Solar Radiation Prediction Based on Convolution Neural Network and Long Short-Term Memory

Photovoltaic power generation is highly valued and has developed rapidly throughout the world. However, the fluctuation of solar irradiance affects the stability of the photovoltaic power system and endangers the safety of the power grid. Therefore, ultra-short-term solar irradiance predictions are widely used to provide decision support for power dispatching systems. Although a great deal of research has been done, there is still room for improvement regarding the prediction accuracy of solar irradiance including global horizontal irradiance, direct normal irradiance and diffuse irradiance. This study took the direct normal irradiance (DNI) as prediction target and proposed a Siamese convolutional neural network-long short-term memory (SCNN-LSTM) model to predict the inter-hour DNI by combining the time-dependent spatial features of total sky images and historical meteorological observations. First, the features of total sky images were automatically extracted using a Siamese CNN to describe the cloud information. Next, the image features and meteorological observations were fused and then predicted the DNI in 10-min ahead using an LSTM. To verify the validity of the proposed SCNN-LSTM model, several experiments were carried out using two-year historical observation data provided by the National Renewable Energy Laboratory (NREL). The results show that the proposed method achieved nRMSE of 23.47% and forecast skill of 24.51% for the whole year of 2014, and it also did better than some published methods especially under clear sky and rainy days.

Numerical design and studies of multipurpose concentrated solar thermal heating system

Solar thermal energy systems are future sustainable solutions for both domestic as well as industrial use. Solar thermal systems operating in medium temperature range (373-673 K) require concentrated solar-thermal heating (CSH). In this work, a comprehensive numerical tool is developed to design and study multipurpose on-sun CSH system. The model uses a combined Monte-Carlo ray tracing, finite difference method and all heat transfer modes. The model is validated with in-house experiment, which demonstrates its predictive capability. Next, the tool is used to optimise the cavity receiver geometry and predict the performance of the optimised CSH system under different direct normal irradiance (DNI) conditions. A CSH system using Therminol D12 as HTF is presented. Therminol D12 HTF based system is predicted to take longer time than the system using water as HTF, for heating water to a specified temperature because of the heat exchanger effectiveness. However, the designed CSH system using Therminol D12 can attain higher temperatures than water without pressurization and through the heat exchanger can be used as multipurpose system suitable for cooking, laundry, sterilization, process industry etc.

Field Quality Control of Spectral Solar Irradiance Measurements by Comparison with Broadband Measurements

Measurement of solar spectral irradiance is required in an increasingly wide variety of technical applications, such as atmospheric studies, health, and solar energy, among others. The solar spectral irradiance at ground level has a strong dependence on many atmospheric parameters. In addition, spectroradiometer optics and detectors have high sensitivity. Because of this, it is necessary to compare with a reference instrumentation or light source to verify the quality of measurements. A simple and realistic test for validating solar spectral irradiance measurements is presented in this study. This methodology is applicable for a specific spectral range inside the broadband range from 280 to 4000 nm under cloudless sky conditions. The method compares solar spectral irradiance measurements with both predictions of clear-sky solar spectral irradiance and measurements of broadband instruments such as pyrheliometers. For the spectral estimation, a free atmospheric transmittance simulation code with the air mass calculation as the mean parameter was used. The spectral direct normal irradiance (Gbλ) measurements of two different spectroradiometers were tested at Plataforma Solar de Almería, Spain. The results are presented in this article. Although only Gbλ measurements were considered in this study, the same methodology can be applied to the other solar irradiance components.

Analyzing Regional and Local Changes in Irradiance during the 2019 Total Solar Eclipse in Chile, Using Field Observations and Analytical Modeling

Solar eclipses are astronomic phenomena in which the Earth’s moon transits between the planet and the Sun, projecting a shadow onto the planet’s surface. As solar power installed capacity increases, detailed studies of this region-wide phenomenon’s effect in irradiance is of interest; however, the literature mainly reports its effects on localized scales. A measurement campaign spanning over 1400 km was pursued for the 2 July 2019 total solar eclipse in Chile, to register the event and establish a modeling framework to assess solar eclipse effects in irradiance over wide regional scales. This work describes the event and presents an estimation framework to decompose atmospheric and eclipse effects on irradiance. An analytical model was applied to study irradiance attenuation throughout the Chilean mainland territory, using satellite-derived and astronomical data as inputs compared to ground measurements in eight stations. Results showed good agreement between model and observations, with Mean Bias Errors of −0.008 to 0.98 W/m2 for Global Horizontal Irradiance and −0.004 to −4.664 W/m2 for Direct Normal Irradiance, with Normalized Root Mean Squared Errors of 0.7–5.8% and 1.4–12.2%, respectively. Energy losses due to obscuration corresponded between 20–40% for Global Horizontal Irradiance and 25–50% for Direct Normal Irradiance over Chilean territory.

Satellite-derived sunshine duration data in the CM SAF SARAH-3 climate data record

<p>Sunshine Duration (SDU) is an important parameter in climate monitoring (e.g., due to the availability of long term measurements) and weather application. The exceptional sunny years in Europe since 2018 have raised also the attention of the general public towards this parameter.</p><p>The definition of SDU by WMO via the threshold of 120 W/m<sup>2</sup> for the Direct Normal Irradiance (DNI) allows the estimation of sunshine duration from satellite-derived surface irradiance data. Sunshine duration is part of the climate data record (CDR) “Surface Solar Radiation data set – Heliosat” (SARAH-2.1, doi: 10.5676/EUM_SAF_CM/SARAH/V002_01) by EUMETSAT Satellite Application Facility on Climate Monitoring (CM SAF), which is based on observations from the series of Meteosat satellites. The provided temporal resolutions are daily and monthly sums with a grid space of 0.05°; the data are available from 1983 to 2017 at www.cmsaf.eu. This climate data record is temporally extended by the so-called SARAH-ICDR (Interim Climate Data record) with an average timeliness of 3 days to allow climate monitoring. An updated, improved, and extended version of the SARAH-2.1 CDR is currently being developed and will be made available in early 2022. The SARAH-3 CDR of sunshine duration, covering 1983 to 2020, will be improved compared to the current version, in particular during situations with snow-covered surfaces.</p><p>Here, the algorithm, improvements compared to SARAH-2.1 and a first validation will be presented for sunshine duration, especially for Germany and Europe. The validation is based on station data from Climate Data Center (CDC) for Germany and European Climate Assessment & Dataset (ECA&D) for Europe.</p>

Feasibility analysis of a CPV system sized by means of a TJ cell black-box model and applied to a livestock farm welding

In the Concentrating Photovoltaic (CPV) systems, the Triple-Junction (TJ) cell electrical power is separately evaluated as function of its temperature or of the solar concentration factor (C), but generally not simultaneously as a function of both variables. Because all these variables are difficult to link by means of a white-box model, a mathematical model of the black-box type based on experimental data, is defined in this paper in order to link directly the TJ cell electric power together with Direct Normal Irradiance (DNI) and TJ cell temperature at different values of C. The knowledge of a link among TJ cell electric power, DNI and TJ cell temperature is basic to evaluate the real performances of a CPV system when it has to be sized, adopting a modular configuration, to meet the energy demands of a user. Hence, the feasibility of a CPV system adopted for an agricultural livestock farm located in Salerno (Italy), is evaluated by means of the model. The main activity of the farm is the breeding of cattle and sheep for milk production; the farm is made up of a stable and a farmhouse. The optimal number of TJ cells is defined to maximize the profitability of the investment, expressed in terms of Net Present Value. A CPV plant made up of 3000 cells, with an electric peak power of 6.6 kW, allows to maximize the NPV value up to about 16 k€.