Solar Photovoltaic Power Generation Research Articles

Optimization and analysis of methanol production from CO2 and solar-driven hydrogen production: A Danish case study

This paper presents a comprehensive techno-economic analysis of the world's first large-scale commercial Power-to-X (PtX) plant in Kassø, Denmark. This innovative facility combines solar photovoltaic (PV), an electrical grid, green hydrogen production, methanol synthesis, and district heating in an integrated system. We conduct an in-depth analysis to explore optimal operating conditions, the potential for sector coupling within the power and heat sectors, and the economic feasibility of the integrated system. In particular, we study different scenarios considering changes in solar PV power generation, electricity market price, CO2 price, and methanol price to explore their impacts on the system performance. Our results show that the electrolyzer's operation, a pivotal component of the system, heavily depends on the electricity spot price as well as the methanol price. Based on the green production of methanol, a premium price of 4800 DKK/t (0.64 €/t) is considered in this study (selling price of 8400 DKK/t). The results show that in case of high electricity prices (2022 spot market) or no premium price for methanol, the optimum annual production of methanol decreases by 58% and 67%, respectively. Furthermore, we observe that the variability of solar power output significantly impacts the plant's performance and economic viability, as it supplies about 30% of the plant's power consumption. Although the results are unique to the Kassø plant, the study's techniques and insights can be applied to other comparable systems around the world. The study also highlights how crucial it is to take market, climate, and technical factors into account when developing and running integrated energy systems.

Optimal sizing of standalone hybrid renewable energy system based on reliability indicator: A case study

The economical electrification of rural settlements extensively utilizes renewable energy sources. In recent years, the deployment of solar photovoltaic, wind turbine, and biomass gasifier-based power generation technologies for electricity accessibility in remote regions has received greater prominence. This paper presents an optimal component design of a hybrid solar PV-wind and battery system along with a biomass gasifier to provide continuous electricity for rural communities of Uttarakhand, India. In this study, a recently developed population-based giza pyramids construction (GPC) methodology is applied to determine the optimal component sizing. The findings of the GPC method are contrasted with the particle swarm optimization (PSO) methodology to assess the effectiveness of the proposed method. The annualized system cost and levelized cost of energy of the hybrid renewable energy system have been minimized subject to technical reliability indicators such as loss of power supply probability and renewable fraction.Moreover, a systematic exploration of the system has been conducted to assess its optimal feasibility across different values of power loss probability ranging from (0% to 4%). The simulation indicates that the proposed method adeptly identifies globally optimal values, leading to a $177 decrease in annual cost and 8% reduction in average simulation time compared to PSO. The research reveals that the balanced point (relative attainment), where system reliability and cost-effectiveness intersect optimally, is achieved at a 3% power loss level, resulting in the most significant cost reduction of $199 compared to other probability levels.

Analysis of the Problems and Reasons for the Development of Suzhou Hydrogen Energy Industry and Industrial Policies

In recent years, although there have been some policy plans related to hydrogen energy development in China, a complete fiscal policy system has not yet been established. In policies related to hydrogen energy, we cannot keep up with the times. Only some policies are specifically targeted at solar photovoltaic and wind power generation, and some policies are even temporary. These fiscal policies are severely lagging and lack uniformity, which not only weakens the overall effect of the money supply, but also to some extent hinders the healthy and rapid development of the hydrogen energy industry. In addition, the national development plan, including national and local plans, cannot be well connected, resulting in some policies not forming strong support for hydrogen energy. In these industrial plans, production capacity targets account for the majority, but there is a lack of refinement of utilization targets and little mention of the development balance of the industrial chain.

Quantifying the air pollution impacts on solar photovoltaic capacity factors and potential benefits of pollution control for the solar sector in China

Solar photovoltaic (PV) plays a crucial role in China's energy transition. However, air pollution diminishes solar radiation resources, thereby reducing PV power generation efficiency. This study aims to quantify the impacts of air pollution on PV capacity factors in China while emphasizing the geographically specific potential benefits of improved air quality for the future PV sector. Using a PV power generation evaluation model, this study estimated solar PV capacity factors from 1961 to 2016 under both all-sky and clear-sky scenarios. Also, the spatiotemporal patterns of air pollution-induced capacity factor changes were analyzed. The results indicate that the all-sky and clear-sky PV capacity factors showed consistent annual anomalies, suggesting that air pollution due to aerosol emissions drove PV capacity factor temporal evolutions and trends in China. From 1961 to 1990, the national average clear-sky PV capacity factors for fixed modules with optimal tilt angle showed a significant decreasing trend of −0.0053 per decade, whereas from 1990 to 2016, an upward trend of 0.0030 per decade was observed. Compared with fixed modules, tracking systems suffered from greater productivity losses due to air pollution. In comparison to 1961–1965 averages, the provincial PV capacity factors for 2012–2016 decreased by 0.48–13.54%, 1.15–11.40%, 1.06–14.83%, and 1.31–16.51% for fixed modules with optimal tilt angle, horizontal fixed, one-axis horizontal tracking, and two-axis tracking modules, respectively, with decreases of 7–17% in the central and southeast. Furthermore, according to the provincial PV installation targets projected in China's 14th Five-Year Plan, national solar PV power generation was expected to increase by 81.333 TWh to 1069.997 TWh in 2025 with average PV capacity factors for 1961–1965, compared to 2012–2016 averages. In a scenario of keeping grid parity, additional power generation would offer an economic benefit of approximately 30.102 billion CNY.

Enhancement in efficiency of solar photovoltaic power generation with the assistance of PVC/TiO2 reflective composite applied for double-sided power generation

Solar photovoltaic power generation is a productive and environmentally friendly technique. The results of objective evaluations show that double-sided power generation is more efficient than single-sided power generation, with a possible increase of 5 %–30 %. Hence, it is necessary to identify a composite that reflects the exact sunlight waveband (300–1100 nm) onto the backside of photovoltaic panels used for double-sided power generation. Herein, two different crystalline types of titanium dioxide (TiO2), rutile (R–TiO2) and anatase (A-TiO2), were combined with plasticized polyvinyl chloride (PVC) to create composites. A comparative analysis was conducted with other commonly utilized reflective fillers, such as barium sulfate (BaSO4) and magnesium hydroxide (Mg(OH)2). As a result, the R–TiO2 was identified as the most appropriate substance to be blended with PVC for the production of PVC/R–TiO2 composite. As the quantity of R–TiO2 increased from 0 to 100 phr, reflectance in the distinctive waveband of 300–1100 nm of the PVC/R–TiO2 rose from 5.30 % to 82.97 %. Moreover, an improvement in the thermal conductivity of PVC/R–TiO2 sample was observed, which increased by 59.2 % from 0.179 W m−1 K−1 to 0.285 W m−1 K−1, indicating a positive effect on heat transfer. The rheological measurement showed that the amount of reflective filler was inversely proportional to the compatibility of the reflective filler with plasticized PVC in the overall composite system, whereas the thermogravimetric analysis indicated that the thermal stability of the composites improved as the number of reflective fillers increased. Substantially, PVC/R–TiO2 composites exhibit better performance in enhancing the power generation efficiency of solar photovoltaic panels.

Are Regions Conducive to Photovoltaic Power Generation Demonstrating Significant Potential for Harnessing Solar Energy via Photovoltaic Systems?

To achieve the goals of carbon peak and carbon neutrality, Xinjiang, as an autonomous region in China with large energy reserves, should adjust its energy development and vigorously develop new energy sources, such as photovoltaic (PV) power. This study utilized data spatiotemporal variation in solar radiation from 1984 to 2016 to verify that Xinjiang is suitable for the development of PV power generation. Then, the averages of the solar radiation, sunshine duration, and other data in the period after 2000 were used to assess the suitability of Xinjiang, based on spatial principal component analysis (SPCA). Finally, the theoretical power generation potential, fossil fuel reduction, and CO2 emissions reduction were estimated. The results are as follows: (1) In terms of temporal variation, the solar radiation in Xinjiang decreased (1984–2002), increased (2002–2009), and decreased again (2009–2016), but the fluctuations were not statistically significant. In terms of spatial distribution, the Kunlun Mountains in southern Xinjiang had the highest solar radiation during the span of the study period. Hami and Turpan, in eastern Xinjiang, had sufficiently high and stable solar radiation. (2) The area in Xinjiang classed as highly suitable for solar PV power generation is about 87,837 km2, which is mainly concentrated in eastern Xinjiang. (3) In the situation where the construction of PV power plants in Xinjiang is fully developed, the theoretical potential of annual solar PV power generation in Xinjiang is approximately 8.57 × 106 GWh. This is equivalent to 2.59 × 109 tce of coal. Furthermore, 6.58 × 109 t of CO2 emissions can be reduced. PV power generation potential is approximately 27 times the energy consumption of Xinjiang in 2020. Through the suitability assessment and calculations, we found that Xinjiang has significant potential for PV systems.

A comparative study on the combination of life cycle assessment and ecological footprints: solar photovoltaic power generation vs. coal power generation in Ningxia

In China, where energy activities, predominantly driven by fossil fuel combustion, account for nearly 90% of the country’s greenhouse gas (GHG) emissions and coal power alone contributes over 40%, the shift towards carbon neutrality is a critical national ambition. This study conducts a comprehensive comparison of the environmental impacts of solar photovoltaic power generation (SPPG) and coal power, employing both life cycle assessment and ecological footprint analysis. We meticulously analyze the complete lifecycle of SPPG, pinpointing key stages of GHG emissions, and offer nuanced, localized policy recommendations. Our findings indicate that a 1 kWp SPPG module emits 1,601.18 kg of GHGs over its lifespan, equating to 1.35 kg/kW·h per unit of electricity produced—substantially lower than the 4.81 kg/kW·h emitted by coal power, thus highlighting the latter’s heightened environmental detriment. Additionally, this study assesses the ecological footprint of both energy sources in Ningxia. SPPG emerges with an ecological surplus, showcasing a per capita footprint of 0.0342 hm2, compatible with Ningxia’s ecological capacity. In stark contrast, coal power exhibits a sustained ecological deficit over the past 5 years, with a growing per capita footprint of 0.6529 hm2, underscoring its unsustainability. This research provides a detailed comparative analysis of the environmental impacts of SPPG and coal power in Ningxia, offering valuable insights for energy policymakers and industry stakeholders. It underscores the urgent need for industrial restructuring towards more sustainable and renewable energy sources, aligning with China’s broader objectives of environmental preservation and achieving carbon neutrality.

Is there a stronger willingness to pay for photovoltaic power generation with high education in China?

Adoption of clean electric energy depends not only on administrative regulations, but also on public support, in particular, the public is willing to pay for environmental improvements. However, the increase of solar photovoltaic power generation willingness to pay (WTP) associated with higher education attainment and the identification of their causality has been missing. Present paper used the enactment of the Compulsory Schooling Law as an instrumental variable to solve the causal relationship between education and willingness to pay for photovoltaic power generation. The results are as follows:Heckman two-stage model and instrumental variable both confirmed that higher education has a positive impact on WTP for solar photovoltaic power generation. For each level of public education in the east, the WTP of photovoltaic power generation will increase by 7.540 CNY, 8.343 CNY and 8.343 CNY respectively, the central public will increase by 9.637 CNY, 10.775 CNY and 11.758 CNY, and the western public will increase by 12.723 CNY, 15.740 CNY and 17.993 CNY respectively. The positive influence of education level is smaller among the people who know the ladder price better, but it is bigger among the people who are male, older than 45 years old, healthier, higher income and stronger awareness of safe electricity use. The total socio-economic value of photovoltaic power generation is significantly different in eastern, central and western region China.

A Novel Deep Learning-Based Data Analysis Model for Solar Photovoltaic Power Generation and Electrical Consumption Forecasting in the Smart Power Grid

With the installation of solar panels around the world and the permanent fluctuation of climatic factors, it is, therefore, important to provide the necessary energy in the electrical network in order to satisfy the electrical demand at all times for smart grid applications. This study first presents a comprehensive and comparative review of existing deep learning methods used for smart grid applications such as solar photovoltaic (PV) generation forecasting and power consumption forecasting. In this work, electrical consumption forecasting is long term and will consider smart meter data and socioeconomic and demographic data. Photovoltaic power generation forecasting is short term by considering climatic data such as solar irradiance, temperature, and humidity. Moreover, we have proposed a novel hybrid deep learning method based on multilayer perceptron (MLP), long short-term memory (LSTM), and genetic algorithm (GA). We then simulated all the deep learning methods on a climate and electricity consumption dataset for the city of Douala. Electrical consumption data are collected from smart meters installed at consumers in Douala. Climate data are collected at the climate management center in the city of Douala. The results obtained show the outperformance of the proposed optimized method based on deep learning in the both electrical consumption and PV power generation forecasting and its superiority compared to basic methods of deep learning such as support vector machine (SVM), MLP, recurrent neural network (RNN), and random forest algorithm (RFA).

Soil bacterial community in a photovoltaic system adopted different survival strategies to cope with small-scale light stress under different vegetation restoration modes.

Solar photovoltaic (PV) power generation is a major carbon reduction technology that is rapidly developing worldwide. However, the impact of PV plant construction on subsurface microecosystems is currently understudied. We conducted a systematic investigation into the effects of small-scale light stress caused by shading of PV panels and sampling depth on the composition, diversity, survival strategy, and key driving factors of soil bacterial communities (SBCs) under two vegetation restoration modes, i.e., Euryops pectinatus (EP) and Loropetalum chinense var. rubrum (LC). The study revealed that light stress had a greater impact on rare species with relative abundances below 0.01% than on high-abundance species, regardless of the vegetation restoration pattern. Additionally, PV shadowing increased SBCs' biomass by 20-30% but had varying negative effects on the numbers of Operational Taxonomic Unit (OTU), Shannon diversity, abundance-based coverage estimator (ACE), and Chao1 richness index. Co-occurrence and correlation network analysis revealed that symbiotic relationships dominated the key SBCs in the LC sample plots, with Chloroflexi and Actinobacteriota being the most ecologically important. In contrast, competitive relationships were significantly increased in the EP sample plots, with Actinobacteriota having the most ecological importance. In the EP sample plot, SBCs were found to be more tightly linked and had more stable ecological networks. This suggests that EP is more conducive to the stability and health of underground ecosystems in vulnerable areas when compared with LC. These findings offer new insights into the effects of small-scale light stress on subsurface microorganisms under different vegetation restoration patterns. Moreover, they may provide a reference for optimizing ecological restoration patterns in fragile areas.

Predictive Energy Management of a Building-Integrated Microgrid: A Case Study

The efficient integration of distributed energy resources (DERs) in buildings is a challenge that can be addressed through the deployment of multienergy microgrids (MGs). In this context, the Interreg SUDOE project IMPROVEMENT was launched at the end of the year 2019 with the aim of developing efficient solutions allowing public buildings with critical loads to be turned into net-zero-energy buildings (nZEBs). The work presented in this paper deals with the development of a predictive energy management system (PEMS) for the management of thermal resources and users’ thermal comfort in public buildings. Optimization-based/optimization-free model predictive control (MPC) algorithms are presented and validated in simulations using data collected in a public building equipped with a multienergy MG. Models of the thermal MG components were developed. The strategy currently used in the building relies on proportional–integral–derivative (PID) and rule-based (RB) controllers. The interconnection between the thermal part and the electrical part of the building-integrated MG is managed by taking advantage of the solar photovoltaic (PV) power generation surplus. The optimization-based MPC EMS has the best performance but is rather computationally expensive. The optimization-free MPC EMS is slightly less efficient but has a significantly reduced computational cost, making it the best solution for in situ implementation.

Design and Implementation of Single-Phase Grid-Connected Low-Voltage Battery Inverter for Residential Applications

Integrating residential energy storage and solar photovoltaic power generation into low-voltage distribution networks is a pathway to energy self-sufficiency. This paper elaborates on designing and implementing a 3 kW single-phase grid-connected battery inverter to integrate a 51.2-V lithium iron phosphate battery pack with a 220 V 50 Hz grid. The prototyped inverter consists of an LCL-filtered voltage source converter (VSC) and a dual active bridge (DAB) DC-DC converter, both operated at a switching frequency of 20 kHz. The VSC adopted a fast DC bus voltage control strategy with a unified current harmonic mitigation. Meanwhile, the DAB DC-DC converter employed a proportional-integral regulator to control the average battery current with a dynamic DC offset mitigation of the medium-frequency transformer’s currents embedded in the single-phase shift modulation scheme. The control schemes of the two converters were implemented on a 32-bit TMS320F280049C microcontroller in the same interrupt service routine. This work presents a synchronization technique between the switching signal generation of the two converters and the sampling of analog signals for the control system. The prototyped inverter had an efficiency better than 90% and a total harmonic distortion in the grid current smaller than 1.5% at the battery power of ±1.5 kW.

Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection

Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection

Research on optimal dispatching strategy of solar thermal-photovoltaic-wind combined power generation system

New energy photovoltaic generation of electricity and wind power have developed rapidly, and the installed capacity has been increasing, but their volatility and randomness have also caused a certain impact on the power grid. Considering that solar thermal power generation and photovoltaic power generation have natural complementary advantages, and solar thermal power generation and power output of wind power can complement each other in time., this paper proposes an optimal scheduling strategy for solar thermal-photovoltaic-wind alliance power generation system, which uses thermal storage device of the heat power station of solar energy to cope with the problem of wind and light abandonment of new energy power generation and promote the consumption level of renewable energy. The economic and stability deviations of the system before and in the launch the solar thermal power station are compared in depth and the simulation is verified in the IEEE30 node system. The results show that after the introduction of solar thermal power (CSP) station in the combined power generation system, the economy of the scientific is remarkable improvement, the wind turbine is also reduced, which realizes the full absorption of new energy.

Numerical Simulation and Mathematical Analysis of Meta Heuristic MPPT System for Solar Photovoltaic Applications Under Non-Linear Operational Conditions

As a sustainable energy source, the use of solar photovoltaic (PV) systems has significantly increased. Environmental elements, especially partial shadowing circumstances, have a considerable impact on how well solar PV systems function. In such cases, the various local maxima in the power-voltage curve make it difficult for conventional Maximum Power Point Tracking (MPPT) methods to maintain peak efficiency. Heuristic Maximum Power Point Tracking (MPPT) system for solar photovoltaic (PV) applications, employing the cuckoo search algorithm. The primary objective of the research is to enhance the efficiency and reliability of solar PV systems by optimizing the MPPT process, which is crucial for maximizing energy extraction under varying environmental conditions. The model is used to simulate the performance of the system under various environmental conditions, such as changes in temperature and irradiance levels. The simulation results are then statistically analyzed to evaluate the effectiveness of the cuckoo search algorithm in tracking the maximum power point accurately and rapidly. The algorithm demonstrates a robust ability to converge to the maximum power point efficiently, thereby enhancing the overall energy yield of the solar PV system.. The performance of the hybrid PSO-CSA MPPT algorithm in contrast to traditional MPPT techniques is assessed through simulations and tests under various shading circumstances. The findings show that the hybrid strategy regularly outperforms conventional methods by enhancing the total energy production of partially shadowed solar PV installations through faster convergence, less oscillations, and greater tracking accuracy. The proposed hybrid algorithm also demonstrates stability and flexibility in real-world settings, making it a potential option for boosting the dependability and efficiency of solar PV systems when shade is present. This study advances the field of renewable energy and prepares the path for the use of sophisticated optimization methods to the problems of solar PV power generation under changing environmental circumstances.

The Application Status and Prospects of Solar Photovoltaic Power Generation Technology in China

Solar photovoltaic power generation, as an environmentally friendly energy technology that converts sunlight into electricity, directly converts sunlight into electricity through the use of solar panels, further producing clean and environmentally friendly electricity. Through the analysis of the development status of China's solar photovoltaic power generation, this article discusses the development direction of China's solar photovoltaic power generation to provide reference for the healthy development of China's solar photovoltaic power generation industry.

Experimental investigation of electromagnetic interference impact on phase change material coated solar photovoltaic panel

ABSTRACT High Voltage Transmission Line Electromagnetic Field’s (HVTL-EMF) impact on solar PV performance is analyzed in the proposed work. Depending on HV-EMF, the electrical characteristics and conversion process of PhotoVoltaic (PV) panels are analyzed. Electromagnetic (EM) field from HV lines has a partially positive and somewhat negative impact on solar PV. When absorption probability is low, one photon and one phonon are required. Phonons are vibrational energy units. A solar PV cell made of Silicon (Si) semiconductor material requires phonons to have high conversion efficiency and electric field from HV transmission line induces phonon. In addition, electric field from HV line increases the solar cell temperature (10 to 15°C) to the ambient temperature. Because of high solar PV cell temperature and high EM field, solar PV power generation is affected by increasing panel temperature. The proposed system uses unnatural Phase Change Material (PCM-Glauber salt (Na2SO4.10 H2O)) coated to the backside of solar PV to normalize the temperature. The impact of electromagnetic fields produced by HV lines on solar cells coated with PCM is validated with experimental testing results. The experiment considers a HVTL of 230kV and solar PV rating of 20 W. The experimental results are measured at various distance ranging from 12 to 22 meters between solar PV and HV transmission lines. Conversion efficiency of solar PV with PCM coating under the impact of HVTL- EMF has increased by 3%.

Green energy-sourced AI-controlled multilevel UPQC parameter selection using football game optimization

The power quality (PQ) has been significantly affected by the integration of intermittent non-conventional sources (NCS) into the local distribution system in addition to the adoption of power electronic technologies to regulate non-linear loads. This article combines the H-bridge cascade five-level unified power quality conditioner (5L-UPQC) with the wind power generation system (WPGS), solar photovoltaic power generation system (SPVGS), and battery storage system (BSS) as an effective approach to address PQ problems. The utilization of the Levenberg–Marquardt backpropagation (LMBP)-trained Artificial neural network controller (ANNC) in the UPQC is recommended for generating appropriate reference signals for the converters. This eliminates the requirement for conventional complex conversions, such as abc, dq0, and αβ. Moreover, the artificial neuro-fuzzy interface system (ANFIS) is recommended for achieving a DC-link balance. Football game optimization (FBGO) is utilized to determine the optimal shunt and series filter characteristics. The major objectives of the proposed system are to reduce the current waveform irregularities, resulting in a decrease in the total harmonic distortion (THD), an enhancement in the power factor (PF), the mitigation of supply voltage imbalances and disturbances, and the maintenance of a steady direct-current link capacitor voltage (DLCV), despite the variations in the load, solar irradiation, and wind velocity. The efficiency of the suggested strategy is assessed using four case studies that involve different loads, variable wind velocities, and source voltage balancing conditions. Based on the simulation studies and obtained results, the suggested method significantly decreases the THD to values of 2.91%, 3.63%, 3.75%, and 3.50%. Additionally, it achieves a power factor of unity, which is considerably lower compared to other multilevel schemes that use the traditional symmetrical reference frame (SRF) and instantaneous reactive power (pq) methods. This design has been executed using the MATLAB/Simulink program.

Scheme Design and Energy-Saving Optimization of Cold and Heat Energy Supply System for Substation Main Control Building in Cold Area

In the context of global climate change, the implementation of building energy conservation and carbon reduction, as well as the realization of zero-energy buildings, is a key measure to cope with climate change and resource depletion. A substation is an indispensable building in the process of urbanization construction. However, in existing cold areas, the heating form of substations generally adopts electric heating, which consumes a large amount of energy. This paper optimizes the existing HVAC form of substations through the rational utilization of surrounding environmental resources and puts forward reasonable building energy-saving and carbon-reduction methods. It demonstrates the feasibility of combining solar photovoltaic power generation systems, air source heat pumps, and natural ventilation to optimize energy savings and carbon reduction in the main control building of a substation in a cold area. The computational fluid dynamics (CFD) method is used to demonstrate the feasibility of natural ventilation during the summer and transition seasons. The data indicate that the installation of a solar photovoltaic power generation system results in an average annual power generation of 18.75 MWh. Additionally, using an air source heat pump can save 44.5% of electricity compared to electric heating. When both a solar photovoltaic power generation system and an air source heat pump are used to provide a building with cold and heat sources, the annual emissions of CO2 can be reduced by 4.90 tons compared to a traditional electric heating system.

The influence of training datasets on LSTM-based irradiance prediction

In solar photovoltaic power generation, the prediction of solar irradiance is essential for minimizing energy costs and ensuring the provision of high-quality electricity. Deep learning models have recently gained popularity in the field, as numerous scholars have successfully employed them to predict solar irradiance. In line with this, this paper proposes three distinct methods for dividing the training dataset. Subsequently, these methods are employed in predicting solar irradiance using the LSTM-based model. Furthermore, an error analysis of the prediction results is conducted for each of the three models. The optimal training dataset division method is determined and proposed based on a comparison of the sizes of the three models using six error evaluation indexes.