A regime-dependent artificial neural network technique for short-range solar irradiance forecasting

Solar power can provide substantial power supply to the grid; however, it is also a highly variable energy source due to changes in weather conditions, i.e. clouds, that can cause rapid changes in solar power output. Independent systems operators (ISOs) and regional transmission organizations (RTOs) monitor the demand load and direct power generation from utilities, define operating limits and create contingency plans to balance the load with the available power generation resources. ISOs, RTOs, and utilities will require solar irradiance forecasts to effectively and efficiently balance the energy grid as the penetration of solar power increases. This study presents a cloud regime-dependent short-range solar irradiance forecasting system to provide 15-min average clearness index forecasts for 15-min, 60-min, 120-min and 180-min lead-times. A k-means algorithm identifies the cloud regime based on surface weather observations and irradiance observations. Then, Artificial Neural Networks (ANNs) are trained to predict the clearness index. This regime-dependent system makes a more accurate deterministic forecast than a global ANN or clearness index persistence and produces more accurate predictions of expected irradiance variability than assuming climatological average variability.     

Estimation of daily Linke turbidity factor by using global irradiance measurements at solar noon

This work presents a methodology for estimating daily Linke turbidity factor for clear sky days from global horizontal irradiance information at solar noon and monthly mean values of the Linke turbidity factor. The analysis of the method proposed here have been made using the ESRA clear sky model to recalculate the direct normal irradiance using as input the new Linke turbidities. Ground data of three BSRN and six AEMet radiometric meteorological stations have been used for assessing the method. Linke turbidity factor estimated here exhibits higher fluctuations than the monthly means and the comparison of the solar irradiance recalculated with the ground data have shown a noticeable reduction of the root mean square deviation. On the other hand the new Linke turbidity estimations have been compared to those values obtained from normal beam irradiance measures. The discrepancies found point out the high dependence of the reliability of this method with the quality of the ground measurements used.     

A simple approach to the synthetic generation of solar irradiance time series with high temporal resolution

Modeling the performance of some concentrating solar systems for thermal power plants may require high temporal resolution irradiance as input, in order to account for the impact of the cloud transient effects. This work proposes a simple method of generating synthetic irradiance of 10-min intervals from the hourly mean values. Boundary conditions are imposed to preserve the expected behavior under clear sky situations. The procedure consists basically on adding a random fluctuation, which characteristic amplitude depends on the sky conditions, to the hourly interpolated values. The assessment of the method with ground data have shown to main aspects to remark: daily and monthly means from the synthetic data are below 5% of root mean squared deviation compared to the original time series; despite the noticeable uncertainty in the 10-min synthetic irradiance values, the dynamic behavior of the fluctuations is comparable to the original data.     

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.     

Measurement of solar energy radiation in Abu Dhabi,UAE

This paper presents data on measurement of actual solar radiation in Abu Dhabi (24.43°N, 54.45°E). Global solar radiation and surface temperatures were measured and analyzed for one complete year. High resolution, real-time solar radiation and other meteorological data were collected and processed. Daily and monthly average solar radiation values were calculated from the one-minute average recorded values. The highest daily and monthly mean solar radiation values were 369 and 290 W/m², respectively. The highest one-minute average daily solar radiation was 1041 W/m². Yearly average daily energy input was 18.48 MJ/m²/day. Besides the global solar radiation, the daily and monthly average clearness indexes along with temperature variations are discussed. When possible, global solar energy radiation and some meteorological data are compared with corresponding data in other Arab state capitals. The data collected indicate that Abu Dhabi has a strong potential for solar energy capture.     

Global,diffuse and direct solar radiation at the surface in the city of Rio de Janeiro: Observational characterization and empirical modeling

The city of Rio de Janeiro and others 18 cities compose the Metropolitan Area of Rio de Janeiro. The main objective of this work is to characterize observationally the diurnal and seasonal evolution of the solar radiation components in the city of Rio de Janeiro. The measurements of global and diffuse solar radiation and standard meteorological variables at the surface have been carried out regularly at the Geoscience Institute of Federal University of Rio de Janeiro since October of 2011. The microclimatic conditions show that the period 2011–2014 was warmer during most of the year and drier in summer and spring in comparison with climate normal. All solar radiation components present a well defined diurnal cycle with maximum at noon. The estimates of global and direct solar radiation indicate a great potential available for solar energy at the surface, particularly in summer. The behavior of the clearness index and diffuse solar radiation fraction is similar in summer and winter. The Angstrom formula represents properly the estimate of the monthly average daily value of global solar radiation. The sigmoid logistic function is statistically more significant in comparison with others correlation models to represent the diffuse fraction as a function clearness index.     

Evaluation of conventional and high-performance routine solar radiation measurements for improved solar resource, climatological trends, and radiative modeling

The solar renewable energy community depends on radiometric measurements and instrumentation for data to design and monitor solar energy systems, and develop and validate solar radiation models. This contribution evaluates the impact of instrument uncertainties contributing to data inaccuracies and their effect on short-term and long-term measurement series, and on radiation model validation studies. For the latter part, transposition (horizontal-to-tilt) models are used as an example. Confirming previous studies, it is found that a widely used pyranometer strongly underestimates diffuse and global radiation, particularly in winter, unless appropriate corrective measures are taken. Other types of measurement problems are also discussed, such as those involved in the indirect determination of direct or diffuse irradiance, and in shadowband correction methods. The sensitivity of the predictions from transposition models to inaccuracies in input radiation data is demonstrated. Caution is therefore issued to the whole community regarding drawing detailed conclusions about solar radiation data without due attention to the data quality issues only recently identified.     

An analytical comparison of four approaches to modelling the daily variability of solar irradiance using meteorological records

Temporal solar variability significantly affects the integration of solar power systems into the grid. It is thus essential to predict temporal solar variability, particularly given the increasing popularity of solar power generation globally. In this paper, the daily variability of solar irradiance at four sites across Australia is quantified using observed time series of global horizontal irradiance for 2003–2012. It is shown that the daily variability strongly depends on sky clearness with generally low values under a clear or overcast condition and high values under an intermittent cloudiness condition. Various statistical techniques are adopted to model the daily variability using meteorological variables selected from the ERA-Interim reanalysis as predictors. The nonlinear regression technique (i.e. random forest) is demonstrated to perform the best while the performance of the simple analog method is only slightly worse. Among the four sites, Alice Springs has the lowest daily variability index on average and Rockhampton has the highest daily variability index on average. The modelling results of the four sites produced by random forest have a correlation coefficient of above 0.7 and a median relative error around 40%. While the approach of statistical downscaling from a large spatial domain has been applied for other problems, it is shown in this study that it generally suffices to use only the predictors at a single near point for the problem of solar variability. The relative importance of the involved meteorological variables and the effects of clearness on the modelling of the daily variability are also explored.     

Prediction of global daily solar radiation using higher order statistics

The main concern of the present paper is to present and to analyse two procedures for modelling daily global solar radiation. The first one uses the clearness index techniques and the second one uses a totally different type of approach for taking in consideration important properties of such data, including non-Gaussian shape and non-stationarity. This procedure uses the difference between the extraterrestrial and the observed daily global radiation denoted “lost solar component”. Both procedures are based on higher order statistics for generating the global solar radiation using mainly a random process. The prediction results show that the sequences of values generated have the same statistical characteristics as those of sequences observed. The comparison between the two methods used indicates that the developed model based on the “lost solar component” is better than the model obtained using the conventional procedure based on the clearness index.     

One-minute global irradiance probability density distributions conditioned to the optical air mass

Knowledge of the temporal variability of the solar irradiance is important to study solar energy systems involving thermal and photovoltaic processes. The differences between hourly and instantaneous values of the clearness index considerably affect the utilizability of photovoltaic systems. In this work, we analyzed the probability density distributions of one-minute values of global irradiance, conditioned to the optical air mass, considering those as an approximation to the instantaneous distributions. The study reveals that the bimodality that characterizes these distributions increases with optical air mass. We propose the use of a functional form based on Boltzmann's statistics in order to describe these distributions. This function can be used for the generation of synthetic radiation data. Expressing the distribution as a sum of two functions provides an appropriate modeling of the bimodality feature that can be associated with the existence of two levels of irradiation corresponding to two extreme atmospheric situations, cloudless and cloudy conditions.     

Demand side management for remote area power supply systems incorporating solar irradiance model

This paper presents a technique for generating the daily electricity load profile for remote areas in the Middle East from first principles, using diversified demand. The generated load profile includes the energy required to run a small desalination unit to provide the necessary freshwater. Demand side management (DSM) is used in this study to smooth out the daily peaks and fill valleys in the load curve to make the most efficient use of energy resources. Finally, the load profile is compared with real data for six houses collected from Safri area in the Sultanate of Oman. These data may be used as the basis to obtain load profiles of other remote areas of the Middle East since the weather and social factors are similar. The modified hourly variation factor based on weather and economic and social factors of the Middle East is obtained.A solar irradiance model is incorporated in the system to utilise the solar energy available in the Middle East region.     

Modeling solar still production using local weather data and artificial neural networks

A study has been performed to predict solar still distillate production from single examples of two different commercial solar stills that were operated for a year and a half. The purpose of this study was to determine the effectiveness of modeling solar still distillate production using artificial neural networks (ANNs) and local weather data. The study used the principal weather variables affecting solar still performance, which are the daily total insolation, daily average wind velocity, daily average cloud cover, daily average wind direction and daily average ambient temperature. The objectives of the study were to assess the sensitivity of the ANN predictions to different combinations of input parameters as well as to determine the minimum amount of inputs necessary to accurately model solar still performance. It was found that 31-78% of ANN model predictions were within 10% of the actual yield depending on the input variables that were selected. By using the coefficient of determination, it was found that 93-97% of the variance was accounted for by the ANN model. About one half to two thirds of the available long term input data were needed to have at least 60% of the model predictions fall within 10% of the actual yield. Satisfactory results for two different solar stills suggest that, with sufficient input data, the ANN method could be extended to predict the performance of other solar still designs in different climate regimes.     

A simple and efficient procedure for increasing the temporal resolution of global horizontal solar irradiance series

The intermittent nature of instantaneous solar radiation has a considerable impact on the nonlinear behavior of solar energy conversion systems. The time resolution of the Numerical Weather Prediction Models (NWPM) or satellite derived solar irradiance data are typically limited to 1-h (at best 15-min). Unfortunately, this resolution is not sufficient in the design and performance of many solar systems. In this study, a new methodology has been developed to increase the temporal resolution of GHI series from 1-h to 1-min. This methodology uses the clearness index k_t (the ratio of GHI to top-of-atmosphere irradiance on the same plane) to characterize the GHI high-frequency dynamics from a 1-year measurement campaign at a given site. The evaluation of the method with 2 years of measured data in different climatic zones has resulted in KSI(%) (Kolmogorov–Smirnov test Integral parameter) and normalized root mean square deviation values below 8.0% and 1.7% respectively for each month, with negligible bias. Indicators of overall performance show an excellent agreement between measured and modeled 1-min GHI data for each month: average values for Nash-Sutcliffe efficiency, Willmott index of agreement and Legates coefficient of efficiency are found to be 0.94, 0.99 and 1.00, respectively.     

Fluctuations in instantaneous clearness index: Analysis and statistics

Solar radiation is characterized by short fluctuations introduced by passing clouds. An analysis of these fluctuations with regard to solar energy applications should focus on the instantaneous clearness index. Its probability distribution for a given mean clearness index is, as a first approximation, independent from the season and partly also from the site. This is verified for four annual datasets from three different sites.An analysis of fluctuations in solar radiation must focus on their amplitude, persistence, and frequency of occurrence rather than their location in time. The Fourier analysis cannot satisfactorily provide this information since time series of the instantaneous clearness index exhibit no periodicity. Instead, a localized spectral analysis based on wavelet bases rather than on periodic-ones has been applied. This analysis allows the decomposition of the fluctuating clearness index signal into a set of orthonormal subsignals. Each of them represents one specific scale of persistence of the fluctuation.The annual mean square values of all subsignals have been analysed, permitting the allocation of the signal’s power content to the different scales of persistence of a fluctuation. These annual mean values agree well for the different datasets, indicating the existence of statistically significant mean square values of the fluctuations as a function of their persistence.The analysis offers a valuable tool for the estimation of power flow fluctuations introduced by direct solar energy systems. With further elaboration it may be applied by power system operators for network planning in distribution grids with a high density of embedded generation.     

A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste, Italy

Forecasting of solar irradiance is in general significant for planning the operations of power plants which convert renewable energies into electricity. In particular, the possibility to predict the solar irradiance (up to 24 h or even more) can became - with reference to the Grid Connected Photovoltaic Plants (GCPV) - fundamental in making power dispatching plans and - with reference to stand alone and hybrid systems - also a useful reference for improving the control algorithms of charge controllers. In this paper, a practical method for solar irradiance forecast using artificial neural network (ANN) is presented. The proposed Multilayer Perceptron MLP-model makes it possible to forecast the solar irradiance on a base of 24 h using the present values of the mean daily solar irradiance and air temperature. An experimental database of solar irradiance and air temperature data (from July 1st 2008 to May 23rd 2009 and from November 23rd 2009 to January 24th 2010) has been used. The database has been collected in Trieste (latitude 45°40′N, longitude 13°46′E), Italy. In order to check the generalization capability of the MLP-forecaster, a K-fold cross-validation was carried out. The results indicate that the proposed model performs well, while the correlation coefficient is in the range 98-99% for sunny days and 94-96% for cloudy days. As an application, the comparison between the forecasted one and the energy produced by the GCPV plant installed on the rooftop of the municipality of Trieste shows the goodness of the proposed model.     

Study of hourly and daily solar irradiation forecast using diagonal recurrent wavelet neural networks

An accurate forecast of solar irradiation is required for various solar energy applications and environmental impact analyses in recent years. Comparatively, various irradiation forecast models based on artificial neural networks (ANN) perform much better in accuracy than many conventional prediction models. However, the forecast precision of most existing ANN based forecast models has not been satisfactory to researchers and engineers so far, and the generalization capability of these networks needs further improving. Combining the prominent dynamic properties of a recurrent neural network (RNN) with the enhanced ability of a wavelet neural network (WNN) in mapping nonlinear functions, a diagonal recurrent wavelet neural network (DRWNN) is newly established in this paper to perform fine forecasting of hourly and daily global solar irradiance. Some additional steps, e.g. applying historical information of cloud cover to sample data sets and the cloud cover from the weather forecast to network input, are adopted to help enhance the forecast precision. Besides, a specially scheduled two phase training algorithm is adopted. As examples, both hourly and daily irradiance forecasts are completed using sample data sets in Shanghai and Macau, and comparisons between irradiation models show that the DRWNN models are definitely more accurate.     

Fuzzy model representation of thermosyphon solar water heating system

The aim of this paper is to focus on improvement in prediction accuracy of model for thermosyphon solar water heating (SWH) system. The work employs grey-box modeling approach based on fuzzy system to predict the outlet water temperature of the said system. The prediction performance results are compared with neural network technique, which has been suggested by various researchers in the last one decade. The outlet water temperature prediction by fuzzy modeling technique is analyzed by using 3 models, one with three inputs (inlet water temperature, ambient temperature, solar irradiance), next with two inputs (inlet water temperature, solar irradiance) and last one with single input (solar irradiance/inlet water temperature). An improved prediction performance is observed with three inputs fuzzy model.     

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

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.     

Benefits of solar forecasting for energy imbalance markets

Short term electricity trading to balance generation and demand provides an economic opportunity to integrate larger shares of variable renewable energy sources in the power grid. Recently, many regulatory market environments are reorganized to allow short term electricity trading. This study seeks to quantify the benefits of solar forecasting for energy imbalance markets (EIM). State-of-the-art solar forecasts, covering forecast horizons ranging from 24 h to 5 min are proposed and compared against the currently used benchmark models, persistence (P) and smart persistence (SP). The implemented reforecast of numerical weather prediction time series achieves a skill of 14.5% over the smart persistence model. Using the proposed forecasts for a forecast horizon of up to 75 min for a single 1 MW power plant reduces required flexibility reserves by 21% and 16.14%, depending on the allowed trading intervals (5 and 15 min). The probability of an imbalance, caused through wrong market bids from PV solar plants, can be reduced by 19.65% and 15.12% (for 5 and 15 min trading intervals). All EIM stakeholders benefit from accurate forecasting. Previous estimates on the benefits of EIMs, based on persistence model are conservative. It is shown that the design variables regulating the market time lines, the bidding and the binding schedules, drive the benefits of forecasting.     

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.