neuro-fuzzy network. The proposed method predicts the reference PV voltage guarantying optimal power transfer between the PV generator and the main utility grid. The neuro-fuzzy network is composed of a fuzzy rule-based classifier and three multi-layered feed forwarded Artificial Neural Networks (ANN). Inputs of the network (irradiance and temperature) are classified before they are fed into the appropriated ANN for either training or estimation process while the output is the reference voltage. The main advantage of the proposed methodology, comparing to a conventional single neural network-based approach, is the distinct generalization ability regarding to the nonlinear and dynamic behavior of a PV generator. In fact, the neuro-fuzzy network is a neural network based multi-model machine learning that defines a set of local models emulating the complex and nonlinear behavior of a PV generator under a wide range of operating conditions. Simulation results under several rapid irradiance variations proved that the proposed MPPT method fulfilled the highest efficiency comparing to a conventional single neural network and the Perturb and Observe (P&O) algorithm dispositive.     

PV power conversion and short-term forecasting in a tropical,densely-built environment in Singapore

With the substantial growth of solar photovoltaic installations worldwide, forecasting irradiance becomes a critical step in providing a reliable integration of solar electricity into electric power grids. In Singapore, the number of PV installation has increased with a growth rate of 70% over the past 6 years. Within the next decade, solar power could represent up to 20% of the instant power generation. Challenges for PV grid integration in Singapore arise from the high variability in cloud movements and irradiance patterns due to the tropical climate. For a thorough analysis and modeling of the impact of an increasing share of variable PV power on the electric power system, it is indispensable (i) to have an accurate conversion model from irradiance to solar power generation, and (ii) to carry out irradiance forecasting on various time scales. In this work, we demonstrate how common assumptions and simplifications in PV power conversion methods negatively affect the output estimates of PV systems power in a tropical and densely-built environment such as in Singapore. In the second part, we propose and test a novel hybrid model for short-term irradiance forecasting for short-term intervals. The hybrid model outperforms the persistence forecast and other common statistical methods.     

Performance modeling and investigation of fixed, single and dual-axis tracking photovoltaic panel in Monastir city, Tunisia

Presented in this paper was an overview on research works on solar radiation basics and photovoltaic generation. Also, a complete PV modeling and investigation on the effect of using multi-axes sun-tracking systems on the electrical generation was carried out to evaluate its performance using the case study of the Monastir city, Tunisia. The effects of azimuth and tilt angles on the output power of a photovoltaic module were investigated. The instantaneous increments of the output power generated by a photovoltaic module mounted on a single and dual-axis tracking system relative to a traditional fixed panel were estimated. The results show that the yearly optimal tilt angle of a fixed panel faced due to the south is close to 0.9 times Monastir latitude. The gain made by the module mounted on a single-axis tracking panel relative to a traditional fixed panel was analyzed. The monthly increments of the gain are more noticeable for two critical periods which correspond to those surrounding the summer and the winter solstice dates. It reaches the value of 10.34% and 15% in the summer and winter solstice periods, respectively. However, the yearly gain relative to a fixed panel installed with the yearly optimal tilt angle is 5.76%. In some applications, covering loads at early morning or late afternoon hours and in order to more optimize the solar systems exploitation suggest the adjustment of the PV panel orientation to azimuth angles different from the south direction by using a dual-axis tracking installation. The gain made by this recommendation relative to a traditional fixed panel is evaluated. This gain reaches 30% and 44% respectively in the winter and summer solstice days.     

Clear-sky solar luminous efficacy determination using artificial neural networks

Under cloudless conditions, the effect of atmospheric variables, such as turbidity or water vapour, on luminous efficacy is an important source of variability, often limiting the use of simple empirical models to those sites where they were developed. Due to the complex functional relationship between these atmospheric variables and the luminous efficacy components, deriving a non-local model considering all these physical processes is nearly impossible if standard statistical techniques are employed. To avoid this drawback, the use of a new methodology based on artificial neural networks (ANN) is investigated here to determine the luminous efficacy of direct, diffuse and global solar radiation under cloudless conditions. In this purpose, a detailed spectral radiation model (SMARTS) is utilized to generate both illuminance and solar radiation values covering a large range of atmospheric conditions. Different input configurations using combinations of atmospheric variables and radiometric quantities are analyzed. Results show that an ANN model using direct and diffuse solar irradiance along with precipitable water is able to accurately reproduce the variations of the three components of luminous efficacy caused by solar zenith angle and the various atmospheric absorption and scattering processes. This proposed model is considerably simpler than the SMARTS radiation model it is derived from, but still can retain most of its predicting power and versatility. The proposed ANN model can thus be used worldwide, avoiding the need of using detailed atmospheric information or empirical models of the literature if radiometric measurements and precipitable water data (or temperature and relative humidity data) are available.     

光伏光热一体化组件性能实验探究与分析

通过搭建PV/T一体化组件性能测试实验台,测试在不同进口水温、不同一体化组件倾角和不同流量时PV/T一体化组件的热、电效率。结果表明,在进口水温30℃工况下一体化组件拥有最优的热效率值和输出电功率值,其日总热效率为35.97%,对应的输出电功率范围为29.40~30.51 W;45°倾角放置的一体化组件可接收到较多的太阳辐照度,且具有最优的光热性能,对应的日总热效率为32.65%;流量85 L/h工况下一体化组件拥有最优的热效率值,对应的日总热效率值为25.89%,串联50Ω电阻时组件的输出电功率随流量的增大而增大,但变化较小,流量120 L/h工况下一体化组件拥有最优的输出电功率值,对应的输出电功率值范围为24.02~29.19 W。     

A new estimation approach for determining the I-V characteristics of solar cells

A new application of pattern search optimization technique for estimating the parameters of solar cell and PV module is introduced in this article. The estimated parameters are the generated photocurrent, saturation current, series resistance, shunt resistance, and ideality factor. A new objective function formulation is introduced to guide the estimation technique toward the model parameters. The proposed approach is tested and validated using different test cases, e. g. solar cell and PV module, to show its potential. Outcomes of the developed approach are compared with those of different parameter estimation techniques to measure its accuracy. Comparison results are in favor of pattern search algorithm in all cases.     

A power-rating model for crystalline silicon PV modules

A model for the performance of generic crystalline silicon photovoltaic (PV) modules is proposed. The model represents the output power of the module as a function of module temperature and in-plane irradiance, with a number of coefficients to be determined by fitting to measured performance data from indoor or outdoor measurements. The model has been validated using data from 3 different modules characterized through extensive measurements in outdoor conditions over several seasons. The model was then applied to indoor measurement data for 18 different PV modules to investigate the variability in modeled output from different module types. It was found that for a Central European climate the modeled output of the 18 modules varies with a standard deviation (SD) of 1.22%, but that the between-module variation is higher at low irradiance (SD of 3.8%). The variability between modules of different types is thus smaller than the uncertainty normally found in the total solar irradiation per year for a given site. We conclude that the model can therefore be used for generalized estimates of PV performance with only a relatively small impact on the overall uncertainty of such estimates resulting from different module types.     

双面光伏组件辐照度模型的研究

针对双面光伏组件正面和背面获均能吸收太阳光的特点,通过光线跟踪辐照度模型分析,构建区分阴影区和无阴影区的热传输理论视觉因子太阳辐照度模型。模拟结果表明:当双面光伏组件倾斜角比单面组件增加约4°,在地面反射率为30%和50%的情况下,年辐照度增益可提高17.41%和28.79%;且随着离地高度与行间距增加,年辐照度可进一步提高。双面光伏组件辐照度模型为双面光伏组件电站安装时的地面反射率、最佳倾斜角、离地高度及行间距的设置提供了理论支撑。     

光伏阵列倾角对性能影响实验研究

对8块不同朝向和倾角的太阳电池组件输出情况进行了为期一年多的测试,并对实验结果进行了详细的分析和研究.得出:水平布置以及小倾角布置时,灰尘、雨水等因素对光伏阵列产能有较大影响;全年以朝向正南220倾角太阳电池组件产出的电能最多.     

Polar coordinated fuzzy controller based real-time maximum-power point control of photovoltaic system

It is crucial to improve the photovoltaic (PV) system efficiency and to develop the reliability of PV generation control systems. There are two ways to increase the efficiency of PV power generation system. The first is to develop materials offering high conversion efficiency at low cost. The second is to operate PV systems optimally. However, the PV system can be optimally operated only at a specific output voltage and its output power fluctuates under intermittent weather conditions. Moreover, it is very difficult to test the performance of a maximum-power point tracking (MPPT) controller under the same weather condition during the development process and also the field testing is costly and time consuming. This paper presents a novel real-time simulation technique of PV generation system by using dSPACE real-time interface system. The proposed system includes Artificial Neural Network (ANN) and fuzzy logic controller scheme using polar information. This type of fuzzy logic rules is implemented for the first time to operate the PV module at optimum operating point. ANN is utilized to determine the optimum operating voltage for monocrystalline silicon, thin-film cadmium telluride and triple junction amorphous silicon solar cells. The verification of availability and stability of the proposed system through the real-time simulator shows that the proposed system can respond accurately for different scenarios and different solar cell technologies.