Neural Network for Estimating Daily Global Solar Radiation Using Temperature, Humidity and Pressure as Unique Climatic Input Variables

Solar radiation is one of the most important parameters for applications, development and research related to renewable energy. However, solar radiation measurements are not a simple task for several reasons. In the cases where data are not available, it is very common the use of computational models to estimate the missing data, which are based mainly on the search for relationships between weather variables, such as temperature, humidity, precipitation, cloudiness, sunshine hours, etc. But, many of these are subjective and difficult to measure, and thus they are not always available. In this paper, we propose a method for estimating daily global solar radiation, combining empirical models and artificial neural networks. The model uses temperature, relative humidity and atmospheric pressure as the only climatic input variables. Also, this method is compared with linear regression to verify that the data have nonlinear components. The models are adjusted and validated using data from five meteorological stations in the province of Tucumán, Argentina. Results show that neural networks have better accuracy than empirical models and linear regression, obtaining on average, an error of 2.83 [MJ/m2] in the validation dataset.

Spatial and temporal patterns of solar radiation in China from 1957 to 2016

Solar energy is clean and renewable energy that plays an important role in mitigating impacts of environmental problems and climate change.Solar radiation received on the earth's surface determines the efficiency of power generation and the location and layout of photovoltaic arrays.In this paper,the average daily solar radiation of 77 stations in China from 1957 to 2016 was analyzed in terms of spatial and temporal characteristics.The results indicate that Xinjiang,the Qinghai-Tibet Plateau,North,Central and East China show a decreasing trend with an average of 2.54×10^(−3)MJ/(m^(2)⋅10a),while Northwest and Northeast China are basically stabilized,and Southwest China shows a clear increasing trend with an average increase of 1.79×10^(−3)MJ/(m^(2)⋅10a).The average daily solar radiation in summer and winter in China from 1957 to 2016 was 18.74 MJ/m^(2)and 9.09 MJ/m^(2),respectively.Except for spring in Northwest,East and South China,and summer in northeast China,the average daily solar radiation in all other regions show a downward trend.A critical point for the change is 1983 in the average daily solar radiation.Meanwhile,large-scale(25−30 years)oscillation changes are more obvious,while small-scale(5−10 years)changes are stable and have a global scope.The average daily solar radiation shows an increasing-decreasing gradient from west to east,which can be divided into three areas west of 80°E,80°E−100°E and east of 100°E.The average daily solar radiation was 2.07 MJ/m^(2)in the 1980s,and that in 1990s lower than that in the 1960s and the 1970s.The average daily solar radiation has rebounded in the 21st century,but overall it is still lower than the average daily solar radiation from 1957 to 2016(13.87 MJ/m^(2)).

Development of a 50-year daily surface solar radiation dataset over China

Although solar radiation is a crucial parameter in designing solar power devices and studying land surface processes,long-term and densely distributed observations of surface solar radiation are usually not available.This paper describes the development of a 50-year dataset of daily surface solar radiation at 716 China Meteorological Administration(CMA) stations.First,a physical model,without any local calibration,is applied to estimate the daily radiation at all 716 CMA routine stations.Then,an ANN-based(Artificial Neural Network) model is applied to extend radiation estimates to earlier periods at each of all 96 CMA radiation stations.The ANN-based model is trained with recent reliable radiation data and thus its estimate is more reliable than the physical model.Therefore,the ANN-based model is used to correct the physical model dynamically at a monthly scale.The correction generally improves the accuracy of the radiation dataset estimated by the physical model:the mean bias error(MBE) averaged over all the 96 radiation stations during 1994-2002 is reduced from 0.68 to 0.11 MJ m-2 and the root mean square error(RMSE) from 2.01 to 1.80 MJ m-2.The new radiation dataset shows superior performance over previous estimates by locally calibrated ngstr m-Prescott models.Based on the new radiation dataset,the annual mean daily solar radiation over China is 14.3 MJ m-2.The maximal seasonal mean daily solar radiation occurs in the Tibetan Plateau during summer with a value of 27.1 MJ m-2,whereas the minimal seasonal mean daily solar radiation occurs in the Sichuan Basin during winter with a value of 4.7 MJ m-2.