Use of neural networks for the creation of hourly global and diffuse solar irradiance data at representative locations in Greece

In this work, a new approach is tested by applying neural networks treatment to meteorological time-series data sets, recorded during 1991–2000 at certain Greek locations, in order to create fully appropriate solar data information. Neural networks, in this case, are used for creating missing mean, maximum and minimum global and diffuse solar irradiance hourly data, when educated with other known meteorological time-series hourly values. For this purpose, hourly data of air temperature, relative humidity, sunshine duration, clouds’ octals, as well as local latitude are used with regard to these sites. Neural networks’ education process outputs are checked against known hourly values of solar irradiance, based upon the mentioned meteorological hourly raw data necessary for this action recorded at the National Observatory of Athens, the actinometric station at the Technological Education Institute (TEI) of Piraeus, and six other locations. Selection of these sites is representative of the climatic conditions in Greece, from north to south and east to west. Following the same scheme, the produced hourly global and diffuse mean hourly solar irradiance values are in a very good agreement (p<0.01) with actual measurements.     

基于GA-BP神经网络的逐时总辐射分组模型研究

通过分析影响太阳辐射的主要因素,提出以太阳高度角、季节和天气（晴空指数）作为数据划分依据的分组模型建立方法。以拉萨和西安地区的逐时气象数据和辐射数据为例,基于遗传算法（genetic algorithm,GA）优化的BP神经网络,建立太阳高度角、季节和天气类型的逐时总辐射分组模型。该研究揭示分组模型误差变化的规律,并将其估算误差与AllData模型比较。结果显示,相较于AllData模型,分组模型的估算误差均有降低。其中,天气分组模型误差最小,且西安的天气分组模型结果优于拉萨。西安天气分组模型平均绝对百分比误差（MAPE）和相对均方根误差（rRMSE）相较AllData模型结果分别下降3.96%和4.18%。研究结果表明分组模型能够降低逐时总辐射估算误差,可为估算逐时总辐射提供方法借鉴。     

Modelling of solar energy potential in Nigeria using an artificial neural network model

In this study, an artificial neural network (ANN) based model for prediction of solar energy potential in Nigeria (lat. 4–14°N, log. 2–15°E) was developed. Standard multilayered, feed-forward, back-propagation neural networks with different architecture were designed using neural toolbox for MATLAB. Geographical and meteorological data of 195 cities in Nigeria for period of 10 years (1983–1993) from the NASA geo-satellite database were used for the training and testing the network. Meteorological and geographical data (latitude, longitude, altitude, month, mean sunshine duration, mean temperature, and relative humidity) were used as inputs to the network, while the solar radiation intensity was used as the output of the network. The results show that the correlation coefficients between the ANN predictions and actual mean monthly global solar radiation intensities for training and testing datasets were higher than 90%, thus suggesting a high reliability of the model for evaluation of solar radiation in locations where solar radiation data are not available. The predicted solar radiation values from the model were given in form of monthly maps. The monthly mean solar radiation potential in northern and southern regions ranged from 7.01–5.62 to 5.43–3.54 kW h/m² day, respectively. A graphical user interface (GUI) was developed for the application of the model. The model can be used easily for estimation of solar radiation for preliminary design of solar applications.     

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.     

Global solar radiation in Northeastern Saudi Arabia

This paper presents the actual global solar radiation on a horizontal surface along with the prevailing meteorological conditions encountered during the measurement period from 1 January–31 December, for one complete year, in the Arabian Gulf Coast near the city of Dhahran. High resolution, real time solar radiation and meteorological data were collected, and processed. Hourly, daily, and monthly statistics of solar radiation was made from the one-minute averaged recorded values. The highest measured daily, and monthly mean solar radiation were found to be 351 and 328 W/m⁻², respectively. The highest one-minute averaged solar radiation values up to 1183 W/m⁻² were observed in the summer season, from May–September. The highest hourly solar radiation value was recorded as 1053 W/m⁻² in the middle of June. Beside the global solar radiation measurements, the main observed meteorological parameters were temperature, pressure, wind speed, precipitation, and relative humidity. On the other hand, the estimation of daily and monthly mean global solar radiation was performed based upon two empirical formulas which relate the solar radiation to the sunshine duration, relative humidity, maximum temperature, the latitude of the monitoring location, sunset hour and declination angles. The agreement between the measured and estimated solar radiation values was found to be satisfactory. Nevertheless, the empirical formula under-estimates the solar radiation values during summer, and over-estimates during winter.     

Generation of synthetic daily global solar radiation data based on ERA-Interim reanalysis and artificial neural networks

Four variables (total cloud cover, skin temperature, total column water vapour and total column ozone) from meteorological reanalysis were used to generate synthetic daily global solar radiation via artificial neural network (ANN) techniques. The goal of our study was to predict solar radiation values in locations without ground measurements, by using the reanalysis data as an alternative to the use of satellite imagery. The model was validated in Andalusia (Spain), using measured data for nine years from 83 ground stations spread over the region. The geographical location (latitude, longitude), the day of the year, the daily clear sky global radiation, and the four meteorological variables were used as input data, while the daily global solar radiation was the only output of the ANN. Sixty five ground stations were used as training dataset and eighteen stations as independent dataset. The optimum network architecture yielded a root mean square error of 16.4% and a correlation coefficient of 94% for the testing stations. Furthermore, we have successfully tested the forecasting capability of the model with measured radiation values at a later time. These results demonstrate the generalization capability of this approach over unseen data and its ability to produce accurate estimates and forecasts.     

Test reference year generation from meteorological and simulated solar radiation data

In this paper, a new method for generating test reference year (TRY) from the measured meteorological variables is proposed. Hourly recorded data of air temperature, relative humidity and wind velocity for two stations, Valladolid and Madrid (Spain) were selected to develop the method and a TRY was obtained. Monthly average solar radiation values were calculated taking into account the temperature and solar radiation correlations. Four different methodologies were used to evaluate hourly global solar radiation from hourly weather data of temperature and, as a consequence, four different TRYs with common data sets of temperature, relative humidity and wind velocity were generated for Valladolid and Madrid (Spain) stations. In order to evaluate the four different methodologies, TRYs data were compared with long-term measured data series using statistical estimators such as average, standard deviation, root mean square error (rmse) and mean bias error (mbe). Festa and Ratto and the TAG model, from Aguiar and Collares-Pereira, respectively, turned out to be the best methods for generating hourly solar irradiation data. The best performance was shown by the TRY0 year which was based on the solar radiation models mentioned above. The results show that the best reference year for each site varies with the season and the characteristics of the station.     

RECONSTRUCTION OF SYNTHETIC METEOROLOGICAL SEQUENCES BY USING MARKOV TRANSITION MATRIX FOR SOLAR THERMAL SIMULATION

A Markov Transition Matrix (MTM) approach used to reconstruct the synthetic sequences of both hourly global radiation and hourly ambient temperature, which has a strong effect on the output of solar thermal systems and has not been taken into account. The result shows that the main statistical features of natural sequences, i.e., probability density function, sequential characteristics and the variance of the fluctuations, can be simulated by Markov transition-matrix obtained from recorded meteorological data. Its quality depends upon data record number in order that the synthetic sequences match long-term statistic characters of natural sequences. Comparisons have been made among different record number and the minimum number of records is sought. It is shown that the minimum data to generate hourly MTM is 12,410 data number for global radiation and 43,800 data for ambient temperature.     

Estimation of hourly solar radiation for India

The ASHRAE constants predict high values of the hourly beam radiation and very low values of the hourly diffuse radiation when used to predict radiation at Indian locations. Hence a procedure has been developed for the estimation of direct, diffuse and global hourly solar radiation on a horizontal surface for any location in India. To calculate hourly solar radiation, an exponential curve, similar to the one used by ASHRAE, was fitted to the measured solar radiation data of six cities from different regions of India. The statistical analysis was carried out for the data computed using ASHRAE constants and the set of constants obtained for India using the measured data of four different Indian cities selected randomly. Three statistical indicators were used to compare the accuracy of the developed procedure. The results show that ASHRAE constants are not suitable to estimate hourly solar radiation in India. Hourly solar radiation estimated by constants obtained for India are fairly comparable with measured data. The mean percentage error with Indian constants for these four Indian cities was found as low as 2.27, −6.29 and −6.09% for hourly beam, diffuse and global radiation, respectively.     

Estimation of solar radiation over Cambodia from long-term satellite data

In this work, monthly average daily global solar irradiation over Cambodia was estimated from a long-term satellite data. A 14-year period (1995–2008) of visible channel data from GMS5, GOES9 and MTSAT-1R satellites were used to provide earth-atmospheric reflectivity. A satellite-based solar radiation model developed for a tropical environment was used to estimate surface solar radiation. The model relates the satellite-derived earth-atmospheric reflectivity to absorption and scattering coefficients of various atmospheric constituents. The absorption of solar radiation due to water vapour was calculated from precipitable water derived from ambient relative humidity and temperature. Ozone data from the TOMS and OMI satellite data were employed to compute the solar radiation absorption by ozone. The depletion of radiation due to aerosols was estimated from the visibility data. Five new solar radiation measuring stations were established at Cambodian cities, namely Siem Reap (13.87°N, 103.85°E), Kompong Thom (12.68°N, 104.88°E), Phnom Penh (11.55°N, 104.83°E), Sihanouke Ville (10.67°N, 103.63°E) and Kampot (10.70°N, 104.28°E). Global solar radiation measured at these stations was used to validate the model. The validation was also carried out by using solar radiation measured at four Thai meteorological stations. These stations are situated near the Cambodian border. Monthly average daily global irradiation from these stations was compared with that calculated from the model. The measured and calculated irradiation is in good agreement, with the root mean square difference of 6.3%, with respect to the mean values. After the validation, the model was used to calculate monthly average daily global solar irradiation over Cambodia. Based on this satellite-derived irradiation, solar radiation maps for Cambodia were generated. These maps show that solar radiation climate of this country is strongly influenced by the monsoons. A solar radiation database was also generated for solar energy applications in Cambodia.     

Distribution and temporal variability of the solar resource at a site in south-east Norway

Globally, solar energy is expected to play a significant role in the changing face of energy economies in the near future. However, the variability of this resource has been the main barrier for solar energy development in most locations around the world. This paper investigated the distribution and variability of solar radiation using the a 10-year (2006 to 2015) data collected at Sørås meteorological station located at latitude 59° 39′ N and longitude 10° 47′E, about 93.3 m above sea level (about 30 km from Oslo), in south-eastern part of Norway. It is found that on annual basis, the total number of days with a global solar radiation of less than 1 kWh/(m²·d) is 120 days while the total number of days with an expected global solar radiation greater than 3 kWh/(m²·d) is 156 days (42.74%) per year. The potential energy output from a horizontally placed solar collector in these 156 days is approximately 75% of the estimated annual energy output. In addition, it is found that the inter-annual coefficient of variation of the global solar radiation is 4.28%, while that of diffuse radiation is 4.96%.     

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.     

Calculation of solar radiation using a methodology with worldwide potential

Surface meteorological observations from the DATSAV2 database provide the capability to use the METSTAT (meteorological/statistical) model to calculate hourly values of direct normal, diffuse horizontal, and global horizontal solar radiation for locations throughout the world. Opaque cloud cover, a key input parameter to the METSTAT model, is derived from the DATSAV2 layered cloud cover information. Resulting multiyear data sets include solar radiation and other meteorological data such as dry bulb temperature, dew point temperature, wind speed, and atmospheric pressure. Data filling procedures ensure that the multiyear data sets are serially complete. A minor revision to METSTAT improved solar radiation estimates for conditions of high cloud amounts and low ceiling heights. The methodology was applied to regions of Southern Africa and Saudi Arabia.     

Monthly mean hourly global solar radiation estimation

In this paper, selected empirical models were used to estimate the monthly mean hourly global solar radiation from the daily global radiation at three sites in the east coast of Malaysia. The purpose is to determine the most accurate model to be used for estimating the monthly mean hourly global solar radiation in these sites. The hourly global solar radiation data used for the validation of selected models were obtained from the Malaysian Meteorology Department and University Malaysia Terengganu Renewable Energy Station. In order to indicate the performance of the models, the statistical test methods of the normalized mean bias error, normalized root mean square error, correlation coefficient and t-statistical test were used. The monthly mean hourly global solar radiation values were calculated by using six models and the results were compared with corresponding measured data. All the models fit the data adequately and can be used to estimate the monthly mean hourly global solar radiation. This study finds that the Collares-Pereira and Rabl model performed better than the other models. Therefore the Collares-Pereira and Rabl model is recommended to estimate the monthly mean hourly global radiations for the east coast of Malaysia with humid tropical climate and in elsewhere with similar climatic conditions.     

太阳逐时总辐射混沌优化神经网络预测模型研究

根据影响太阳逐时总辐射的气象、地理等方面因素的分析以及对太阳逐时总辐射历史数据的相关性分析,确定了建立太阳逐时总辐射的神经网络预测模型输入因素项。根据全年最大可照时数统一了太阳逐时总辐射各天的历史数据,并对宝山气象站的太阳逐时总辐射建立了混沌优化神经网络预测模型(CONN),编制了计算机程序。模型输出反映了太阳逐时总辐射的变化规律,预测结果也足够准确。     

Techniques for the precise estimation of hourly values of global, diffuse and direct solar radiation

The method usually used to compute solar radiation, when no measured data are available, is the well-known regression technique relating mean daily totals of global and diffuse solar radiation with the mean duration of sunshine. Using this method and taking into account the first order multiple reflections between the ground and the atmosphere, regression parameters were obtained from the monthly mean values of daily totals of global solar radiation and sunshine at a network of 16 stations in India. Daily values of global and diffuse solar radiation were then computed for 121 stations, where sunshine data are available for periods of 6–28 yr, using interpolated values of the regression parameters. Where no sunshine data were available, global and diffuse solar radiation were computed from cloud observations, using the inverse relationship between sunshine and cloudiness. Further, using the empirical relationship between daily totals and the corresponding hourly values of global and diffuse solar radiation, two sets of curves were prepared valid for the whole country, using which mean hourly values of global and diffuse radiation could be deduced from the corresponding daily totals, with a high degree of accuracy. The paper discusses the validity of the techniques used for computing daily and hourly values of global and diffuse solar radiation from sunshine and cloud amounts at an extended network of 145 stations in India and stresses the fact that such techniques are successful, only if accurate data on both radiation and sunshine are available at a widely distributed network of stations for a minimum period from at least 5 to 6 yr, using carefully calibrated and well-maintained instruments of the required quality. Theoretical models have also been used to compute clear sky noon values of global, diffuse and direct solar radiation from the solar constant, allowing for attenuation by atmospheric constituents such as ozone, water vapour, dust and aerosols. Using a simple model, calculations of global and diffuse solar radiation on clear days were made for 145 stations from values of the solar constant and measured values of ozone, water vapour and atmospheric turbidity. A method of extending the technique to overcast skies and partly clouded skies is discussed. The values of the mean annual transmission factor for global solar radiation under cloud-free conditions using the two methods show excellent agreement and establishes the soundness of the regression technique on one hand and the reliability of the theoretical model used for computing clear sky radiation, on the other.     

An application of the multilayer perceptron: Solar radiation maps in Spain

In this work an application of a methodology to obtain solar radiation maps is presented. This methodology is based on a neural network system [Lippmann, R.P., 1987. An introduction to computing with neural nets. IEEE ASSP Magazine, 4–22] called Multi-Layer Perceptron (MLP) [Haykin, S., 1994. Neural Networks. A Comprehensive Foundation. Macmillan Publishing Company; Hornik, K., Stinchcombe, M., White, H., 1989. Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359–366]. To obtain a solar radiation map it is necessary to know the solar radiation of many points spread wide across the zone of the map where it is going to be drawn. For most of the locations all over the world the records of these data (solar radiation in whatever scale, daily or hourly values) are non-existent. Only very few locations have the privilege of having good meteorological stations where records of solar radiation have being registered. But even in those locations with historical records of solar data, the quality of these solar series is not as good as it should be for most purposes. In addition, to draw solar radiation maps the number of points on the maps (real sites) that it is necessary to work with makes this problem difficult to solve. Nevertheless, with the application of the methodology proposed in this paper, this problem has been solved and solar radiation maps have been obtained for a small region of Spain: Jaén province, a southern province of Spain between parallels 38°25′ N and 37°25′ N, and meridians 4°10′ W and 2°10′ W, and for a larger region: Andalucía, the most southern region of Spain situated between parallels 38°40′ N and 36°00′ N, and meridians 7°30′ W and 1°40′ W.     

Application of neural networks for the prediction of hourly mean surface temperatures in Saudi Arabia

This paper utilizes artificial neural networks for the prediction of hourly mean values of ambient temperature 24 h in advance. Full year hourly values of ambient temperature are used to train a neural network model for a coastal location — Jeddah, Saudi Arabia. This neural network is trained off-line using back propagation and a batch learning scheme. The trained neural network is successfully tested on temperatures for years other than the one used for training. It requires only one temperature value as input to predict the temperature for the following day for the same hour. The predicted hourly temperature values are compared with the corresponding measured values. The mean percent deviation between the predicted and measured values is found to be 3.16, 4.17 and 2.83 for three different years. These results testify that the neural network can be a valuable tool for hourly temperature prediction in particular and other meteorological predictions in general.     

Use of artificial neural networks for mapping of solar potential in Turkey

Turkey has sufficient solar radiation intensities and radiation durations for solar thermal applications since Turkey lies in a sunny belt, between 36° and 42° N latitudes. The yearly average solar-radiation is 3.6 kWh/m²day, and the total yearly radiation period is ∼2610 h. The main focus of this study is to determine the solar-energy potential in Turkey using artificial neural-networks (ANNs). Scaled conjugate gradient (SCG), Pola-Ribiere conjugate gradient (CGP), and Levenberg-Marquardt (LM) learning algorithms and a logistic sigmoid transfer function were used in the network. In order to train the neural network, meteorological data for the last 3 years (2000–2002) from 17 stations (namely cities) spread over Turkey were used as training (11 stations) and testing (6 stations) data. Meteorological and geographical data (latitude, longitude, altitude, month, mean sunshine duration, and mean temperature) are used as inputs to the network. Solar radiation is in the output layer. The maximum mean absolute percentage error was found to be less than 6.7% and R² values to be about 99.8937% for the testing stations. However, the respective values were found to be 2.41 and 99.99658% for the training stations. The trained and tested ANN models show greater accuracies for evaluating solar resource posibilities in regions where a network of monitoring stations has not been established in Turkey. The predicted solar-potential values from the ANN were given in the form of monthly maps. These maps are of prime importance for different working disciplines, like those of scientists, architects, meteorologists, and solar engineers in Turkey. The predictions from ANN models could enable scientists to locate and design solar-energy systems in Turkey and determine the appropriate solar technology.     

Analysis of solar radiation measurements at Al-Arish area, North Sinai, Egypt

This paper presents basic data for a five year period from 1986 to 1990 for global and diffuse solar radiation data at Al-Arish (31°04′N, 33°49′E). These data have been processed, analysed, presented, arranged in tables and graphs and discussed. Mean annual monthly and daily total, the diurnal variation and the frequency of daily totals of global solar radiation are computed and discussed. A correlation between the hourly values of the clearness and diffuse index were obtained and the recommended correlation equations were also given. The isopleths of hourly global radiation were also designed and discussed. The frequency distribution and the frequency of extended periods of low radiation income have been studied which are of particular interest in the field performance of solar energy systems.