Photovoltaic power generation project intelligent economic evaluation method based on kilowatt-hour cost analysis

Abstract

The invention discloses a photovoltaic power generation project intelligent economic evaluation method based on kilowatt-hour cost analysis, and the method comprises the following steps: 1, collecting the latest data for photovoltaic economic evaluation through employing a computer AI, and carrying out the data cleaning; 2, establishing a photovoltaic prediction model based on the data subjected to data cleaning; 3, inputting characteristic parameters of a photovoltaic power generation project to be subjected to economic evaluation into the photovoltaic prediction model to obtain corresponding photovoltaic economic evaluation parameter data; 4, setting other economic evaluation parameter data; 5, converting the photovoltaic economic evaluation parameter data into cost per kilowatt-hour; and 6, comparing the kilowatt-hour cost with the current market sales electricity price to obtain an evaluation conclusion. According to the invention, economic evaluation can be carried out on the photovoltaic power generation project more comprehensively and rapidly.

Description

Technical Field

[0001] The present invention relates to the technical field of computer-aided design, and in particular to an intelligent economic evaluation method for photovoltaic power generation projects based on cost-per-kilowatt-hour analysis. Background Art

[0002] In the prior art, the economic evaluation of new energy power generation projects is mainly about the calculation of the project's internal rate of return. For non-economic or financial professionals, the meaning and parameter settings of the internal rate of return are complex and difficult to understand.

[0003] Therefore, how to conduct economic evaluation of photovoltaic power generation projects more comprehensively and quickly has become a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0004] In view of the above-mentioned defects of the prior art, the present invention provides an intelligent economic evaluation method for photovoltaic power generation projects based on cost per kilowatt-hour analysis, the purpose of which is to be able to perform economic evaluation of photovoltaic power generation projects more comprehensively and quickly.

[0005] To achieve the above object, the present invention discloses an intelligent economic evaluation method for photovoltaic power generation projects based on cost per kilowatt-hour analysis, comprising the following steps:

[0006] Step 1: Use computer AI to collect the latest data for photovoltaic economic evaluation and perform data cleaning;

[0007] Step 2: Establishing a photovoltaic prediction model based on the data after the data cleaning;

[0008] Step 3: inputting characteristic parameters of the photovoltaic power generation project to be economically evaluated into the photovoltaic prediction model to obtain corresponding photovoltaic economic evaluation parameter data;

[0009] Step 4: Set other economic evaluation parameter data;

[0010] Step 5: converting the photovoltaic economic evaluation parameter data into a kilowatt-hour cost;

[0011] Step 6: Compare the electricity cost per kilowatt-hour with the current market electricity price to obtain an evaluation conclusion.

[0012] Preferably, step 1 is as follows:

[0013] Step 1.1, using the AI ​​script and the requests library of Python software to send an HTTP request to capture the latest data for the photovoltaic economic evaluation;

[0014] Step 1.2: Use Pandas software to clean the latest data, delete duplicates, process missing values, and convert data types. Finally, save the cleaned data into a CSV file.

[0015] More preferably, in step 1, the latest data refers to data from the date of collection within one year, three years or five years, including photovoltaic capacity, construction location, construction investment, construction period value-added tax, construction period interest, project net residual value, operation period, operating costs in the tth year, annual depreciation and power generation data in the tth year.

[0016] More preferably, step 2 is as follows:

[0017] Step 2.1, taking the photovoltaic capacity and the construction location as features, and taking the construction period value-added tax, the construction period interest, the project net residual value, the operation period, the t-year operating cost, the annual depreciation amount and the t-year power generation data as target variables to establish a random forest regression machine learning model;

[0018] Step 2.2: train, evaluate, and test the random forest regression machine learning model. After completion, use the trained random forest regression machine learning model as the photovoltaic prediction model.

[0019] Preferably, in step 3, the characteristic parameters of the photovoltaic power generation project to be economically evaluated include the photovoltaic capacity of the photovoltaic power generation project to be economically evaluated, and the construction site of the photovoltaic power generation project to be economically evaluated;

[0020] The corresponding photovoltaic economic evaluation parameter data include the predicted construction investment, construction period value-added tax, construction period interest, project net residual value, operation period, t-year operating cost, annual depreciation and t-year power generation data of the photovoltaic power generation project to be economically evaluated.

[0021] Preferably, in step 4, the other economic evaluation parameter data include the benchmark rate of return or discount rate of the photovoltaic power generation project to be economically evaluated, and the corporate income tax rate.

[0022] Preferably, in step 5, the photovoltaic economic evaluation parameter data is converted into the calculation formula of the cost per kilowatt-hour as follows:

[0023]

[0024] Wherein, LCOE is the cost per kilowatt-hour of electricity;

[0025] I g Investment in project construction, value-added tax and construction period interest;

[0026] V R is the net residual value of the project;

[0027] is the operating cost in year t;

[0028] R TAX is the corporate income tax rate;

[0029] D depreciation is the annual depreciation amount;

[0030] T r For the operation period:

[0031] E t is the power generation in year t;

[0032] i c The benchmark yield or discount rate.

[0033] Preferably, in step 6, if the cost per kilowatt-hour is lower than the current market sales electricity price, the output evaluation conclusion is: the project is feasible; if the cost per kilowatt-hour is higher than the current market sales electricity price, the output evaluation conclusion is: the project is not feasible.

[0034] Beneficial effects of the present invention:

[0035] The application of the present invention can more comprehensively and quickly carry out economic evaluation of photovoltaic power generation projects.

[0036] The concept, specific structure and technical effects of the present invention will be further described below to fully understand the purpose, characteristics and effects of the present invention. DETAILED DESCRIPTION

[0037] Example

[0038] The intelligent economic evaluation method of photovoltaic power generation projects based on cost-per-kilowatt-hour analysis includes the following steps:

[0039] Step 1: Use computer AI to collect the latest data for photovoltaic economic evaluation and perform data cleaning;

[0040] Step 2: Establish a photovoltaic prediction model based on the data after data cleaning;

[0041] Step 3: Inputting characteristic parameters of the photovoltaic power generation project to be economically evaluated into the photovoltaic prediction model to obtain corresponding photovoltaic economic evaluation parameter data;

[0042] Step 4: Set other economic evaluation parameter data;

[0043] Step 5: Convert photovoltaic economic evaluation parameter data into electricity cost;

[0044] Step 6: Compare the cost per kilowatt-hour with the current market electricity price to obtain an evaluation conclusion.

[0045] The present invention uses AI scripts to obtain the latest photovoltaic data in a timely and rapid manner, converts a large amount of complex photovoltaic data into a simple cost per kilowatt-hour through software, and draws conclusions by comparing the cost per kilowatt-hour with the sales electricity price, thereby enabling a more comprehensive and rapid economic evaluation of photovoltaic power generation projects.

[0046] In some embodiments, step 1 is as follows:

[0047] Step 1.1: Use the AI ​​script to send HTTP requests using the requests library of Python software to fetch the latest data for photovoltaic economic evaluation;

[0048] Step 1.2: Use Pandas software to clean the latest data, delete duplicates, process missing values, and convert data types. Finally, save the cleaned data into a CSV file.

[0049] In some embodiments, in step 1, the latest data refers to data from the date of collection one year, three years, or five years ago, including photovoltaic capacity, construction location, construction investment, construction period value-added tax, construction period interest, project net residual value, operation period, operating costs in the tth year, annual depreciation amount, and power generation data in the tth year.

[0050] In some embodiments, step 2 is as follows:

[0051] Step 2.1, taking PV capacity and construction location as features, and taking construction period value-added tax, construction period interest, project net residual value, operation period, operating cost in the tth year, annual depreciation and power generation data in the tth year as target variables to establish a random forest regression machine learning model;

[0052] Step 2.2: Train, evaluate, and test the random forest regression machine learning model. After completion, use the trained random forest regression machine learning model as a photovoltaic prediction model.

[0053] In some embodiments, in step 3, the characteristic parameters of the photovoltaic power generation project to be economically evaluated include the photovoltaic capacity of the photovoltaic power generation project to be economically evaluated, and the construction site of the photovoltaic power generation project to be economically evaluated;

[0054] The corresponding photovoltaic economic evaluation parameter data include the predicted construction investment, construction period value-added tax, construction period interest, project net residual value, operation period, t-year operating cost, annual depreciation and t-year power generation data of the photovoltaic power generation project to be economically evaluated.

[0055] In some embodiments, in step 4, other economic evaluation parameter data include a benchmark rate of return or discount rate of the photovoltaic power generation project to be economically evaluated, and a corporate income tax rate.

[0056] In some embodiments, in step 5, the calculation formula for converting the photovoltaic economic evaluation parameter data into the cost per kilowatt-hour is as follows:

[0057]

[0058] Among them, LCOE is the cost per kilowatt-hour of electricity;

[0059] I g Investment in project construction, value-added tax and construction period interest;

[0060] V R is the net residual value of the project;

[0061] is the operating cost in year t;

[0062] R TAX is the corporate income tax rate;

[0063] D depreciation is the annual depreciation amount;

[0064] T r For the operation period:

[0065] E t is the power generation in year t;

[0066] i c The benchmark yield or discount rate.

[0067] In some embodiments, in step 6, if the cost per kilowatt-hour is lower than the current market electricity price, the output evaluation conclusion is: the project is feasible; if the cost per kilowatt-hour is higher than the current market electricity price, the output evaluation conclusion is: the project is not feasible.

[0068] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. An intelligent economic evaluation method for photovoltaic power generation projects based on cost per kilowatt-hour analysis; characterized in that: The steps include: Step 1: Use computer AI to collect the latest data for photovoltaic economic evaluation and perform data cleaning; Step 2: Establishing a photovoltaic prediction model based on the data after the data cleaning; Step 3: inputting characteristic parameters of the photovoltaic power generation project to be economically evaluated into the photovoltaic prediction model to obtain corresponding photovoltaic economic evaluation parameter data; Step 4: Set other economic evaluation parameter data; Step 5: converting the photovoltaic economic evaluation parameter data into a kilowatt-hour cost; Step 6: Compare the electricity cost per kilowatt-hour with the current market electricity price to obtain an evaluation conclusion.

2. The intelligent economic evaluation method for photovoltaic power generation projects based on cost per kilowatt-hour analysis according to claim 1 is characterized in that: Step 1 is as follows: Step 1.1, using the AI ​​script and the requests library of Python software to send an HTTP request to capture the latest data for the photovoltaic economic evaluation; Step 1.2: Use Pandas software to clean the latest data, delete duplicates, process missing values, and convert data types. Finally, save the cleaned data into a CSV file.

3. The intelligent economic evaluation method for photovoltaic power generation projects based on cost per kilowatt-hour analysis according to claim 2 is characterized in that: In step 1, the latest data refers to data from the date of collection within one year, three years or five years, including photovoltaic capacity, construction location, construction investment, construction period value-added tax, construction period interest, project net residual value, operation period, operating cost in the tth year, annual depreciation and power generation data in the tth year.

4. The intelligent economic evaluation method for photovoltaic power generation projects based on cost per kilowatt-hour analysis according to claim 3 is characterized in that: Step 2 is as follows: Step 2.1, taking the photovoltaic capacity and the construction location as features, and taking the construction period value-added tax, the construction period interest, the project net residual value, the operation period, the t-year operating cost, the annual depreciation amount and the t-year power generation data as target variables to establish a random forest regression machine learning model; Step 2.2: train, evaluate, and test the random forest regression machine learning model. After completion, use the trained random forest regression machine learning model as the photovoltaic prediction model.

5. The intelligent economic evaluation method for photovoltaic power generation projects based on cost per kilowatt-hour analysis according to claim 1 is characterized in that: In step 3, the characteristic parameters of the photovoltaic power generation project to be economically evaluated include the photovoltaic capacity of the photovoltaic power generation project to be economically evaluated and the construction site of the photovoltaic power generation project to be economically evaluated; The corresponding photovoltaic economic evaluation parameter data include the predicted construction investment, construction period value-added tax, construction period interest, project net residual value, operation period, t-year operating cost, annual depreciation and t-year power generation data of the photovoltaic power generation project to be economically evaluated.

6. The intelligent economic evaluation method for photovoltaic power generation projects based on cost per kilowatt-hour analysis according to claim 1 is characterized in that: In step 4, the other economic evaluation parameter data include the benchmark rate of return or discount rate of the photovoltaic power generation project to be economically evaluated, and the corporate income tax rate.

7. The intelligent economic evaluation method for photovoltaic power generation projects based on cost per kilowatt-hour analysis according to claim 1 is characterized in that: In step 5, the photovoltaic economic evaluation parameter data is converted into the calculation formula of the cost per kilowatt-hour as follows: Wherein, LCOE is the cost per kilowatt-hour of electricity; I g Investment in project construction, value-added tax and construction period interest; V R is the net residual value of the project; is the operating cost in year t; R TAX is the corporate income tax rate; D depreciation is the annual depreciation amount; T r For the operation period: E t is the power generation in year t; i c The benchmark yield or discount rate.

8. The intelligent economic evaluation method for photovoltaic power generation projects based on cost per kilowatt-hour analysis according to claim 1 is characterized in that: In step 6, if the cost per kilowatt-hour is lower than the current market electricity price, the evaluation conclusion is output as follows: the project is feasible; if the cost per kilowatt-hour is higher than the current market electricity price, the evaluation conclusion is output as follows: the project is not feasible.

Images