The Influence of Air Pollution Concentrations on Solar Irradiance Forecasting Using CNN-LSTM-mRMR Feature Extraction

Maintaining a steady power supply requires accurate forecasting of solar irradiance,since clean energy resources do not provide steady power.The existing forecasting studies have examined the limited effects of weather conditions on solar radiation such as temperature and precipitation utilizing convolutional neural network(CNN),but no comprehensive study has been conducted on concentrations of air pollutants along with weather conditions.This paper proposes a hybrid approach based on deep learning,expanding the feature set by adding new air pollution concentrations,and ranking these features to select and reduce their size to improve efficiency.In order to improve the accuracy of feature selection,a maximum-dependency and minimum-redundancy(mRMR)criterion is applied to the constructed feature space to identify and rank the features.The combination of air pollution data with weather conditions data has enabled the prediction of solar irradiance with a higher accuracy.An evaluation of the proposed approach is conducted in Istanbul over 12 months for 43791 discrete times,with the main purpose of analyzing air data,including particular matter(PM10 and PM25),carbon monoxide(CO),nitric oxide(NOX),nitrogen dioxide(NO_(2)),ozone(O₃),sulfur dioxide(SO_(2))using a CNN,a long short-term memory network(LSTM),and MRMR feature extraction.Compared with the benchmark models with root mean square error(RMSE)results of 76.2,60.3,41.3,32.4,there is a significant improvement with the RMSE result of 5.536.This hybrid model presented here offers high prediction accuracy,a wider feature set,and a novel approach based on air concentrations combined with weather conditions for solar irradiance prediction.

Spatial and Temporal Variability of Solar Irradiance in Botswana

This study evaluated the potential of Botswana’s sustainable energy production using ERA5 reanalysis data of solar irradiance variability on an optimally inclined plane from 1971 to 2020. Spatial-temporal solar irradiance fluctuations were the focus of the study, and the relation to cloud cover and aerosol optical depth was investigated. The key findings suggest that the summer/rainfall season (November to March) is the peak season with average monthly solar irradiance of 313 - 445 W/m2 across southern, central, and northern parts of Botswana, the Kalahari Desert and the Makgadikgadi Pans being identified as prime sites for solar energy projects. The long-term trend analysis showed a decrease in solar irradiance in December but a consistent increase from August to October, indicating a potential shift in solar resources toward an earlier season. Contrary to other studies that found that aerosol optical depth dominates effects on long-term trends and year-to-year variability of solar irradiance, for this case, cloud cover, particularly mid-level clouds, is found to have a more dominant role in Botswana. Solar irradiance characteristics of three distinct regions were identified through K-means clustering. Moreover, Ensemble Empirical Mode Decomposition (EEMD) analysis showed the commonality and time scale linkage between solar irradiance and cloud cover between the identified regions. These results highlight the importance of including cloud-related weather patterns under the global warming scenario in solar energy planning and emphasize the secondary role of aerosols in Botswana, thus providing critical information for the region’s solar energy development and policy formulation.

Impact Analysis of Solar Irradiance Change on Precision Orbit Determination of Navigation Satellites

Solar radiation pressure is the main driving force and error source for precision orbit determination of navigation satellites.It is proportional to the solar irradiance,which is the"sun constant".In regular calculation,the"solar constant"is regard as a constant.However,due to the existence of sunspots,flares,etc.,the solar constant is not fixed,the change in the year is about 1%.To investigate the variation of solar irradiance,we use interpolation and average segment modeling of total solar irradiance data of SORCE,establishing variance solar radiation pressure(VARSRP)model and average solar radiation pressure(AVESRP)model based on the built solar pressure model(SRPM)(constant model).According to observation data of global positioning system(GPS)and Beidou system(BDS)in 2015 and comparing the solar pressure acceleration of VARSRP,AVESRP and SRPM,the magnitude of change can reach 10-10 m/s^2.In addition,according to the satellite precise orbit determination,for GPS satellites,the results of VARSRP and AVESRP are slightly smaller than those of the SRPM model,and the improvement is between 0.1 to 0.5 mm.For geosynchronous orbit(GEO)satellites of BDS,The AVESRP and VARSRP have an improvement of 3.5 mm and 4.0 mm,respectively,based on overlapping arc,and SLR check results show the AVESRP model and the VARSRP model is improved by 2.3 mm and 3.5 mm,respectively.Moreover,the change of inclined geosynchronous orbit(IGSO)satellites and medium earth orbit(MEO)satellites is relatively small,and the improvement is smaller than 0.5 mm.

Periodic exposure to ambient solar irradiance benefits the growth of juvenile seedlings of Hizikia fusiformis

In our trials, from 2007 to 2008, of mass production of seedlings of Hizikiafusiformis using synchronization techniques, problems of a ＂dark thalli＂ phenomenon and epiphytes contamination severely threatened the health of juvenile seedlings. In this investigation, we optimized conditions for improving the growth of juvenile seedlings. Seven string collectors were seeded with zygotes and a series of experiments were conducted including direct exposure to solar irradiance, co-culture with Ulva spp. and treatment with sodium hypochlorite. It was found that direct exposure to solar irradiance （maximum： 1 740 μmol photons/（m2.s）） for 2 h per day could efficiently enhance the growth of young seedlings and simultaneously inhibit the growth of epiphytic algae. In this treatment, 50-day old seedlings could reach an average of 0.44 cm in length and possess up to nine leaflets. However, a single treatment with 18-mmol/L sodium hypochlorite for 10 rain severely harmed 15-day old seedlings. In comparison, weekly treatment with 2.2-mmol/L sodium hypochlorite for 10 rain brought no apparent harm to seedlings and eliminated epiphytic algae efficiently. However, this treatment significantly increased the detachment rate of seedlings, Inoculating Ulva spp. onto the collector caused a dramatic decrease in the number of seedlings. However, the growth of the remaining seedlings appeared unhampered. All collectors except the control were daily sprayed with a high pressure water jet from the 84 day post fertilization. From the first day to 50th day, no ＂dark thallus＂ was observed on any of the seven collectors. We believe that well-timed daily exposure to solar irradiance would favor H. fusiformis in its early growing stages.

Measuring solar irradiance profiles in the Arctic sea ice using fiber optic spectrometry via inclined holes

An irradiance profile measurement approach and profiling system were developed to measure the solar irradiance profile of the Arctic sea ice using fiber optic spectrometry.The approach involved using a miniature spectrometer to sense light signals collected and transmitted from a fiber probe.The fiber probe was small,and could thus move freely in inclined bore holes drilled in sea ice with its optical entrance pointing upward.The input-output relationship of the system was analyzed and built.Influence factors that determined the system output were analyzed.A correctional system output approach was proposed to correct the influence of these factors,and to obtain the solar irradiance profile based on the measurements outputted by this system.The overall performance of the system was examined in two ice floes in the Arctic during the 9th Chinese National Arctic Research Expedition.The measured solar irradiance profiles were in good agreement with those obtained using other commercially available oceanographic radiometers.The derived apparent optical properties of sea ice were comparable to those of similar sea ice measured by other optical instruments.

Distribution of Solar Irradiance on Inclined Surfaces Due to the Plane of the Ground

Measurements of solar radiation are ordinarily made on horizontal planes recording global, diffuse and reflected components. The beam component and distribution of the global radiation on tilted planes can be calculated via the said components, as the position of the Sun in the sky’s sphere is known. Another ordinary procedure is measuring beam and diffuse components and calculating global radiation. These measurements require stationary equipment and in such a way it is difficult to study the influence of different grounds on the distribution of radiation on the inclined surfaces due to the ground. This distribution has some importance in civil engineering, but it is not popular in the field of solar radiation investigations. Present paper shows how this distribution can be calculated measuring only global irradiance on the horizontal and vertical planes. Such an approach, which is valid in clear-sky and overcast conditions, allows the use of a portable measuring device and studies of different grounds. The coincidence of the calculated values with the actual is good, except for snow-cover and discrete cloud, which do not correspond to the isotropic sky and ground models.

Identifying representative days of solar irradiance and wind speed in Brazil using machine learning techniques

The investment levels in electricity production capacity from variable Renewable Energy Sources have substantially grown in Brazil over the last decades,following the worldwide-seeking-goal of a carbon-neutral economy and the country’s incentives in diversifying its generation mix.From a long-term perspective,the current non-storable capability of renewable energy sources requires an adequate uncertainty characterization over the years.In this context,the main objective of this work is to provide a thorough descriptive analytics of the time-linked hourly-based daily dynamics of wind speed and solar irradiance in the main resourceful regions of Brazil.Leveraging on unsupervised Machine Learning methods,we focus on identifying similar days over the years,Representative Days,that can depict the fundamental underlying behaviour of each source.The analysis is based on a historical dataset of different sites with the highest potential and installed capacity of each source spread over the country:three in the Northeast and one in the South Regions,for wind speed;and three in the Northeast and one in the Southeast Regions,for solar irradiance.We use two Partitioning Methods(𝐾-Means and𝐾-Medoids),the Hierarchical Ward’s Method,and a Model-Based Method(Self-Organizing Maps).We identified that wind speed and solar irradiance can be effectively represented,respectively,by only two representative days,and two or three days,depending on the region and method(segments data with respect to the intensity of each source).Analysis with higher Representative Days highlighted important hidden patterns such as different wind speed modulations and solar irradiance peak-hours along the days.

Tilted global solar irradiance in Bahrain:an experimental study

In the present work,tilted global solar irradiance data are presented and analysed,measured for a period of 1 year on the campus of Bahrain Polytechnic,Kingdom of Bahrain,from both a fixed photovoltaic panel and a moving one via a two-axis solar tracker.The fixed panel faces south with an angle of 26°with respect to the horizontal,coinciding with the local geographical latitude.The second panel is moved by two motors,controlled by a global positioning system and suitable software so that the Sun’s rays are perpendicular to the panel surface.A pyranometer is installed on each panel,recording the tilted global solar irradiance,stored by using a data logger.The analysis of the data obtained shows a 33%solar energy gain on an annual basis for the moving panel(2780 versus 2088 kWh/m^(2) on the fixed panel).More importantly,in June,when the energy demand in Bahrain is elevated due to the increased residential cooling loads,the solar energy received by the moving panel is 54.7%higher compared with that of the fixed panel.On a percentage basis,the increase in solar energy from the moving panel is profound in the early morning and late evening hours.Moreover,the reduction in the solar energy received by the fixed panel from May to June does not appear in the moving panel because of the adjustable orientation of the latter.Throughout the year,the mean daily solar power varies between 0.37 and 0.56 kW/m^(2) for the fixed panel,and 0.45 and 0.70 kW/m^(2) for the moving panel.In winter,solar energy fluctuations are elevated due to erratic weather conditions that present a peak standard deviation of 28%of the corresponding mean.The data presented are useful for potential solar investments in Gulf countries.

Classification and Summarization of Solar Irradiance and Power Forecasting Methods:A Thorough Review

Solar forecasting is of great importance for ensuring safe and stable operations of the power system with increased solar power integration,thus numerous models have been presented and reviewed to predict solar irradiance and power forecasting in the past decade.Nevertheless,few studies take into account the temporal and spatial resolutions along with specific characteristics of the models.Therefore,this paper aims to demonstrate a comprehensive and systematic review to further solve these problems.First,five classifications and seven pre-processing methods of solar forecasting data are systematically reviewed,which are significant in improving forecasting accuracy.Then,various methods utilized in solar irradiance and power forecasting are thoroughly summarized and discussed,in which 128 algorithms are elaborated in tables in the light of input variables,temporal resolution,spatial resolution,forecast variables,metrics,and characteristics for a more fair and comprehensive comparison.Moreover,they are categorized into four groups,namely,statistical,physical,hybrid,and others with relevant application conditions and features.Meanwhile,six categories,along with 30 evaluation criteria,are summarized to clarify the major purposes/applicability of the different methods.The prominent merit of this study is that a total of seven perspectives and trends for further research in solar forecasting are identified,which aim to help readers more effectively utilize these approaches for future in-depth research.

Response of photoelectron peaks in the Martian ionosphere to solar EUV/X-ray irradiance

An important population of the dayside Martian ionosphere are photoelectrons that are produced by solar Extreme Ultraviolet and X-ray ionization of atmospheric neutrals.A typical photoelectron energy spectrum is characterized by a distinctive peak near 27 eV related to the strong solar HeⅡ emission line at 30.4 nm,and an additional peak near 500 eV related to O Auger ionization.In this study,the extensive measurements made by the Solar Wind Electron Analyzer on board the recent Mars Atmosphere and Volatile Evolution spacecraft are analyzed and found to verify the scenario that Martian ionosphere photoelectrons are driven by solar radiation.We report that the photoelectron intensities at the centers of both peaks increase steadily with increasing solar ionizing flux below 90 nm and that the observed solar cycle variation is substantially more prominent near the O Auger peak than near the HeⅡ peak.The latter observation is clearly driven by a larger variability in solar irradiance at shorter wavelengths.When the solar ionizing flux increases from 1 mW·m^-2 to 2.5 mW·m^-2,the photoelectron intensity increases by a factor of 3.2 at the HeⅡ peak and by a much larger factor of 10.5 at the O Auger peak,both within the optically thin regions of the Martian atmosphere.

Experimental characterization and correction of non-equivalence of Solar Irradiance Absolute Radiometer

We experimentally evaluate and correct the non-equivalence between electrical and radiative heating of solar irradiance absolute radiometer to compensate the systematic error of radiant power measurement at ambient pressure. A relative difference of the order of 0.08%-0.27% between electrical and radiative heating sensitivities is shown, and the resulting non-equivalence correction factor is calculated. The radiant power measurement equation is modified using the non-equivalence correction factor, a systematic deviation of 0.19% of radiant power measurement is hence eliminated.

Solar-assisted two-stage catalytic membrane reactor for coupling CO_(2) splitting with methane oxidation reaction

A two-stage catalytic membrane reactor(CMR)that couples CO_(2) splitting with methane oxidation reactions was constructed based on an oxygen-permeable perovskite asymmetric membrane.The asymmetric membrane comprises a dense SrFe_(0.9)Ta_(0.1)O_(3-σ)(SFT)separation layer and a porous Sr_(0.9)(Fe_(0.9)Ta_(0.1))_(0.9)Cu_(0.1)O_(3-σ)(SFTC)catalytic layer.In thefirst stage reactor,a CO_(2) splitting reaction(CDS:2CO_(2)→2CO+O_(2))occurs at the SFTC catalytic layer.Subsequently,the O_(2) product is selectively extracted through the SFT separation layer to the permeated side for the methane combustion reaction(MCR),which provides an extremely low oxygen partial pressure to enhance the oxygen extraction.In the second stage,a Sr_(0.9)(Fe_(0.9)Ta_(0.1))_(0.9)Ni_(0.1)O_(3-σ)(SFTN)catalyst is employed to reform the products derived from MCR.The two-stage CMR design results in a remarkable 35.4%CO_(2) conversion for CDS at 900℃.The two-stage CMR was extended to a hollowfiber configuration combining with solar irradiation.The solar-assisted two-stage CMR can operate stably for over 50 h with a high hydrogen yield of 18.1 mL min^(-1) cm^(-2).These results provide a novel strategy for reducing CO_(2) emissions,suggesting potential avenues for the design of the high-performance CMRs and catalysts based on perovskite oxides in the future.

Anomalous pattern of ocean heat content during different phases of the solar cycle in the tropical Pacific

Solar radiation is a forcing of the climate system with a quasi-11-year period.As a quasi-period forcing,the influence of the phase of the solar cycle on the ocean system is an interesting topic of study.In this paper,the authors investigate a particular feature,the ocean heat content（OHC）anomaly,in different phases of the total solar irradiance（TSI） cycle.The results show that almost opposite spatial patterns appear in the tropical Pacific during the ascending and declining phases of the TSI cycle.Further analysis reveals the presence of the quasi-decadal（11-year） solar signal in the SST,OHC and surface zonal wind anomaly field over the tropical Pacific with a high level of statistical confidence（95%）.It is noted that the maximum centers of the ocean temperature anomaly are trapped in the upper ocean above the main pycnocline,in which the variations of OHC are related closely with zonal wind and ocean currents.

Fengyun-4 Geostationary Satellite-Based Solar Energy Nowcasting System and Its Application in North China

Surface solar irradiance(SSI)nowcasting(0-3 h)is an effective way to overcome the intermittency of solar energy and to ensure the safe operation of grid-connected solar power plants.In this study,an SSI estimate and nowcasting system was established using the near-infrared channel of Fengyun-4A(FY-4A)geostationary satellite.The system is composed of two key components:The first is a hybrid SSI estimation method combining a physical clear-sky model and an empirical cloudy-sky model.The second component is the SSI nowcasting model,the core of which is the derivation of the cloud motion vector(CMV)using the block-matching method.The goal of simultaneous estimation and nowcasting of global horizontal irradiance(GHI)and direct normal irradiance(DNI)is fulfilled.The system was evaluated under different sky conditions using SSI measurements at Xianghe,a radiation station in the North China Plain.The results show that the accuracy of GHI estimation is higher than that of DNI estimation,with a normalized root-mean-square error(nRMSE)of 22.4%relative to 45.4%.The nRMSE of forecasting GHI and DNI at 30-180 min ahead varied within 25.1%-30.8%and 48.1%-53.4%,respectively.The discrepancy of SSI estimation depends on cloud occurrence frequency and shows a seasonal pattern,being lower in spring-summer and higher in autumn-winter.The FY-4A has great potential in supporting SSI nowcasting,which promotes the development of photovoltaic energy and the reduction of carbon emissions in China.The system can be improved further if calibration of the empirical method is improved.

Development of Solar Spectroradiometer for Meteorological Observation

A newgeneration of solar spectroradiometer has been developed by CUST/JRSI to improve solarirradiance observation data under hyperspectral resolution. It is based on the grating spectroradiometer with a back-thinned CCD linear image sensor and is operated in a hermetically sealed enclosure. The solar spectroradiometer is designed to measure the solar spectral irradiance from300 nm to 1100 nm wavelength range with the spectral resolution of 2 nm( the full width at half maximum). The optical bench is optimized to minimize stray light. The Peltier device is used to stabilize the temperature of CCD sensor to 25℃,while the change of temperature of CCD sensor is controlled to ±1℃ by the dedicated Peltier driver and control circuit.

Observation of clouds and solar radiation over the Pacific Ocean as relation to global climate

During a research cruise over the Pacific Ocean in 1989, solar irradiance was measured with a broad-band pyranometer along the cruise track. Cloud cover was photographed with an all-sky time-lapse came ra. Cloud types were observed and recorded. The data show that both the types and the amounts of clouds affect radiation fluxes on the sea surface. For low-level and middle-level clouds, the correlations (r) between measured irradiance (in Percent of calculated maximum irradiance) and cloud amount (in fraction of sky) were significant: r=-0. 79 and - 0. 66, respectively. For high-level clouds, the correlation was not significant: r=-0. 21. The results indicate that cloud shortwave forcing is a major modifier of the earth's surface insolation and change of cloud amount may affect global climate.

Potentiality of Solar Photovoltaic Energy in Paraiba, Brazil, and the Relation with Sustainable Development

The use of non-renewable energy has been a major environmental concern and, therefore, there is a need to look for other renewable energy sources, especially photovoltaic’s. In view of this, an attempt was made to quantify the potential of solar irradiance in the State of Paraiba, as an alternative source for conversion and use in electrical energy, these determinations being the main objectives. Global solar irradiance and solar photovoltaic data were extracted from scientific publications and/or made available on the websites of the National Institute of Meteorology (INMET), the Ministry of Mines and Energy and the National Electric Energy Agency, among others. For the case study, semi-structured questionnaires were applied in different business establishments in Campina Grande, with questions related to socioeconomic aspects and photovoltaic technology. Data were analyzed using descriptive statistics criteria and using an Excel spreadsheet. The main results indicated that the Brazilian energy matrix is predominantly from renewable sources. The Northeast is the second region with the highest production of photovoltaic solar energy and the State of Paraiba occupies its fourth position in the generation of this type of energy. The option of photovoltaic technology is a promising alternative, especially for rural areas, where there is not always a conventional electricity grid. The high availability of solar energy in northeastern Brazil, in almost all months of the year, especially in the state of Paraiba, demonstrates the existence of a high potential to generate electricity from photovoltaic systems. This technology contributes to local sustainable development, as it is an activity that generates employment and income, without degrading the environment.

Stochastic Modeling of Total Ground Irradiance of Horizontal Surface

This paper describes relatively simple stochastic model of the total ground irradiance of horizontal surface. For this purpose clearness index is modeled as a stochastic signal. The parameters of clearness index stochastic signal are chosen to fit values of daily mean insolation for each month for the location of Zagreb, Croatia. Complete model has been done in MATLAB. This model can be used for Monte Carlo simulations of technical solar systems such as photovoltaic systems or solar thermal energy systems.

Bi-LSTM-Based Deep Stacked Sequence-to-Sequence Autoencoder for Forecasting Solar Irradiation and Wind Speed

Wind and solar energy are two popular forms of renewable energy used in microgrids and facilitating the transition towards net-zero carbon emissions by 2050.However,they are exceedingly unpredictable since they rely highly on weather and atmospheric conditions.In microgrids,smart energy management systems,such as integrated demand response programs,are permanently established on a step-ahead basis,which means that accu-rate forecasting of wind speed and solar irradiance intervals is becoming increasingly crucial to the optimal operation and planning of microgrids.With this in mind,a novel“bidirectional long short-term memory network”(Bi-LSTM)-based,deep stacked,sequence-to-sequence autoencoder(S2SAE)forecasting model for predicting short-term solar irradiation and wind speed was developed and evaluated in MATLAB.To create a deep stacked S2SAE prediction model,a deep Bi-LSTM-based encoder and decoder are stacked on top of one another to reduce the dimension of the input sequence,extract its features,and then reconstruct it to produce the forecasts.Hyperparameters of the proposed deep stacked S2SAE forecasting model were optimized using the Bayesian optimization algorithm.Moreover,the forecasting performance of the proposed Bi-LSTM-based deep stacked S2SAE model was compared to three other deep,and shallow stacked S2SAEs,i.e.,the LSTM-based deep stacked S2SAE model,gated recurrent unit-based deep stacked S2SAE model,and Bi-LSTM-based shallow stacked S2SAE model.All these models were also optimized and modeled in MATLAB.The results simulated based on actual data confirmed that the proposed model outperformed the alternatives by achieving an accuracy of up to 99.7%,which evidenced the high reliability of the proposed forecasting.

Artificial Intelligence Based Solar Radiation Predictive Model Using Weather Forecasts

Solar energy has gained attention in the past two decades,since it is an effective renewable energy source that causes no harm to the environment.Solar Irradiation Prediction(SIP)is essential to plan,schedule,and manage photovoltaic power plants and grid-based power generation systems.Numerous models have been proposed for SIP in the literature while such studies demand huge volumes of weather data about the target location for a lengthy period of time.In this scenario,commonly available Artificial Intelligence(AI)technique can be trained over past values of irradiance as well as weatherrelated parameters such as temperature,humidity,wind speed,pressure,and precipitation.Therefore,in current study,the authors aimed at developing a solar irradiance prediction model by integrating big data analytics with AI models(BDAAI-SIP)using weather forecasting data.In order to perform long-term collection of weather data,Hadoop MapReduce tool is employed.The proposed solar irradiance prediction model operates on different stages.Primarily,data preprocessing take place using various sub processes such as data conversion,missing value replacement,and data normalization.Besides,Elman Neural Network(ENN),a type of feedforward neural network is also applied for predictive analysis.It is divided into input layer,hidden layer,loadbearing layer,and output layer.To overcome the insufficiency of ENN in choosing the value of weights and hidden layer neuron count,Mayfly Optimization(MFO)algorithm is applied.In order to validate the performance of the proposed model,a series of experiments was conducted.The experimental values infer that the proposed model outperformed other methods used for comparison.