Solar Radiation Power Research Articles

Analysis of Inverter Efficiency Using Photovoltaic Power Generation Element Parameters

Photovoltaic power generation is influenced not only by variable environmental factors, such as solar radiation, temperature, and humidity, but also by the condition of equipment, including solar modules and inverters. In order to preserve energy production, it is essential to maintain and operate the equipment in optimal condition, which makes it crucial to determine the condition of the equipment in advance. This paper proposes a method of determining a degradation of efficiency by focusing on photovoltaic equipment, especially inverters, using LSTM (Long Short-Term Memory) for maintenance. The deterioration in the efficiency of the inverter is set based on the power generation predicted through the LSTM model. To this end, a correlation analysis and a linear analysis were performed between the power generation data collected at the power plant to learn the power generation prediction model and the data collected by the environmental sensor. With this analysis, a model was trained using solar radiation data and power data that are highly correlated with power generation. The results of the evaluation of the model’s performance show that it achieves a MAPE of 7.36, an RMSE of 27.91, a MAE of 18.43, and an R2 of 0.97. The verified model is applied to the power generation data of the selected inverters for the years 2020, 2021, and 2022. Through statistical analysis, it was determined that the error rate in 2022, the third year of its operation, increased by 159.55W on average from the error rate of the power generation forecast in 2020, the first year of operation. This indicates a 0.75% decrease in the inverter’s efficiency compared to the inverter’s power generation capacity. Therefore, it is judged that it can be applied effectively to analyses of inverter efficiency in the operation of photovoltaic plants.

Investigation into the electrolysis performance of a novel directly solar irradiated solid oxide electrolysis cell

Current coupling methods linking solar energy to solid oxide electrolysis cell (SOEC) mostly involve indirect coupling, with limited studies exploring direct coupling. This study is the first to evaluate a novel directly solar irradiated solid oxide electrolysis cell, anticipating a reduction in polarization loss incurred during the electrolysis process and improving the electrochemical performance of the system through direct solar irradiation. Additionally, it aims to reduce electric energy consumption required to maintain the high-temperature environment for the reaction and enhance the energy conversion efficiency of the electrolysis system, presenting a unique coupling technology. Hence, this paper proposes and develops the inaugural solar SOEC system, directly harnessing sunlight on the SOEC electrode surface, achieving stable and continuous hydrogen production through experimental methods. Experimental results demonstrate that direct solar irradiation increases the SOEC system’s heating rate by 12 times compared to electric heating, with a notably swifter response time. Under identical electrolysis voltages, the system exhibits significantly higher efficiency under direct solar irradiation than under electric heating. Moreover, for equivalent hydrogen production, the total energy input from solar energy is lower than that from electric heating, saving about 76 % of energy. Under specific conditions—solar radiation power of 123.2 W, electrolysis temperature of 655 °C, cathode-side gas input maintaining a water-hydrogen molar ratio of 8:2, and an electrolysis voltage of 1.5 V—the SOEC system sustains a nearly constant current density of about 359 mA/cm2 for 3 h. Comparative experiments conducted under identical working conditions, both in solar and electrically heated environments, reveal that the electrochemical impedance spectroscopy indicates inhibited mass transfer processes during electrolysis under direct solar irradiation. Consequently, the electrochemical performance of the SOEC system operating under direct solar irradiation was lower than that under electrically heated environments, across varying electrolysis temperatures and water contents. This study uncovers the pivotal influence of direct solar irradiation on concentration losses during the electrolysis process. The corresponding concentration losses can be subsequently mitigated by optimizing the reactor structure of the solar SOEC system.

Application of silicon nanowires in sensors of temperature, light and humidity

Resistive and capacitive types of sensors based on silicon nanowires (SiNWs) for measuring of physical quantities have been manufactured. Silicon nanowires were obtained through a two-step metal-assisted chemical etching (MACE) method. The surface morphology of the silicon nanowire array was investigated using atomic force microscopy (AFM) and scanning electron microscopy (SEM). The impact of SiNWs synthesis parameters on sensor sensitivity has been investigated. In particular, the influence of deposition time of AgNPs and etching time of silicon, as well as the content of H2O2 in the etchant, preliminary texturing of the substrate, and additional post-processing in isotropic/anisotropic etchant after the MACE process, on the characteristics of physical quantity sensors has been determined. Static and dynamic parameters were calculated for the obtained sensors. To compare the obtained sensors, physical sensors without SiNWs were manufactured. The highest response value for temperature sensors was 132, which is two orders of magnitude better than for sensors without SiNWs. The presence of SiNWs on the surface of the sensor led to an increase in the response value by about two orders of magnitude for all types of sensors. The speed of humidity sensors improved by 3–4 times, and for temperature and light sensors by an order of magnitude. Further device applications include of multi-parameter sensors, human breath sensors, and solar radiation power sensors.

Fe/Ni bimetallic magnetic nano-alloy (INBMNA): An efficient heterogeneous catalyst for photo-Fenton-like degradation of phenol in aqueous environment

A lot of attention has been drawn to photo-Fenton-like catalysis among advanced oxidation processes for environmental remediation applications. Herein, we have successfully fabricated iron-nickel bimetallic magnetic nano-alloy (INBMNA) as an efficient heterogeneous photo-Fenton-like catalyst using the chemical reduction method and characterized by several analytical techniques. The characterization results show that the catalyst has a spherical shape with a mesoporous nature and contains a large specific surface area. The impact of various parameters was investigated and optimized to check the catalytic performance of INBMNAs and the found results showed that excellent photo-Fenton-like activity persisted under 6.0 pH conditions for the degradation of hazardous pollutant (phenol) under solar light exposure and microwave radiation power, respectively. Additionally, the exposed INBMNA/H2O2 system provided continuous redox cycles of Fe3+/Fe2+ and Ni2+/Ni0 pair in the Fenton-active species for stable operation. The photo-Fenton-like activity was also performed to check the effect of different inorganic anions which significantly hinder phenol reduction. Besides, the steady performance of the catalyst to remove phenol was performed in tap water and river water. Free radical trapping experiments were tested to know the role of important radicals in the photo-Fenton process. Moreover, the mechanism and possible degradation pathways of phenol were checked. By cyclic degradation experiments, the performance of the catalyst is stable and almost unchanged and can be reused several times. This study provides a promising INBMNA/H2O2 system, which encourages its widespread use in environmental remediation applications.

3D liquid-based porous coating integrated with oleophilic MXene nanoflakes for durable ultra-low ice adhesion and exceptional photothermal slippery properties

The accumulation of ice on the surfaces of equipment/facilities can result in energy wastage, substantial economic losses, and even pose a threat to personal safety. In this work, a three-dimensional (3D) liquid-based porous resin coating doped with oleophilic molybdenum carbide (Mo2C) MXene nanoflakes was fabricated on a pre-coated oleogel sealer layer of aluminum plate. The results showed a reduction of approximately 99.1 % in ice adhesion strength (∼4.66 kPa) compared to the sandblasted aluminum plate and consistently maintained ice adhesion strength below 10 kPa for 70 days. Moreover, the coating exhibited excellent photothermal properties, with icing time delayed by a factor of 33.2 under simulated solar radiation power of 96 mW/cm2 (1 sun) at an ambient temperature of − 15 °C. The ice adhered to the coating could easily slide off without the external force under “1 sun” at − 10 °C. The superior anti/de-icing performance of the coating can be primarily attributed to the low interfacial modulus of the porous structure, the exceptional retention of silicone-oil, and the excellent photothermal effect of embedded MXene nanoflakes. The 3D liquid-based porous coating, possessing extremely low ice adhesion and remarkable de-icing stability, demonstrates the substantial potential for practical applications that require sustained anti/de-icing performance.

Improving the systems for controlling ground-based sun orientation devices

The control system for terrestrial two-axis devices for orientation to the Sun has been improved with a high-speed microcontroller operation algorithm. A geomagnetic sensor was introduced into the system to increase the reliability of monitoring the positioning of solar cells. The basis of the algorithm is a simplified astronomical and geographical model of the movement of the Sun in the celestial sphere. The control system automatically tracks the trajectory of the Sun and calculates its angular coordinates for the current moment of time on any day of the year and for any point on the globe. The derived equations of the simplified mathematical model are suitable for calculations of orientation angles to the Sun in real time on 8-bit microcontrollers with low computing power. The control system by AVR-328 microcontrollers was studied. It was established that the use of the algorithm when programming microcontrollers for two-axis orientation systems ensures high stability and reliability of the tracker`s functioning process. The technical parameters of the AVR-328 microcontrollers in the case of using the developed algorithm ensure that the control system performs one reorientation step in a time interval of less than 2 seconds, which ensures the minimum technical period of the reorientation process by the tracker drive mechanisms which is about 5 seconds. Deviations of the calculated orientation angle from the exact value do not exceed 3°, which corresponds to the relative accuracy of recording the solar radiation intensity, which is less than 0.3 %. The microcontroller program written according to the developed simplified algorithm occupies about 35 % of its memory. Therefore, the use of the developed algorithm frees up the resources of AVR-328 microcontrollers for performing additional data processing operations and automatic control over various additional devices related to the process of orientation to the Sun. In the case of solar energy, the algorithm ensures the use of about 98 % of the power of solar radiation

Simulation model of a flat plate air solar collector

Simulation model of a flat plate air solar collector

Corrective Day-ahead Prediction of Solar Radiation based on Online Measurements

In recent years, reduction of greenhouse gas emissions has been a serious issue throughout the world. The Japanese Government aims to reduce 25% of the emissions in 1990 by 2020. Eco-cities which effectively use renewable energy sources attract an attention in order to attain this goal. A smart energy town project in Honjyo, Japan has been conducted by making use of renewable energy sources. Above all, photovoltaic (PV) generators are expected to play a key role in this project. In addition, PV generators are expected to be installed in the residential and commercial areas due to ease of its installation. However, unstable power output from PV generation causes negative impacts on power quality of distribution networks. Therefore, prediction of PV output is indispensable to operate networks properly. In this paper, we propose a method to predict a day-ahead solar radiation and output power of PV generation in specific areas. Furthermore, the predicted solar radiation is corrected using the on-line measured actual data. As a result, the correction of a day-ahead prediction proposed here reduces errors of daily solar radiation by around 34% .

Enhanced Anti/De-Icing Performance on Rough Surfaces Based on The Synergistic Effect of Fluorinated Resin and Embedded Graphene.

Icing negatively impacts various industrial sectors and daily life, often leading to severe safety problems and substantial economic losses. In this work, a fluorinated resin coating with embedded graphene nanoflakes is prepared using a spin-coating curing process. The results shows that the ice adhesion strength is reduced by ≈97.0% compared to the mirrored aluminum plate, and the icing time is delayed by a factor of 46.3 under simulated solar radiation power of 96mWcm-2 (1 sun) at an ambient temperature of -15°C. The superior anti/de-icing properties of the coating are mainly attributed to the synergistic effect of the fluorinated resin with a low surface energy, the rough structure of the sandblasted aluminum plate, which reduces the contact area, and the embedded graphene nanoflakes with a superior photothermal effect. Furthermore, the hydrogen bonding competition effect between the exposed-edge oxygen-containing functional groups of the embedded graphene nanoflakes and water molecules further improves the anti-icing properties. This work proposes a facile preparation method to prepare coatings with excellent anti/de-icing properties, offering significant potential for large-scale engineering applications.

Experimental Analysis of Weather Condition Effects on Photovoltaic Systems’ Performance: A Jordan Case Study

Energy generation and economic development are closely linked, with energy playing a pivotal role in wealth creation. However, the finite nature of fossil fuel resources and associated environmental challenges has emphasized the need for sustainable energy alternatives based on renewable sources. Among these alternatives, photovoltaic (PV) systems hold significant potential for fostering a sustainable energy system. Despite ongoing material research, achieving a major breakthrough in enhancing the conversion efficiency of commercial PV modules remains a challenge. To optimize PV system yield, installation must consider geographic location and design factors. PV modules often yield different results compared to manufacturer specifications due to factors such as high temperatures, dust, and arid to semiarid climates. Therefore, it is crucial to conduct outdoor testing and characterization of PV modules tailored to specific locations, such as Jordan, to maximize system performance. This research aims to examine the impact of ambient temperature, dust accumulation, and solar irradiance intensity on PV system performance in Jordan, providing valuable insights through monitoring power output variations. The findings will contribute to improving PV system efficiency in Jordan’s unique climate and aid manufacturers in developing innovative PV applications. The collected data includes solar radiation, temperature, voltage, current, and output power. The results confirm that the Azraq site is a better location when compared to Mafraq based on the possibility of generated more output power using a PV system.

Investigation into the hydrogen production performance of a novel 5-kW hybrid-system composed of a solar steam generator directly connected with conventional solid oxide electrolysis cells

Coupling solar energy with solid oxide electrolysis cell has the potential to reduce electricity consumption and improve energy conversion efficiency. This study introduces a pioneering 5 kW direct-connected hybrid system that couples a solar steam generator with solid oxide electrolysis cells utilizing conventional electrical energy for the electrolysis process. The successful demonstration of hydrogen production showcases promising results. When the solar irradiation power is 2.26 kW, the inlet water flow rate is 1.23 kg/h under operations at 700 °C, the hydrogen production efficiency of the system reaches 95.2 %, and the steam conversion ratio approaches 92 %, giving a cumulative hydrogen production yield of 5,840 NL in 6.3 h. The solid oxide electrolysis system is further tested under different operating conditions of the stack and solar irradiation. The experimental results show that a greater operating temperature is conducive to more efficient hydrogen production, while more water vapor at the cathode leads to a larger steam conversion ratio. The results indicate that increasing the irradiation power is beneficial to hydrogen production while decreasing the irradiation power will lead to fluctuations of hydrogen yield. In addition, the system efficiency (45.3 %) is higher than that of a photovoltaic alkaline water electrolysis (12.6 %) or photovoltaic proton exchange membrane electrolysis (14.76 %) system at the same irradiation power. Under the same electrolysis power and cathode inlet temperature, the total power consumption of a traditional solid oxide electrolysis system is significantly greater than that of the proposed hybrid system. The comparison shows that the saved electricity of the proposed hybrid system can account for about 30 %. Therefore, the proposed hybrid system has significant efficiency and power savings advantages.

The preparation of CNTs/GP/TiN/PDMS/PVDF superhydrophobic coating with strong photothermal and electrothermal properties for anti-icing and de-icing

A superhydrophobic coating (PESC) with prominent photothermal and electrothermal properties was obtained by using multi-wall carbon nanotubes (CNTs), graphite powder (GP) and titanium nitride (TiN) nanoparticles as fillers and polydimethylsiloxane (PDMS) and polyvinylidene fluoride (PVDF) as binders. The water contact angle (WCA), water sliding angle (WSA) and the square resistance of the coating is about 154.3 ± 0.5°, 4 ± 0.5° and 25.9 ± 0.5 Ω/□, respectively. The coating can keep an excellent superhydrophobic, conductive, photothermal and electrothermal stability in an environment with huge alternating temperature differences. The measurement results show that the saturation temperature of the PESC become higher and the time required for saturation temperature is also getting shorter by the co-heating of the weak solar radiation and low power density electric heating. Compared to the icing time of the water droplet on the bare glass surface, the icing time of the water droplet on the PESC surface was nearly 14 times longer. The ice-melting ability of the PESC can become stronger with the photo-electric co-heating. Especially, for the co-action of the weak solar radiation and low electrothermal power density, the temperature rise performance, anti-icing and de-icing properties of the PESC is still very good. This makes the PESC have good potential applications in the weak solar radiation and low temperature environment.

Experimental study on a novel waterless solar collector

This study is an endeavour to introduce a novel approach to enhance the performance of solar collectors. The sun emits sufficient power of solar radiation to meet the demand of en-ergy. Harvesting the renewable solar energy needs advanced technologies and requirements. Solar ponds including salinity gradient solar ponds (SGSPs) are common solar collectors. These ponds are one of the solar energy applications used for many industrial and domestic purposes. However, challenges of the conventional SGSPs such as evaporation, salt diffusion, temperature discrepancy, and layer mixing profoundly and significantly affected their expan-sion globally. A novel experimental solar collector configuration to overcome the challenges of the conventional solar ponds (solar collectors) is investigated, there is no water body and no salinity gradient to build; it is entirely a collector with no water body. The experimental unit was constructed in an arid area. It is basically a cylindrical tank with a total depth of 1.4 m with three zones or layers to store heat namely, paraffin wax layer (10 cm thickness). The paraffin layer was covered with a layer of coal with a thickness of 30 cm. On the top of coal layer, an air gap with a thickness of 80 cm was left. A clear plastic cover with a thickness of 0.2 cm was utilized to cover the constructed layers and making the air gap. The experimental unit was monitored, and temperature measurements were collected for the period of 17/7/2021- 30/9/2021. The results demonstrated that temperature of the paraffin wax layer reached more than 48 °C in a short period and with a small day and night discrepancy (1 °C). Temperature of the paraffin layer remained constant around 43 °C even in night-time during the period of the study. Furthermore, the results showed that temperatures of coal layer and air gap reached the maximum at the daytime of 53 °C and 71 °C respectively with a clear discrepancy between day and night. The results of the present study are encouraging for more investigations in this new direction of solar collectors.

New Analysis of the Seasonal Variation of the Critical Frequencies foF2 by a Proposed Formula of the Power of Solar Radiation

The present article is a new analysis of the seasonal variation of the critical frequencies foF2 by establishing a formula as a tool. Thus, from the formula of the power of solar radiation proposed, by its two components, one the power linked to the angles of attack of the solar rays and the other the power imparted to the Earth-Sun distance, we will understand the asymmetries foF2 peaks at the equinoxes and the various winter and semiannual anomalies. By the power component imparted to the contribution of sunspots, we will understand the reversal of the maximum peak during the growth and waning phase of the solar cycle. Finally, by the power component linked to the transport mechanism and the reinforcement by the solar wind of the ionization, we will understand the why of the noninversion of the maximum of the peaks.

Radio Resource Management Satellite Communication Network MCDM Method

Worldwide deployment of heterogeneous wireless networks is growing as a result of consumer demand for connectivity at all times and in all places. These customers' interest in multimedia apps like video streaming and VoIP, which demand tight Quality of Service (QoS) support, is growing at the same time. With such limitations, provisioning network resources is a difficult undertaking. In fact, it might be challenging for a network operator to identify trustworthy criteria to choose the optimum network that ensures user happiness while maximising network utilisation, given the availability of numerous access technologies (WiFi, WiMAX, or cellular networks). To solve this problem, each eNB just needs to learn the traffi c conditions or patterns of its owncell in our proposal. Wireless communication systems depend heavily on radio resource management (RRM). To ensure the efficient and successful operation of wireless networks, it involves the allocation and control of radio frequency spectrum, power, and other resources. RRM is significant because it can use scarce radio resources as efficiently as possible, enhancing capacity, lowering interference, and improving service quality. Successful deployment and operation of wireless communication systems like cellular networks, Wi-Fi, and Bluetooth depend on effective RRM approaches. The need for wireless communication is growing, and new technologies and standards are constantly being developed. The methodology of radio resource management (RRM) involves a variety of techniques and algorithms designed to allocate radio resources in a way that maximizes network performance while minimizing interference. Taken as alternate parameter is Laser communication, optical networks, satellite optical communication, vibrations, satellite networks. Taken as is solar radiation power, thermal bending, micro meteorite impact, solar and lunar gravity, earth oblations method. satellite optical communication has reached near 2000 data set compare other data set. The operation of wireless communication networks depends on radio resource management (RRM). Wireless networks would have interference, congestion, and a lacklustre level of service if effective RRM procedures weren't used. RRM is therefore a key component in ensuring that wireless communication systems can provide users with dependable and high-quality services.

Decomposition spectral graph convolutional network based on multi-channel adaptive adjacency matrix for renewable energy prediction

The intermittence and randomicity of renewable energy can seriously disrupt its productivity and reliability, particularly in unforeseen circumstances. Yet, most existing renewable energy prediction (REP) methods fail to model the inter-temporal correlations among input variables and suffer from impractical decomposition process, resulting in less good prediction accuracy. Aiming to improve these issues and power REP technique to better serve modern society, this work proposes a novel decomposition spectral graph convolutional network, named DASGCN, as a general solution for REP. Compared with existing REP models, DASGCN has two main characteristics: (1) It incorporates a carefully designed decomposition block which can decompose input multivariate time series efficiently, (2) A multi-channel adaptive adjacent matrix is proposed to model the complex correlation among entangled input variables automatically and generate the interpretable graph structure without prior domain knowledge. The comprehensive experiments on four real-world datasets demonstrate that the proposed DASGCN can significantly outperform benchmark models and achieve high performance on wind speed, wind power, solar radiation and photovoltaic power prediction tasks.

Improving Solar PV Prediction Performance with RF-CatBoost Ensemble: A Robust and Complementary Approach

Although solar energy is renewable, environmental conditions can make it unpredictable, which makes it difficult to maintain a consistent supply of electricity. Accurate solar forecast techniques are essential to overcome this. Therefore, an efficient model for predicting solar irradiance and PV power output is presented in this study. The suggested model is especially designed for Agartala city in Tripura, India, where the installed capacity of Grid Interactive Solar Power is extremely low. The proposed model for solar irradiance prediction involves utilizing a combination of the Random Forest and CatBoost algorithms. The model is developed using 10 years of solar data and other relevant meteorological parameters with a 1-hour interval and assessed at various stages to make long-term monthly predictions. In addition, we compared this model to other existing models for solar irradiance prediction. The study showcased the efficacy of Random Forest and CatBoost algorithms when utilized individually and as an ensemble. The results demonstrate the effectiveness of the Random Forest and CatBoost ensemble, with an impressive accuracy improvement of 6% and an R2-score of 86%. Additionally, in terms of RMSE and MAE, the model demonstrates superior performance with lower values of 83.8466 and 45.4011, respectively confirms to the proposed model's viability and suitability for long-term solar radiation and PV power predictions.

Improving the methodology for determining the main parameters of solar batteries

The article cites the need for a reliable and economical power supply to rural consumers. At the same time, it is important to develop distributed generation, including on the basis of renewable sources, using solar and wind energy to reduce costs. The necessity of choosing solar panels with optimal parameters, taking into account the influence of external factors, is shown. To determine the actual generated power of solar batteries, the concept of "power loss during the conversion of the solar radiation flux into electrical power" is introduced. It has been established that insufficient studies of the regime parameters of photocells, in particular, the temperature of its heating and the corresponding change in efficiency, taking into account external factors, do not allow choosing a module with effective power. To study the parameters of solar batteries, an equivalent circuit and methods for determining its parameters are presented. The established dependence of the excess of the SM temperature over the ambient temperature on the power of solar radiation is presented, which formed the basis of an improved method for determining the parameters of solar batteries. The presented results of the study allow at the design stages to determine the expected power of a solar photovoltaic installation and choose its optimal parameters.

Daytime radiative cooling multilayer films designed by a machine learning method and genetic algorithm.

Recently, there has been growing interest and attention towards daytime radiative cooling. This cooling technology is considered a potentially significant alternative to traditional cooling methods because of its neither energy consumption nor harmful gas emission during operation. In this paper, a daytime radiative cooling emitter (DRCE) consisting of polydimethylsiloxane, silicon dioxide, and aluminum nitride from top to bottom on a silver-silicon substrate was designed by a machine learning method (MLM) and genetic algorithm to achieve daytime radiative cooling. The optimal DRCE had 94.43% average total hemispherical emissivity in the atmospheric window wavelength band and 98.25% average total hemispherical reflectivity in the solar radiation wavelength band. When the ambient temperature was 30°C, and the power of solar radiation was about 900W/m 2, the net cooling power of the optimal DRCE could achieve 140.38W/m 2. The steady-state temperature of that could be approximately 9.08°C lower than the ambient temperature. This paper provides a general research strategy for MLM-driven design of DRCE.

Investigating the Power of LSTM-Based Models in Solar Energy Forecasting

Solar is a significant renewable energy source. Solar energy can provide for the world’s energy needs while minimizing global warming from traditional sources. Forecasting the output of renewable energy has a considerable impact on decisions about the operation and management of power systems. It is crucial to accurately forecast the output of renewable energy sources in order to assure grid dependability and sustainability and to reduce the risk and expense of energy markets and systems. Recent advancements in long short-term memory (LSTM) have attracted researchers to the model, and its promising potential is reflected in the method’s richness and the growing number of papers about it. To facilitate further research and development in this area, this paper investigates LSTM models for forecasting solar energy by using time-series data. The paper is divided into two parts: (1) independent LSTM models and (2) hybrid models that incorporate LSTM as another type of technique. The Root mean square error (RMSE) and other error metrics are used as the representative evaluation metrics for comparing the accuracy of the selected methods. According to empirical studies, the two types of models (independent LSTM and hybrid) have distinct advantages and disadvantages depending on the scenario. For instance, LSTM outperforms the other standalone models, but hybrid models generally outperform standalone models despite their longer data training time requirement. The most notable discovery is the better suitability of LSTM as a predictive model to forecast the amount of solar radiation and photovoltaic power compared with other conventional machine learning methods.