Investment cost estimation model construction method and system of optical storage integrated station

Abstract

The invention discloses a method and a system for constructing an investment cost estimation model of a light-storage integrated station. The method comprises the following steps of: acquiring engineering quantity, equipment composition, energy storage scale, sending-out line parameters and a construction period financial structure in research data of a photovoltaic project; respectively quantifying the data into a direct current side installed capacity, an energy storage configuration proportion, a transmission project line length, a power transmission line voltage grade, a financing interest rate and a construction period; the total investment is divided into basic cost, energy storage increment cost, capitalization interest cost and outgoing line cost, and the four costs are composed of direct current side installed capacity, energy storage configuration proportion, outgoing engineering line length, power transmission line voltage grade, financing interest rate and construction period; forming an overall nonlinear prediction model based on the four costs; and early-stage investment estimation, scheme comparison and selection and power station economy evaluation of the photovoltaic project are carried out based on the overall nonlinear prediction model. According to the invention, accurate prediction of new energy projects of different scales is realized through the overall nonlinear prediction model.

Description

Technical Field

[0001] This invention belongs to the field of new energy engineering economics and project investment technology, specifically involving a method and system for constructing an investment cost estimation model for integrated photovoltaic and energy storage power stations. Background Technology

[0002] Cost prediction for new energy power generation is one of the core research directions in the field of energy engineering economics. The engineering cost structure of centralized photovoltaic, wind power, and integrated photovoltaic-storage projects is complex and significantly affected by factors such as scale, energy storage configuration, voltage level, transmission conditions, and financing environment. Traditional methods that rely on manual experience or simplified linear models are no longer sufficient to meet the actual needs of the large number, large scale, and highly differentiated structure of current new energy projects.

[0003] Currently, most scholars and engineering consulting firms in the engineering field still rely on three methods to estimate project costs: (1) analogy with historical feasibility study projects; (2) item-by-item superposition according to engineering quotas; and (3) linear regression analysis of the impact of each individual indicator on the total investment. However, the analogy method is easily affected by individual case differences and cannot adapt to the special characteristics of photovoltaic base projects, which are characterized by "huge scale, high energy storage ratio, long transmission distance, and rapid voltage level improvement". Although the quota-based evaluation method has a clear structure, the quota update is lagging and it is difficult to reflect the trend of rapid decline in the price of new energy equipment; while linear regression assumes that there is a linear relationship between variables and costs, which is inconsistent with the actual engineering laws. For example, the installed capacity has economies of scale (decreasing marginal cost), the price of energy storage is affected by the depth of configuration and grows exponentially, and there is a compound interest effect between the construction period and the financing interest rate. These are not things that can be described by linear relationships.

[0004] Although the "learning curve model" is widely used internationally to describe the decrease in unit cost brought about by the expansion of industry scale (such as the empirical patterns of CAPEX decline in photovoltaic and wind power by IRNEA and IEA), the learning curve is a top-down macro statistical model and is not specific to any particular project. Its scope of application is mainly at the global or national level.

[0005] Therefore, it is necessary to study a new energy investment cost prediction model based on engineering mechanisms, combined with nonlinear regression structure, that can simultaneously cover scale effect, energy storage expansion effect, capitalized interest effect and transmission line effect. Summary of the Invention

[0006] To address the problems in related technologies, this application provides a method and system for constructing an investment cost estimation model for integrated photovoltaic and energy storage power stations, thus solving the problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for constructing an investment cost estimation model for an integrated photovoltaic and energy storage power station, comprising the following steps: Step S1: Obtain the engineering quantities, equipment composition, energy storage scale, transmission line parameters, and construction period financial structure from the feasibility study data of the photovoltaic project; quantify the engineering quantities into DC side installed capacity; quantify the energy storage scale into energy storage configuration ratio; quantify the transmission line parameters into transmission line length and transmission line voltage level; quantify the construction period financial structure into financing interest rate and construction period. Step S2: Break down the total investment in the new energy photovoltaic project into basic cost, incremental energy storage cost, capitalized interest cost, and transmission line cost; Step S21: Calculate the basic cost based on the DC-side installed capacity; Step S22: Calculate the incremental cost of energy storage based on the energy storage configuration ratio and DC-side installed capacity; Step S23: Calculate the capitalized interest cost based on the DC-side installed capacity, financing rate, and construction period; Step S24: Calculate the cost of the transmission project based on the length of the transmission line and the voltage level of the transmission line; Step S3: Construct an overall nonlinear prediction model based on the base cost, incremental energy storage cost, capitalized interest cost, and transmission line cost; Step S4: Based on the overall nonlinear prediction model, estimate the initial investment of the photovoltaic project, compare and select schemes, and evaluate the economic efficiency of the power plant.

[0008] Furthermore, the basic cost is obtained, which is expressed as: ; In the formula, Basic cost; The unit capacity baseline cost under standardized conditions; To reflect the degree of economies of scale; This refers to the installed capacity on the DC side.

[0009] Furthermore, the energy storage cost is obtained, which is expressed as follows: ; In the formula, For incremental costs of energy storage; d is the benchmark cost coefficient for energy storage systems; d is the exponential parameter. This refers to the energy storage configuration ratio.

[0010] Furthermore, we obtain the capitalized interest cost, which is represented as: ; In the formula, Capitalized interest costs; For financing interest rate; The construction period.

[0011] Furthermore, the cost of the outgoing project is obtained, which is expressed as follows: ; In the formula, To cover the project costs; Voltage level of the transmission line; The length of the transmission line.

[0012] Furthermore, a general nonlinear prediction model is constructed, which is expressed as: .

[0013] Furthermore, the specific process for estimating the initial investment, comparing different options, and evaluating the economic viability of photovoltaic projects is as follows: The sample data includes the actual cost of the project; engineering data from existing photovoltaic and energy storage projects are selected as the sample data. The sample data is fitted using an overall nonlinear prediction model to obtain the prediction results of the overall nonlinear prediction model; the prediction results of the overall nonlinear prediction model include the cost of model prediction. Calculate the coefficient of determination between the actual cost of the project and the cost predicted by the model. When the coefficient of determination When it approaches 1; The root mean square error (RMSE) of the actual project cost and the model-predicted cost is calculated, and the RMSE is only in the tens of millions of yuan. The mean absolute percentage error (MAPE) is calculated between the actual cost of the project and the cost predicted by the model, and the MAPE is controlled within a few percentage points. When the coefficient of determination When the root mean square error (RMSE) is close to 1, the average absolute error (MAPE) is only in the tens of millions of yuan range, and the average absolute error (MAPE) is controlled within a few percentage points, the accuracy requirements for engineering investment estimation are met, and a project sample is obtained. As the number of project samples increases, the coefficients a, b, c, and d in the base cost, incremental energy storage cost, capitalized interest cost, and transmission line cost can be recalibrated. When there are enough project samples, , , , Substituting a, b, c, d, and sample data from the Xinjiang Uygur Autonomous Region into the overall nonlinear prediction model constitutes a system of equations; by solving the system of equations, coefficients with regional engineering significance are obtained; The overall nonlinear prediction model is based on the engineering significance coefficient of the adapted region, which accurately completes the early investment estimation, scheme comparison and selection and power plant economic evaluation of photovoltaic projects. Preliminary Investment Estimate: Based on the overall nonlinear prediction model, the basic cost, incremental energy storage cost, capitalized interest cost, and transmission line cost are superimposed to obtain the preliminary investment estimate; Scheme comparison: The DC side installed capacity (Cap), energy storage configuration ratio (ESS), engineering line length (Dist), and transmission line voltage level are substituted into the overall nonlinear prediction model to calculate the cost. The cost calculation scheme is selected by combining the comparison and rationality of photovoltaic and energy storage projects. Power plant economic evaluation: Based on the cost predicted by the model and combined with the expected power generation revenue of the photovoltaic and energy storage project, the economic feasibility of the photovoltaic and energy storage project is judged.

[0014] A system for constructing an investment cost estimation model for an integrated photovoltaic and energy storage power station, applied to the aforementioned method for constructing an investment cost estimation model for an integrated photovoltaic and energy storage power station, includes: The data acquisition module is used to acquire the engineering quantities, equipment composition, energy storage scale, transmission line parameters, and construction period financial structure from the feasibility study data of photovoltaic projects; quantify the engineering quantities into DC side installed capacity; quantify the energy storage scale into energy storage configuration ratio; quantify the transmission line parameters into transmission line length and transmission line voltage level; and quantify the construction period financial structure into financing interest rate and construction period. The decomposition module is used to break down the total investment in a new energy photovoltaic project into basic cost, incremental energy storage cost, capitalized interest cost, and transmission line cost. The cost construction module is used to construct the basic cost based on the DC-side installed capacity. The incremental construction module is used to calculate the incremental cost of energy storage based on the energy storage configuration ratio and DC-side installed capacity. The capitalized interest construction module is used to construct the capitalized interest cost based on the DC-side installed capacity, financing rate, and construction period. The transmission project construction module is used to calculate the cost of the transmission project based on the length and voltage level of the transmission line. A predictive model is constructed based on the base cost, incremental energy storage cost, capitalized interest cost, and transmission line cost to form an overall nonlinear predictive model. The predictive evaluation model is used to estimate the initial investment of photovoltaic projects, compare different options, and evaluate the economic efficiency of power plants based on an overall nonlinear predictive model.

[0015] Compared with existing technologies, the present invention has the following advantages: (1) This invention, through its overall nonlinear prediction model, can not only handle new energy projects of different scales, but also objectively and accurately predict investment costs based on the long-standing engineering characteristics of a region, such as high energy storage ratio, long transmission distance, and high voltage level. The physical meaning of the parameters in the model is fully interpretable and can be directly used for cost sensitivity analysis, policy calculation, and preliminary investment assessment. Attached Figure Description

[0016] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0017] like Figure 1 As shown, the present invention provides a technical solution: a method for constructing an investment cost estimation model for an integrated photovoltaic and energy storage power station, comprising: Step S1: Since the total investment of new energy projects consists of multiple complex costs, and there are both linear relationships and nonlinear couplings between these costs, traditional empirical formulas are difficult to use for high-precision prediction. This invention obtains the engineering quantities, equipment composition, energy storage scale, transmission line parameters, and construction period financial structure from the feasibility study data of photovoltaic projects; quantifies the engineering quantities as DC-side installed capacity; quantifies the energy storage scale as energy storage configuration ratio; quantifies the transmission line parameters as transmission line length and transmission line voltage level; and quantifies the construction period financial structure as financing interest rate and construction period.

[0018] Step S2: Break down the total investment in the new energy photovoltaic project into basic cost, incremental energy storage cost, capitalized interest cost, and transmission line cost; Step S21: Calculate the basic cost based on the DC-side installed capacity; In many new energy projects, the basic cost (one of the core components of the total investment) exhibits an approximately power function law with the DC-side installed capacity extracted in step S1. The reason for this is that large-scale projects can significantly reduce the fixed construction costs through the (installed capacity) determined in step S1, while the costs of civil engineering, installation, electrical materials, etc. will expand in an incompletely linear manner with the increase. Therefore, taking the DC-side installed capacity in step S1 as the core variable, the basic cost can be expressed as a power function: ; In the formula, Basic cost; The unit capacity baseline cost under standardized conditions; To reflect the degree of economies of scale; This refers to the installed capacity on the DC side; The power exponent b is the manifestation of "economies of scale" in engineering—when the installed capacity of a photovoltaic project increases: 1. Fixed construction costs will be diluted; 2. Bargaining power for bulk equipment procurement will increase; 3. The growth rate of costs such as power transmission lines will be slower than the growth rate of capacity. Based on these realities, the relationship between "investment and the growth of installed capacity" will be "sublinear (cost growth is slower than capacity growth)" or "slightly superlinear (cost growth is slightly faster than capacity growth)". Therefore, the value of b is usually in the range of 0.9–1.1. when When the rate of increase is less than 1: the rate of increase in cost is less than the rate of increase in capacity → this reflects the "economies of scale" (the larger the installed capacity, the lower the unit cost). when When ≈1: Costs and capacity increase approximately proportionally → The impact of scale on costs is not significant; when >1: Cost growth rate > Capacity growth rate → Excessive scale will increase construction complexity (increase unit cost).

[0019] Step S22: Calculate the incremental cost of energy storage based on the energy storage configuration ratio and DC-side installed capacity; Regarding the incremental cost of energy storage, the "photovoltaic + energy storage" project in Xinjiang Uygur Autonomous Region has strong regional characteristics, and the incremental cost of energy storage is highly dependent on the proportion of energy storage configuration. Characteristics of incremental energy storage costs (especially electrochemical energy storage): Non-linear growth of fixed costs: Fixed costs such as battery cell procurement, BMS system integration, temperature control system, and fire-suppression components will not increase linearly with the expansion of energy storage capacity (for example, if the energy storage capacity doubles, these fixed costs will not also double). System constraints: Energy storage systems are constrained by C-rate (charge and discharge rate), safety standards, and integration methods. The larger the energy storage capacity, the more limited the room for reduction in "cost per unit capacity" (marginal unit price is difficult to reduce). Therefore, the cost of energy storage is established with an exponential relationship, meaning: ; In the formula, For incremental costs of energy storage; d is the benchmark cost coefficient for energy storage systems; d is the exponential parameter. The energy storage configuration ratio; When d>1, it means that if the energy storage configuration ratio (ESS) is increased slightly, the total cost will increase at a rate that exceeds the linear range (for example, if the ESS increases by 20%, the total cost may increase by 30%). When d approaches 1, the energy storage configuration ratio (ESS) and energy storage cost change almost proportionally (for example, if the ESS increases by 20%, the total cost will also increase by about 20%).

[0020] Step S23: Calculate the capitalized interest cost based on the DC-side installed capacity, financing rate, and construction period; Capitalized interest costs It reflects the financing cost, and the relationship between the financing interest rate r and the construction period T is strongly non-linear, so it is suitable to use the simplified IDC (construction period interest) formula for calculation; Interest is not linearly accumulated, but rather a compounding phenomenon of "time the capital is tied up × cost of capital." This is applicable to new energy projects with long construction cycles. Therefore, a simplified IDC (Interest During Construction) method is used to calculate the capitalized interest cost, which is expressed as: ; In the formula, Capitalized interest costs; T / 2 reflects the average time that funds are actually used; When the financing interest rate (r) is selected as "the same period LPR (Loan Prime Rate)" or the loan interest rate agreed in the project contract; This formula for calculating capitalized interest costs not only conforms to the financial calculation logic in the engineering field, but also maintains consistency with the calculation method of construction period interest in actual projects.

[0021] Step S24: Calculate the cost of the transmission project based on the length of the transmission line and the voltage level of the transmission line; The cost of transmission line projects is mainly related to the length of the transmission line and the voltage level of the transmission line. In the cost system of 110kV, 220kV, and 330kV power transmission projects in Xinjiang Uygur Autonomous Region, although the cost per kilometer does not vary significantly, the costs of collection lines, overhead lines, and tower foundations increase approximately linearly with the distance of transmission. Therefore, a simple linear relationship is used to calculate the cost of transmission projects, expressed as follows: ; In the formula, To cover the project costs; Voltage level of the transmission line; The length of the transmission line.

[0022] Step S3: Construct an overall nonlinear prediction model based on the base cost, incremental energy storage cost, capitalized interest cost, and transmission line cost; The overall nonlinear prediction model is expressed as follows: .

[0023] Step S4: Based on the overall nonlinear prediction model, estimate the initial investment of the photovoltaic project, compare and select different schemes, and evaluate the economic efficiency of the power plant; Power function term of the overall nonlinear prediction model The exponential term of the overall nonlinear prediction model reflects the economies of scale brought about by the scale of installed capacity. (for c⋅ESS) d Optimization yields an exponential term that characterizes the nonlinear amplification effect of costs when the energy storage configuration ratio increases; the overall nonlinear prediction model... Reflects the compounded capitalized interest rate under the combined effect of construction period financing interest rate and construction period; linear terms of the overall nonlinear prediction model. This describes an approximately linear increase in investment resulting from the length of the outgoing transmission line; The sample data obtained from Xinjiang Uygur Autonomous Region includes the actual cost of the project (engineering data of existing photovoltaic and energy storage projects in Xinjiang Uygur Autonomous Region are selected as samples). The sample data of Xinjiang Uygur Autonomous Region is fitted by an overall nonlinear prediction model and an existing linear regression model of the same caliber. The prediction results of the overall nonlinear prediction model are obtained. The goodness of fit of the overall nonlinear prediction model is significantly better than that of the linear regression model of the same caliber. The prediction results of the overall nonlinear prediction model include the cost predicted by the model. Calculate the coefficient of determination between the actual cost of the project and the cost predicted by the model. When the coefficient of determination When it approaches 1; The root mean square error (RMSE) of the actual project cost and the model-predicted cost is calculated, and the RMSE is only in the tens of millions of yuan. The mean absolute percentage error (MAPE) is calculated between the actual cost of the project and the cost predicted by the model, and the MAPE is controlled within a few percentage points. When the coefficient of determination When the root mean square error (RMSE) is close to 1, the average absolute error (MAPE) is only in the tens of millions of yuan range, and the average absolute error (MAPE) is controlled within a few percentage points, the accuracy requirements for engineering investment estimation are met, and a project sample is obtained. As the number of project samples increases, the coefficients a, b, c, and d in the base cost, incremental energy storage cost, capitalized interest cost, and transmission line cost can be recalibrated. When there are enough project samples, , , , Substituting a, b, c, d, and sample data from the Xinjiang Uygur Autonomous Region into the overall nonlinear prediction model constitutes a system of equations; by solving the system of equations, coefficients with regional engineering significance are obtained; The overall nonlinear prediction model is based on the engineering significance coefficient of the adapted region, which accurately completes the early investment estimation, scheme comparison and selection and power plant economic evaluation of photovoltaic projects. Preliminary Investment Estimate: Based on the overall nonlinear prediction model, the basic cost, incremental energy storage cost, capitalized interest cost, and transmission line cost are superimposed to obtain the preliminary investment estimate; Scheme comparison: The DC side installed capacity (Cap), energy storage configuration ratio (ESS), engineering line length (Dist), and transmission line voltage level are substituted into the overall nonlinear prediction model to calculate the cost. The cost calculation scheme is selected by combining the comparison and rationality of photovoltaic and energy storage projects. Power plant economic evaluation: Based on the cost predicted by the model and combined with the expected power generation revenue of the photovoltaic and energy storage project, the economic feasibility of the photovoltaic and energy storage project is judged.

[0024] A system for constructing an investment cost estimation model for an integrated photovoltaic and energy storage power station, applied to the aforementioned method for constructing an investment cost estimation model for an integrated photovoltaic and energy storage power station, includes: The data acquisition module is used to acquire the engineering quantities, equipment composition, energy storage scale, transmission line parameters, and construction period financial structure from the feasibility study data of photovoltaic projects; quantify the engineering quantities into DC side installed capacity; quantify the energy storage scale into energy storage configuration ratio; quantify the transmission line parameters into transmission line length and transmission line voltage level; and quantify the construction period financial structure into financing interest rate and construction period. The decomposition module is used to break down the total investment in a new energy photovoltaic project into basic cost, incremental energy storage cost, capitalized interest cost, and transmission line cost. The cost construction module is used to construct the basic cost based on the DC-side installed capacity. The incremental construction module is used to calculate the incremental cost of energy storage based on the energy storage configuration ratio and DC-side installed capacity. The capitalized interest construction module is used to construct the capitalized interest cost based on the DC-side installed capacity, financing rate, and construction period. The transmission project construction module is used to calculate the cost of the transmission project based on the length and voltage level of the transmission line. A predictive model is constructed based on the base cost, incremental energy storage cost, capitalized interest cost, and transmission line cost to form an overall nonlinear predictive model. The predictive evaluation model is used to estimate the initial investment of photovoltaic projects, compare different options, and evaluate the economic efficiency of power plants based on an overall nonlinear predictive model.

[0025] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for constructing an investment cost estimation model of a light and storage integrated station, characterized in that, Comprising the following steps: Step S1: Obtain the engineering quantity, equipment composition, energy storage scale, transmission line parameters and construction period financial structure in the feasibility study data of the photovoltaic project; Quantify the engineering quantity as the installed capacity on the DC side; Quantify the energy storage scale as the energy storage configuration ratio; Quantify the transmission line parameters as the length of the transmission project line and the voltage grade of the transmission line; Quantify the construction period financial structure as the financing interest rate and the construction period; Step S2: Disassemble the total investment in the new energy photovoltaic project into the basic cost, energy storage incremental cost, capitalized interest cost and transmission line cost; Step S21: Construct the basic cost based on the installed capacity on the DC side; Step S22: Construct the energy storage incremental cost based on the energy storage configuration ratio and the installed capacity on the DC side; Step S23: Construct the capitalized interest cost based on the installed capacity on the DC side, the financing interest rate and the construction period; Step S24: Construct the transmission project cost based on the length of the transmission project line and the voltage grade of the transmission line; Step S3: Construct the overall nonlinear prediction model based on the basic cost, the energy storage incremental cost, the capitalized interest cost and the transmission line cost; Step S4: Estimate the early-stage investment of the photovoltaic project, compare schemes and evaluate the economic efficiency of the power station based on the overall nonlinear prediction model.

2. The investment cost estimation model construction method of the optical storage integrated station according to claim 1, characterized in that: The basic cost is obtained, which is represented as: ； In the formula, is the base cost; is the unit capacity reference cost under standardized conditions; is the degree of scale economy; is the direct current side installed capacity.

3. The investment cost estimation model construction method of the optical storage integrated station according to claim 2, characterized in that: The energy storage cost is obtained, which is represented as: ； wherein is the incremental cost of energy storage; is the benchmark cost factor for energy storage systems; d is an exponential parameter; is the energy storage configuration ratio.

4. The investment cost estimation model construction method of the optical storage integrated station according to claim 3, characterized in that: The capitalized interest cost is obtained, which is represented as: ； wherein is the capitalized interest cost; is the financing rate; is the construction period.

5. The investment cost estimation model construction method of a light storage integrated station according to claim 4, characterized in that: The transmission project cost is obtained, which is represented as: ； wherein is the cost of the transmission project; is the voltage level of the transmission line; is the length of the transmission project line. 6.The method of claim 5, wherein the method further comprises: determining the investment cost of the integrated station based on the determined cost of the power storage system and the determined cost of the power generation system. The overall nonlinear prediction model is constructed, which is represented as: 。 7. The investment cost estimation model construction method of a light storage integrated station according to claim 6, characterized in that: The early-stage investment estimation of the photovoltaic project, scheme comparison and economic efficiency evaluation of the power station are as follows: Obtain sample data including actual project cost; Select the engineering data of the built photovoltaic storage project as sample data; Fit the sample data through the overall nonlinear prediction model to obtain the prediction result of the overall nonlinear prediction model; The prediction result of the overall nonlinear prediction model includes the cost predicted by the model; Determination of the coefficient of the actual cost of the project and the model predicted cost When the coefficient of determination Approaches 1; Calculate the root mean square error RMSE of the actual project cost and the cost predicted by the model; The root mean square error RMSE is only in the order of tens of millions of yuan; Calculate the average absolute percentage error MAPE of the actual project cost and the cost predicted by the model; The average absolute percentage error MAPE is controlled within a few percentage points; When the determination coefficient When the determination coefficient is close to 1, the root mean square error (RMSE) is only in the order of ten million yuan, and the mean absolute percentage error (MAPE) is controlled in the range of several percentage points, the project investment estimation accuracy requirements are met, and the project sample is obtained. With the increase of project samples, the a, b, c, d coefficients in the basic cost, the energy storage incremental cost, the capitalized interest cost and the transmission line cost can be recalibrated; When having enough project samples, the following steps are taken , , , , a, b, c, d, and Xinjiang Uygur Autonomous Region sample data are substituted into the overall nonlinear prediction model to form an equation group; the equation group is solved to obtain coefficients with regional engineering significance; The overall nonlinear prediction model is based on the adaptation area engineering significance coefficient, and can accurately complete the early-stage investment estimation of the photovoltaic project, scheme comparison and economic efficiency evaluation of the power station; Early-stage investment estimation: Based on the overall nonlinear prediction model, the basic cost, the energy storage incremental cost, the capitalized interest cost and the transmission line cost are superimposed to obtain the early-stage investment estimation; Scheme comparison: Substitute the installed capacity on the DC side Cap, the energy storage configuration ratio ESS, the length of the engineering line Dist and the voltage grade of the transmission line into the overall nonlinear prediction model to calculate the cost, and screen the cost calculation scheme in combination with the comparability and rationality of the photovoltaic storage project; Economic efficiency evaluation of power station: Based on the cost predicted by the model, in combination with the expected power generation income of the photovoltaic storage project, the economic feasibility of the photovoltaic storage project is judged.

8. A system for constructing an investment cost estimation model of a photovoltaic storage integrated station, applied to the method for constructing an investment cost estimation model of a photovoltaic storage integrated station according to any one of claims 1-7, characterized in that, Comprise: An acquisition data module is configured to acquire the engineering quantity, equipment composition, energy storage scale, transmission line parameters and construction period financial structure in the feasibility study data of the photovoltaic project; the engineering quantity is quantified as the installed capacity of the direct current side; the energy storage scale is quantified as the energy storage configuration ratio; the transmission line parameters are quantified as the length of the transmission project line and the voltage grade of the transmission line; The construction period financial structure is quantified as the financing interest rate and the construction period; A decomposition module is configured to decompose the total investment in the new energy photovoltaic project into the basic cost, energy storage incremental cost, capitalization interest cost and transmission line cost; A cost construction module is configured to construct the basic cost based on the installed capacity of the direct current side; An incremental construction module is configured to construct the energy storage incremental cost based on the energy storage configuration ratio and the installed capacity of the direct current side; A capitalization interest construction module is configured to construct the capitalization interest cost based on the installed capacity of the direct current side, the financing interest rate and the construction period; A transmission project construction module is configured to construct the transmission project cost based on the length of the transmission project line and the voltage grade of the transmission line; A prediction construction model is configured to construct a total nonlinear prediction model based on the basic cost, the energy storage incremental cost, the capitalization interest cost and the transmission line cost; A prediction evaluation model is configured to evaluate the early-stage investment estimation, scheme comparison and power station economy of the photovoltaic project based on the total nonlinear prediction model.

Images