Photovoltaic development prediction method and device based on full life cycle regression analysis

Abstract

The invention relates to a photovoltaic development prediction method and device based on full life cycle regression analysis. The method comprises the following steps: collecting and taking trade barrier tax quantitative data of each country, policy preferential subsidy quantitative data and industrial chain correlation data of each country and the country as core independent variables; taking the economic scale of each country, the environmental adjustment tax of each country, the leveling and leveling cost of kilowatt-hour of each country and the photovoltaic module single-watt quotation of each country as control variables; carrying out regression analysis by taking the national photovoltaic export scale proportion in the world as a dependent variable to obtain an international photovoltaic trade model; and solving an international photovoltaic trade model according to photovoltaic historical trade import and export data to obtain prediction data of a national photovoltaic export scale proportion, and performing bidirectional comparison with photovoltaic trade customs value data to iteratively optimize model parameters. Compared with the prior art, the method can accurately predict the development change of photovoltaic power generation, and provides a powerful analysis tool and decision basis for the development of the photovoltaic industry of each country in international trade.

Description

Technical Field

[0001] This invention relates to the field of forecasting and planning technology for the photovoltaic industry, and in particular to a method and apparatus for forecasting photovoltaic development based on full life cycle regression analysis. Background Technology

[0002] Against the backdrop of global energy transition and the rapid development of the photovoltaic industry, the international trade environment is becoming increasingly complex, and competition among photovoltaic companies worldwide is intensifying. On the one hand, with rising environmental awareness and growing demand for clean energy, the photovoltaic market is expanding, and many countries are actively developing their photovoltaic industries, leading to a diversification of the global photovoltaic product supply structure. On the other hand, the rise of trade protectionism and the frequent introduction of trade policies and industry support measures by various countries are having a significant impact on the import and export of photovoltaic products.

[0003] Against this backdrop, traditional trade analysis methods are insufficient to comprehensively and accurately measure the position and competitiveness of a country's photovoltaic industry in international trade. Previous studies may have focused only on a single factor, such as the impact of tariffs on trade, or analyzed only from the perspective of macroeconomic aggregates, lacking models that comprehensively consider the impact of multiple factors such as trade protectionism, policy implementation details, industrial linkages, and cost prices on photovoltaic trade.

[0004] The invention disclosed in CN116307285B, authorized by patent announcement number CN116307285B, is a new energy development prediction device and method. The device includes: a parameter prediction module for predicting key characteristic parameters of new energy development and inputting the prediction results of these key characteristic parameters as parameters into a system dynamics module; a power system production simulation module for generating wind power utilization rate functions and photovoltaic power generation utilization rate functions through multiple linear regression based on various power generation, transmission, and consumption technical and economic characteristic parameters and key-level annual production simulation results; and a system dynamics module including a wind power development simulation system and a photovoltaic power generation development simulation system. The wind power development simulation system is used to perform wind power development simulation based on the wind power utilization rate function according to the prediction results of the key characteristic parameters; and the photovoltaic power generation development simulation system is used to perform photovoltaic power generation simulation based on the photovoltaic power generation utilization rate function according to the prediction results of the key characteristic parameters.

[0005] The scheme makes predictions based on photovoltaic power generation capacity and wind power utilization rate separately, which cannot accurately predict the development and changes of photovoltaic power generation. Summary of the Invention

[0006] The purpose of this invention is to overcome the shortcomings of existing technologies, such as the inability of traditional trade analysis methods to comprehensively and accurately measure the status and competitiveness of a country's photovoltaic industry in international trade and the inability to accurately predict the development and changes of photovoltaic power generation, and to provide a photovoltaic development prediction method and device based on full life cycle regression analysis.

[0007] The objective of this invention can be achieved through the following technical solutions:

[0008] A photovoltaic development forecasting method based on full life-cycle regression analysis includes the following steps:

[0009] We obtained historical import and export data of photovoltaic trade, and collected and used quantitative data on trade barriers and tariffs, policy incentives and subsidies, and the degree of industrial chain correlation between each country and our country as core independent variables; we used the economic scale of each country, environmental adjustment tariffs, levelized cost of electricity, and photovoltaic module price per watt as control variables; and we used our country's proportion in the world photovoltaic export scale as the dependent variable.

[0010] A regression analysis was conducted based on the identified core independent variables, control variables, and dependent variables to obtain the international photovoltaic trade model.

[0011] Based on historical photovoltaic trade import and export data, the international photovoltaic trade model is solved to obtain predicted data on the proportion of the country's photovoltaic exports. This data is then compared bidirectionally with customs value data of photovoltaic trade to iteratively optimize the parameters of the international photovoltaic trade model.

[0012] Furthermore, the calculation expression for the international photovoltaic trade model is as follows:

[0013] pvlq it =α1trade it +α2policy it +α3relate it +β1GDP it +β2TAR it +β3LCOE it +β4PWP it +ε

[0014] In the formula, pvlq it The percentage of China's photovoltaic exports in the world in year t, trade it For the quantitative data of trade barriers and tariffs in country i in year t, policy it For the quantitative data of policy incentives and subsidies in country i in year t, relate it The data represents the degree of industrial chain correlation between country i and other countries in year t, with α1, α2, and α3 as the coefficients of the core independent variables, and GDP. it For the economic scale of country i in year t, TAR it For the t-th year of the environmental adjustment tariff in country i, LCOE it For the levelized cost of electricity in country i in year t, PWP it Let represent the price per watt of photovoltaic modules in country i in year t, β1, β2, β3, and β4 be the coefficients of the control variables, ε be the random error term, subscript i represent country i, and subscript t represent year t.

[0015] Furthermore, the formula for calculating the proportion of the country's global photovoltaic export volume is as follows:

[0016]

[0017] In the formula, pvlq it The percentage of China's photovoltaic exports in the world in year t, PV it Let ∑pv represent the photovoltaic export volume of country i in year t, and exit represent the total export volume of all products of country i in year t. it Let ∑ex be the photovoltaic export volume of all countries in year t. it Let t represent the total export volume of all products from all countries in year t.

[0018] Furthermore, the quantification model employs the least squares method for regression analysis.

[0019] Furthermore, an environmental cost coefficient is introduced into the calculation of the environmental adjustment tariff, and the corresponding calculation expression is as follows:

[0020] TAR it =T0+α·C env

[0021] In the formula, TAR it For country i, the environmental adjustment tariff in year t is T0 as the base tariff, C env Here, α is the environmental cost coefficient, and α is an adjustment parameter used to balance the impact of environmental costs on tariffs.

[0022] Furthermore, if α > 0, it means that increased environmental costs will lead to increased tariffs;

[0023] If α < 0, then increased environmental costs will lead to a reduction in tariffs.

[0024] Furthermore, the calculation expression for the Levelized Cost of Electricity (LCOE) is as follows:

[0025]

[0026] In the formula, L1 is the net present value of the life cycle cost, which includes the initial investment cost, operation and maintenance cost, fuel cost and disposal cost when the project is decommissioned, and L2 is the total power generation, which is the total amount of electricity that the project is expected to generate during its entire life cycle.

[0027] Furthermore, the method also includes: using real-time transaction data to calculate the predicted proportion of the country's photovoltaic export scale through a trained international photovoltaic trade model, thereby analyzing the specialization and concentration parameters of the country's photovoltaic industry.

[0028] Furthermore, the method also includes: making decisions on the development scale of the photovoltaic industry in international trade based on forecast data of the proportion of domestic photovoltaic exports.

[0029] The present invention also provides a photovoltaic development forecasting device based on full life cycle regression analysis, including a memory and a processor. The memory stores a computer program, and the processor calls the computer program to execute the steps of the method described above.

[0030] Compared with the prior art, the present invention has the following advantages:

[0031] (1) In order to comprehensively and accurately measure the status and competitiveness of the country's photovoltaic industry in international trade, this invention integrates core independent variables (trade protectionism, policy situation, and correlation with China's photovoltaic industry) as the research focus, sets control variables (economic scale of each country, import tariffs, levelized cost of electricity, and price per watt of photovoltaic modules) as interference exclusion variables, and uses scientific econometric methods (the proportion of the country's global photovoltaic export scale and the least squares method to estimate the regression coefficient) to construct a model that can more accurately reflect the location quotient of international photovoltaic trade export volume, thereby providing a powerful analytical tool and decision-making basis for the development of the photovoltaic industry in international trade of various countries.

[0032] (2) This invention incorporates environmentally adjusted tariffs, adjusting the basic tariffs based on environmental cost coefficients. Compared to traditional inter-country photovoltaic trade models that only focus on correlation analysis at the national level, this study further refines the granularity of correlations based on a full life-cycle analysis. Using granular data at the manufacturer level throughout the entire photovoltaic industry chain lifecycle facilitates the analysis of collaborative relationships between upstream and downstream sectors, and accurately pinpoints the distribution and density of pollutant and greenhouse gas emissions. It helps to grasp new trends and variables in industry changes from a supply chain perspective, overcoming the limitations of traditional trade model analysis that relies on a single trade value. By introducing environmental cost parameters, it allows for comparative analysis of changes in the added value of advanced production capacity and the elimination of outdated production capacity.

[0033] (3) This invention selects the proportion of a country's global photovoltaic exports as the dependent variable, which can accurately measure the degree of specialization and relative concentration of the photovoltaic industry in international trade of various countries. This helps governments to formulate targeted photovoltaic industry development policies. When facing foreign trade protectionism, they can adjust export promotion policies or adopt trade negotiation strategies in a timely manner based on the model results. For enterprises, it can guide their market layout decisions, and choose more favorable export destinations or investment and factory locations based on the correlation between each country and the international photovoltaic industry, as well as market tariffs, costs, etc., thereby promoting the rational layout and healthy development of the photovoltaic industry in the international market of various countries.

[0034] (4) The parameter settings of this model take into account the research on photovoltaic supply and demand structure analysis combined with economic analysis (price, cost, tariff, subsidy), technical framework (efficiency, specifications), and the entire life cycle perspective of photovoltaic products. It takes into account all aspects of photovoltaic products, such as raw material and equipment supply, production and processing, and recycling after retirement, especially the comprehensive impact assessment of photovoltaic products on the natural environment. Attached Figure Description

[0035] Figure 1 This is a flowchart illustrating a photovoltaic development prediction method based on full life cycle regression analysis provided in an embodiment of the present invention.

[0036] Figure 2 This is a topological diagram illustrating the source of independent variable parameter data provided in an embodiment of the present invention;

[0037] Figure 3 This is a flowchart illustrating the operational logic of a photovoltaic development prediction method based on full life-cycle regression analysis provided in this embodiment of the invention. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0039] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0040] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0041] Example 1

[0042] like Figure 1 As shown, this embodiment provides a photovoltaic development forecasting method based on full life cycle regression analysis, including the following steps:

[0043] S1: Obtain historical import and export data of photovoltaic trade, collect and use quantitative data on trade barriers and tariffs of various countries, quantitative data on policy preferences and subsidies, and data on the correlation between various countries and the domestic industrial chain as core independent variables; use the economic scale of various countries, environmental adjustment tariffs of various countries, levelized cost of electricity of various countries, and the price per watt of photovoltaic modules of various countries as control variables; use the proportion of the country's global photovoltaic export scale as the dependent variable.

[0044] Specifically, based on historical import and export data of photovoltaic (PV) trade, core independent variables are collected: quantitative data on trade barriers and tariffs; quantitative data on policy incentives and subsidies; and data on the correlation with the domestic industrial chain. Control variables are set: the economic scale of market entities, import tariffs, levelized cost of electricity (LCOE), and the price per watt of PV modules. A life-cycle assessment (LCA) parameter framework is constructed, including quantitative data on environmental impact assessment and carbon footprint data. A comprehensive tariff is obtained by adjusting the tariff levels of market entities in conjunction with the PV environmental cost coefficient. Parameters are solved using bilateral trade volume as the dependent variable.

[0045] S2: Based on the identified core independent variables, control variables, and dependent variables, a regression analysis was conducted to obtain the international photovoltaic trade model;

[0046] That is, based on the variables defined above, a quantitative model is constructed. Combining the location quotient formula, regression analysis is performed to determine the proportional relationship of the coefficients of the independent variables, with the location quotient parameter (the proportion of the country's photovoltaic export scale in the world) as the dependent variable. An international photovoltaic trade model is then constructed to calculate parameters that measure the degree of specialization and relative concentration of the photovoltaic industry in various countries in international trade.

[0047] S3: Based on historical photovoltaic trade import and export data, solve the international photovoltaic trade model to obtain the predicted data of the proportion of the country's photovoltaic export scale, and compare it with the customs value data of photovoltaic trade to iteratively optimize the parameters of the international photovoltaic trade model;

[0048] That is, a fitting and correction operation is performed based on the constructed model. The model parameters are accurately solved using real-time transaction data to determine the impact of location quotient parameters on international photovoltaic trade. The results obtained from the above model are compared bidirectionally with customs value data, and the model parameters are continuously iterated and optimized. These analytical results will provide important basis for strategic decision-making in the photovoltaic industry and help relevant countries formulate scientific and reasonable development strategies in a complex and ever-changing international trade environment.

[0049] The following is a detailed description of each step:

[0050] In step S1, the process of acquiring photovoltaic data is as follows:

[0051] Based on historical import and export data of photovoltaic trade, core independent variables (quantified data of trade barriers and tariffs, quantitative data of policy incentives and subsidies, and data on the correlation with China's industrial chain) and control variables (economic scale of market entities, import tariffs, levelized cost of electricity, and price per watt of photovoltaic modules, etc.) are determined, and a full life cycle evaluation parameter framework (quantified data of environmental impact assessment and carbon footprint data) is constructed, with bilateral trade volume as the dependent variable to solve for the parameters.

[0052] The independent variables collected in this invention cover multiple aspects of data, including trade protectionism, policy implementation, industrial linkages, GDP, trade tariffs, cost per kilowatt-hour, and module prices, comprehensively reflecting the relevant factors of international photovoltaic trade.

[0053] like Figure 2 As shown, the source of the independent variable data is:

[0054] Data on trade protectionism comes from: government websites, international organization websites, and academic databases;

[0055] Data on policy implementation comes from: news media, government statistical agencies, and professional research institutions;

[0056] The data on the relevance of the photovoltaic industry comes from: photovoltaic seminars, financial media reports, and customs value ratios;

[0057] GDP data comes from: reports from international organizations, government statistical departments, and professional economic research institutions;

[0058] Data on environmental adjustment tariffs comes from: documents from international organizations, corporate announcements and financial reports, and reports from industry associations and research institutions;

[0059] Levelized cost of electricity (LCOE) data are sourced from: the International Renewable Energy Agency, academic databases, corporate financial reports, and announcements.

[0060] The price data per watt for photovoltaic modules comes from: industry professional websites, bidding and procurement platforms, and research reports from financial and securities institutions.

[0061] In step S2, the process of constructing the international photovoltaic trade model is as follows:

[0062] By combining the location quotient formula and regression analysis, the proportional relationship of the coefficients of the independent variables is determined, and the location quotient parameter is the dependent variable. An international photovoltaic trade model is constructed to calculate the parameters that measure the degree of specialization and relative concentration of the photovoltaic industry in various countries in international trade.

[0063] The expression for the location quotient is:

[0064]

[0065] In the formula, pvlq itThe percentage of China's photovoltaic exports in the world in year t, PV it Let ∑pv represent the photovoltaic export volume of country i in year t, and exit represent the total export volume of all products of country i in year t. it Let ∑ be the photovoltaic export volume of all countries in year t. exit Let t represent the total export volume of all products from all countries in year t.

[0066] This model employs the location quotient formula to calculate the location quotient of China's photovoltaic (PV) export volume, accurately measuring the degree of specialization and relative concentration of the PV industry in international trade across different countries. This helps governments formulate targeted PV industry development policies and adjust export promotion policies or trade negotiation strategies in a timely manner when facing foreign trade protectionism. For enterprises, it guides their market layout decisions, enabling them to choose more favorable export destinations or investment locations based on the correlation between each country and the international PV industry, as well as market tariffs and costs, thus promoting the rational layout and healthy development of the PV industry in the international market.

[0067] The regression analysis expression is:

[0068] y = β0 + β1x + β2x + ε

[0069] Where y is the dependent variable, x is the independent variable, β0 is the intercept, β1 is the regression coefficient, and ε is the random error term.

[0070] The least squares method is used to estimate the regression coefficients:

[0071]

[0072] Where n is the number of samples, and These are the sample means of x and y, respectively.

[0073] The calculation expression for the international photovoltaic trade model is as follows:

[0074] pvlq it =α1trade it +α2policy it +α3relate it +β1GDP it +β2TAR it +β3LCOE it +β4PWP it +ε

[0075] In the formula, the core independent variables are trade protectionism in each country, policy implemented by each country's government, and correlation between each country and China's photovoltaic industry; the control variables are GDP of each country, environmental adjustment tariff (Tar) of each country, levelized cost of electricity (LCOE) of each country, and price per watt (PWP) of each country's photovoltaic modules; ε is the random error term, α1, α2, and α3 are the coefficients of the core independent variables, and β1, β2, β3, and β4 are the coefficients of the control variables. The subscript i represents the i-th country, and the subscript t represents the t-th year.

[0076] The specific environmental adjustment tariffs adopted by various countries are as follows: an environmental cost coefficient is introduced into the tariff calculation formula. The basic tariff is T0, and the environmental cost coefficient is C. env The adjusted tariff (TAR) it It can be represented as:

[0077] TAR it =T0+α·C env

[0078] Here, α is an adjustment parameter used to balance the impact of environmental costs on tariffs. If α > 0, an increase in environmental costs will lead to an increase in tariffs; if α < 0, an increase in environmental costs will lead to a decrease in tariffs.

[0079] The international photovoltaic trade model clearly defines the reference indicators for environmental factors in the photovoltaic production process and how the increased costs are transferred to the tariffs of various countries. That is, the model incorporates a full life cycle analysis, which includes specific values ​​for various environmental costs, such as energy consumption, chemical use, and waste disposal.

[0080] This model adjusts the setting of environmental tariffs. Compared to traditional inter-country photovoltaic trade models that only analyze correlations at the national level, this study further refines the granularity of correlations based on a full life-cycle analysis. Using granular data at the manufacturer level throughout the entire photovoltaic industry chain lifecycle, it is beneficial for analyzing the synergistic relationships between upstream and downstream industries, and accurately locating the distribution and density of pollutant and greenhouse gas emissions. It helps to grasp new trends and variables in industry changes from a supply chain perspective, overcoming the limitations of traditional trade models that rely on a single trade value. By introducing environmental cost parameters, it compares and analyzes changes in the added value of advanced production capacity and the elimination of outdated production capacity.

[0081] The formula for calculating LCOE (Low Cost of Electricity) is:

[0082]

[0083] In the formula, L1 is the net present value of life cycle cost, which includes the initial investment cost of the project, operation and maintenance costs, fuel costs (for power generation methods that require fuel), and disposal costs when the project is decommissioned. L2 is the total power generation, which is the total amount of electricity that the project is expected to generate during its entire life cycle.

[0084] The parameter settings of this model take into account the analysis of photovoltaic supply and demand structure, combined with economic analysis (price, cost, tariffs, subsidies), technological framework (efficiency, specifications), and the entire life cycle perspective of photovoltaic products. It considers all aspects of photovoltaic products, including raw material and equipment supply, manufacturing and processing, and post-retirement recycling, especially the comprehensive environmental impact assessment of photovoltaic products.

[0085] In step S3, the process of performing fitting correction operations based on the constructed model is as follows:

[0086] By accurately solving the model parameters using real-time transaction data, the impact of location quotient parameters on international photovoltaic trade is determined. The results obtained from this model are then compared bidirectionally with customs value data, and the model parameters are continuously iterated and optimized. These analytical results will provide important basis for strategic decision-making in the photovoltaic industry and help relevant countries formulate scientific and reasonable development strategies in a complex and ever-changing international trade environment.

[0087] The operating logic of this invention is as follows: Figure 3 As shown, this model first collects core independent variables such as trade barriers and tariffs based on historical photovoltaic trade import and export data, sets control variables such as economic scale, and constructs a full life-cycle evaluation parameter framework, solving for parameters with bilateral trade volume as the dependent variable. Then, based on the above variables, a quantitative model is constructed. Combining the location quotient formula and regression analysis, the relationship between independent variable coefficients is determined, and an international photovoltaic trade model is built to calculate the specialization and concentration parameters of the photovoltaic industry in various countries. Finally, the constructed model is fitted and corrected, and parameters are accurately solved using real-time transaction data. The parameters are iteratively optimized through bidirectional comparison with customs value data, providing important basis for strategic decision-making in the photovoltaic industry. The entire model operates logically, from data collection and variable setting to model construction and parameter calculation, and then to model correction and application, each step is interconnected, aiming to provide scientific analysis and decision support for the development of the photovoltaic industry in international trade. The construction of the quantitative model lays the foundation for scientific analysis, while continuous fitting and correction ensure the model's timeliness and accuracy. The combination of these two factors ultimately makes the model's output, such as the specialization and concentration parameters of the photovoltaic industry in various countries, as well as the impact of key factors on the trade pattern, highly credible and practical. This provides strong data support and scientific basis for all participants in the photovoltaic industry chain, namely enterprises, governments, and research institutions, to make accurate strategic decisions in a complex and ever-changing international environment.

[0088] Example 2

[0089] This embodiment provides a photovoltaic development forecasting device based on full life cycle regression analysis, including a memory and a processor. The memory stores a computer program, and the processor calls the computer program to execute the steps of a photovoltaic development forecasting method based on full life cycle regression analysis as described in Embodiment 1.

[0090] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1.A photovoltaic development prediction method based on a full life cycle regression analysis, characterized by, The method comprises the following steps: Obtaining photovoltaic historical trade import and export data, collecting and quantifying data of trade barriers and tariffs, data of policy subsidies, and data of the correlation between the home country and the industry chain of each country as core independent variables; taking the economic scale of each country, the environmental adjustment tariff of each country, the levelized cost of electricity (LCOE) of each country, and the single-watt quotation of each country as control variables; and taking the proportion of the home country's photovoltaic export scale in the world as a dependent variable; Performing regression analysis according to the determined core independent variables, control variables, and dependent variables to obtain an international photovoltaic trade model; Solving the international photovoltaic trade model according to the photovoltaic historical trade import and export data to obtain prediction data of the proportion of the home country's photovoltaic export scale, and performing bidirectional comparison with photovoltaic trade customs value data to iteratively optimize the parameters of the international photovoltaic trade model. 2.The photovoltaic development prediction method based on the full life cycle regression analysis of claim 1, wherein, The calculation expression of the international photovoltaic trade model is: pvlq it = a1trade it + a2policy it + a3relate it + b1GDP it + b2TAR it + b3LCOE it + b4PWP it + e where pvlq it is the i country's t year's proportion of the world's photovoltaic export scale, trade it is the i country's t year's trade barrier tariff quantification data, policy it is the i country's t year's policy preferential subsidy quantification data, relate it is the i country's t year's correlation data with each industry chain, α1, α2 and α3 are the coefficients of the core independent variables, GDP it is the i country's t year's economic scale, TAR it is the i country's t year's environmental adjustment tariff, LCOE it is the i country's t year's levelized cost of electricity, PWP it is the i country's t year's photovoltaic module single watt quotation, β1, β2, β3 and β4 are the coefficients of the control variables, ε is a random error term, subscript i is the i country, and subscript t is the t year. 3.The photovoltaic development prediction method based on the full life cycle regression analysis of claim 1, wherein, The calculation expression of the proportion of the home country's photovoltaic export scale in the world is: where pvlq it is the share of world PV export size of country i in year t, pv it is the PV export of country i in year t, exit is the total export of country i in year t, ∑pv it is the total PV export of all countries in year t, ∑ex it is the total export of all countries in year t. 4.The photovoltaic development prediction method based on the full life cycle regression analysis of claim 1, wherein, The least square method is used for regression analysis of the quantitative model. 5.The photovoltaic development prediction method based on the full life cycle regression analysis of claim 1, wherein, An environmental cost coefficient is introduced in the calculation process of the environmental adjustment tariff, and the corresponding calculation expression is: TAR it = T0+ a · C env In the formula, TAR it is the environmental adjustment tariff of country i in year t, T0 is the basic tariff, C env is the environmental cost coefficient, and α is the adjustment parameter used to balance the impact of environmental cost on the tariff. 6.The photovoltaic development prediction method based on the full life cycle regression analysis of claim 5, wherein, If α>0, it indicates that an increase in the environmental cost will lead to an increase in the tariff. If α<0, it indicates that an increase in the environmental cost will lead to a decrease in the tariff. 7.The photovoltaic development prediction method based on the full life cycle regression analysis of claim 1, wherein, The calculation expression of the LCOE is: In the formula, L1 is the net present value of the life cycle cost, including the initial investment cost, operation and maintenance cost, fuel cost, and disposal cost when the project is decommissioned, and L2 is the total power generation, which is the total power generated by the project in its entire life cycle. 8.The photovoltaic development prediction method based on the full life cycle regression analysis of claim 1, wherein, The method further comprises: using real-time transaction data to calculate prediction data of the proportion of the home country's photovoltaic export scale by the trained international photovoltaic trade model, so as to analyze the specialization degree and concentration degree parameters of the home country's photovoltaic industry. 9.The photovoltaic development prediction method based on the full life cycle regression analysis of claim 8, wherein, The method further comprises: making a development scale decision of the photovoltaic industry in international trade according to the prediction data of the proportion of the home country's photovoltaic export scale. 10.A photovoltaic development prediction device based on a full life cycle regression analysis, characterized by, The system comprises a memory and a processor, the memory stores a computer program, and the processor invokes the computer program to execute the steps of the method according to any one of claims 1 to 9.

Images