New energy station operation and maintenance cost evaluation method based on business classification and prediction model

Abstract

The invention discloses a new energy station operation and maintenance cost evaluation method based on a business classification and prediction model. The method comprises the steps of obtaining a plurality of parameter variables required for operation cost evaluation of a new energy station according to energy business, and performing variable grade setting; performing distribution function analysis on each parametric variable in each grade, and constructing a cost dynamic change probability model of each parametric variable according to an analysis result; constructing an operation and maintenance variable coupling time sequence prediction model based on time sequence analysis and a high-frequency dynamic algorithm according to a correlation coefficient between the core parameter variable and the non-core parameter variable and the cost dynamic change probability model of each parameter variable; and determining an operation and maintenance cost estimation value of each parameter variable under the current probability condition parameter through an operation and maintenance variable coupling time sequence prediction model. The method fully considers the influence of multiple factors on the operation and maintenance cost, and achieves the precise prediction and comprehensive evaluation of the operation and maintenance cost.

Description

Technical Field

[0001] The present invention relates to the field of cost assessment technology, and in particular to a new energy station operation and maintenance cost assessment method based on business classification and prediction model. Background Art

[0002] After the new energy station is equipped with an energy storage system, it can smooth the output of wind power and photovoltaic power, provide primary frequency regulation for the system, and carry out applications such as peak shaving and valley filling, auxiliary peak and frequency regulation, and direct dispatch of provincial networks, creating more space for the consumption and utilization of new energy. Therefore, the equipment operation of new energy stations is particularly important. At present, there is no mature model to support the statistics and evaluation of costs. The current cost statistics are based on manual reporting, which is easy to miss, no statistical standards, and inaccurate statistical data. The cost evaluation calculation method is single, with few key parameter factors, and the fixed algorithm cannot be applied to all stations. The main problems that still exist in the current operating cost evaluation are: manual reporting, easy to miss, and inaccurate statistical data; single calculation method, few key parameter factors, and fixed algorithms cannot be applied to all stations; low intelligence, and the need to provide a large amount of basic data. There is a lack of standard knowledge in statistics, including labor costs, outsourcing costs, technical transformation costs, management costs and other types of costs, and there is a lack of guiding standards; the statistical caliber is inconsistent and the statistics are not standardized; the calculation rules are complicated and the cost classification standards are not unified, which leads to confusion and inconsistency in the evaluation process. The statistical caliber often does not match the actual situation on the site, and the impact of multiple factors on operation and maintenance costs is not considered, resulting in a large deviation between the evaluation results and the actual costs. This seriously restricts the efficiency and accuracy of the operation and maintenance management of new energy stations. Summary of the invention

[0003] In view of the above problems, the present invention provides a new energy station operation and maintenance cost assessment method based on business classification and prediction model to solve the problems mentioned in the background technology, such as complex calculation rules and inconsistent cost classification standards, which lead to confusion and inconsistency in the assessment process, and the statistical caliber often does not match the actual situation on site, resulting in a large deviation between the assessment results and the actual costs. This seriously restricts the efficiency and accuracy of the operation and maintenance management of new energy stations.

[0004] A method for evaluating the operation and maintenance costs of a new energy station based on business classification and prediction model comprises the following steps:

[0005] Obtain multiple parameter variables required for operating cost evaluation of new energy stations based on energy business and set variable levels;

[0006] Perform distribution function analysis on each parameter variable in each level, and build a dynamic cost change probability model for each parameter variable based on the analysis results;

[0007] According to the correlation coefficient between core parameter variables and non-core parameter variables and the dynamic change probability model of the cost of each parameter variable, a coupled time series prediction model of operation and maintenance variables based on time series analysis and high-frequency dynamic algorithm is constructed;

[0008] The estimated value of operation and maintenance cost of each parameter variable under the current probability condition parameters is determined through the operation and maintenance variable coupling time series prediction model.

[0009] Preferably, the step of obtaining a plurality of parameter variables required for operating cost assessment of a new energy station according to the energy business and setting the variable levels includes:

[0010] Determine the power generation type of the new energy station, and determine the energy business of the new energy station according to the power generation type, the power generation type includes: photovoltaic and wind power;

[0011] Based on the energy business, obtain the production and operation information and financial information of new energy stations, and analyze the production and operation information and financial information;

[0012] Obtaining multiple parameter variables required for operating cost evaluation of new energy stations based on the analysis results;

[0013] The parameter variables required for evaluating multiple operating expenses are divided into four categories based on production operations and financial related criteria.

[0014] Preferably, after obtaining a plurality of parameter variables required for evaluating the operating costs of the new energy station according to the energy business, the method further includes:

[0015] The Pearson test is used to test the correlation between the parameter variables required for the evaluation of various operating expenses, and the correlation coefficient between the parameter variables required for the evaluation of various operating expenses is determined based on the correlation;

[0016] The parameter variables whose correlation coefficients are greater than or equal to the preset threshold are merged.

[0017] Preferably, the distribution function analysis is performed on each parameter variable in each level, and a cost dynamic change probability model of each parameter variable is constructed according to the analysis result, including:

[0018] Obtain a discrete sequence of each parameter variable, perform power spectrum analysis on each parameter variable according to the discrete sequence, and obtain analysis results;

[0019] Determine the actual distribution state of each parameter variable according to the analysis results, and determine the distribution function equation of each parameter variable according to the actual distribution state;

[0020] The distribution function equation of each parameter variable is analyzed according to different power station types to obtain the probability distribution state of all basic data of each parameter variable;

[0021] Obtain the rated standard of each parameter variable under each probability distribution state and set it as the standard fixed-rate operation and maintenance fee of each parameter variable;

[0022] A dynamic cost change probability model for each parameter variable is constructed based on the standard fixed operation and maintenance costs of each parameter variable under each probability distribution state and the probability distribution state of basic data.

[0023] Preferably, the method of constructing an operation and maintenance variable coupling time series prediction model based on time series analysis and high-frequency dynamic algorithm according to the correlation coefficient between the core parameter variables and the non-core parameter variables and the cost dynamic change probability model of each parameter variable includes:

[0024] Obtain the mathematical model relationship between core parameter variables and non-core parameter variables through non-linear models;

[0025] According to the mathematical model relationship, the correlation coefficient between the core parameter variables and the non-core parameter variables is determined through the probability density function equation;

[0026] Extract the trend, linear and periodic change data features corresponding to the time series data of each parameter variable;

[0027] According to the data characteristics and the correlation coefficients between the core parameter variables and the non-core parameter variables and the probability model of the dynamic change of the cost of each parameter variable, a rolling prediction model of the autoregression and high-frequency dynamic change of each parameter variable is constructed.

[0028] Preferably, the operation and maintenance cost estimation value of each parameter variable under the current probability condition parameter is determined by coupling the operation and maintenance variable with the time series prediction model, including:

[0029] The operation and maintenance cost estimation prediction value range of each parameter variable under different probability conditions is determined through the operation and maintenance variable coupling time series prediction model;

[0030] Obtain the current probability condition parameters, and determine the operation and maintenance cost probability curve of each parameter variable under the current probability condition parameters according to the current probability condition parameters and the operation and maintenance cost estimation prediction value interval of each parameter variable under different probability conditions;

[0031] Determine the estimated value of the operation and maintenance cost under different probabilities under the current condition parameters of each parameter variable according to the operation and maintenance cost probability curve;

[0032] Based on the estimated values ​​of operation and maintenance costs under different probabilities under the current condition parameters of each parameter variable and the basic information, personnel information and asset information of the new energy station, a cost assessment report is generated through a preset cost assessment model.

[0033] Preferably, it also includes:

[0034] Generate periodic evaluation data for each parameter variable through the operation and maintenance variable coupling time series prediction model;

[0035] Import periodic evaluation data and actual cost statistics into the operation and maintenance variable coupling time series forecasting model and compare them to obtain Gaussian distribution;

[0036] The prediction accuracy is determined according to the Gaussian distribution, and the offset probability number is added to the parameter value of the operation and maintenance variable coupling time series prediction model according to the prediction accuracy to complete the parameter tuning.

[0037] Preferably, determining the actual distribution state of each parameter variable according to the analysis result includes:

[0038] Determine the data range of each parameter variable based on the analysis results, and determine the data jump frequency based on the data range;

[0039] The discrete sequence data of each parameter variable is divided into several unit arrays based on the data jump frequency;

[0040] Determine the array boundaries of each unit array and compile a frequency distribution table based on the data boundaries;

[0041] Determine the actual distribution status of each parameter variable based on the frequency distribution table.

[0042] Preferably, it also includes:

[0043] Collect geographical environment parameters around the construction site of new energy stations and determine the operation and maintenance difficulty index based on the geographical environment parameters;

[0044] Set the geographical environment coefficient of new energy stations based on the operation and maintenance difficulty index and the conversion rules between the geographical environment coefficient and freight costs;

[0045] According to the conversion rules, the estimated value of the operation and maintenance costs of the new energy station is calculated to obtain the final cost assessment value.

[0046] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0047] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0049] Figure 1A workflow diagram of a new energy station operation and maintenance cost assessment method based on business classification and prediction model provided by the present invention;

[0050] Figure 2 Another work flow chart of a new energy station operation and maintenance cost assessment method based on business classification and prediction model provided by the present invention;

[0051] Figure 3 The present invention provides another workflow diagram of a new energy station operation and maintenance cost assessment method based on business classification and prediction model. DETAILED DESCRIPTION

[0052] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0053] After the new energy station is equipped with an energy storage system, it can smooth the output of wind power and photovoltaic power, provide primary frequency regulation for the system, and carry out applications such as peak shaving and valley filling, auxiliary peak and frequency regulation, and direct dispatch of provincial networks, creating more space for the consumption and utilization of new energy. Therefore, the equipment operation of new energy stations is particularly important. At present, there is no mature model to support the statistics and evaluation of costs. The current cost statistics are based on manual reporting, which is easy to miss, no statistical standards, and inaccurate statistical data. The cost evaluation calculation method is single, with few key parameter factors, and the fixed algorithm cannot be applied to all stations. The main problems that still exist in the current operating cost evaluation are: manual reporting, easy to miss, and inaccurate statistical data; single calculation method, few key parameter factors, and fixed algorithms cannot be applied to all stations; low intelligence, and the need to provide a large amount of basic data. There is a lack of standard knowledge in statistics, including labor costs, outsourcing costs, technical transformation costs, management costs and other types of costs, and there is a lack of guiding standards; the statistical calibers are inconsistent and the statistics are not standardized; the calculation rules are complicated, and the cost classification standards are not unified, which leads to confusion and inconsistency in the evaluation process. The statistical caliber often does not match the actual situation on the site, and the impact of multiple factors on operation and maintenance costs is not considered, resulting in a large deviation between the evaluation results and the actual costs. This seriously restricts the efficiency and accuracy of the operation and maintenance management of new energy stations. In order to solve the above problems, this embodiment discloses a method for evaluating the operation and maintenance costs of new energy stations based on business classification and prediction models.

[0054] A new energy station operation and maintenance cost evaluation method based on business classification and prediction model, such as Figure 1 As shown, the following steps are included:

[0055] Step S101: acquiring multiple parameter variables required for operating cost evaluation of new energy stations according to energy business and setting variable levels;

[0056] Step S102, performing distribution function analysis on each parameter variable in each level, and constructing a cost dynamic change probability model for each parameter variable according to the analysis results;

[0057] Step S103, constructing an operation and maintenance variable coupling time series prediction model based on time series analysis and high-frequency dynamic algorithm according to the correlation coefficient between the core parameter variables and the non-core parameter variables and the cost dynamic change probability model of each parameter variable;

[0058] Step S104: Determine the estimated value of the operation and maintenance cost of each parameter variable under the current probability condition parameters through the operation and maintenance variable coupling time series prediction model.

[0059] In this embodiment, the distribution function analysis is represented by the probability analysis of the distribution function of each parameter variable in each application scenario;

[0060] In this embodiment, the dynamic change probability model of the cost is represented as a dynamic change model of the cost curve under different occurrence probabilities of parameter variables;

[0061] In this embodiment, the core parameter variables are represented as cost parameter variables corresponding to the necessary operation and maintenance items;

[0062] In this embodiment, the non-core parameter variables are represented as cost parameter variables corresponding to non-essential operation and maintenance items;

[0063] In this embodiment, the operation and maintenance variable coupling time series prediction model based on time series analysis and high-frequency dynamic algorithm is expressed as an operation and maintenance cost prediction model when parameter variables are in high-frequency changes under different time series states.

[0064] The working principle of the above technical solution is: according to the energy business, multiple parameter variables required for operating cost evaluation of new energy stations are obtained and variable levels are set; distribution function analysis is performed on each parameter variable in each level, and a cost dynamic change probability model for each parameter variable is constructed according to the analysis results; according to the correlation coefficient between the core parameter variables and the non-core parameter variables and the cost dynamic change probability model of each parameter variable, an operation and maintenance variable coupling time series prediction model based on time series analysis and high-frequency dynamic algorithm is constructed; the operation and maintenance cost estimate of each parameter variable under the current probability condition parameters is determined through the operation and maintenance variable coupling time series prediction model.

[0065] The beneficial effects of the above technical solution are: by determining the business operation of the new energy station according to the energy business and then determining the parameter variables, the adaptability of the statistical caliber to the actual situation of the new energy station can be effectively grasped, so that the evaluation results are more in line with the operation of the new energy station, and the accuracy and precision are improved. Furthermore, by performing fine parameter variable level division and constructing an operation and maintenance variable coupling time series prediction model based on time series analysis and high-frequency dynamic algorithm, the uniformity of the cost classification standard can be guaranteed. It fully considers the impact of multiple factors on operation and maintenance costs, realizes accurate prediction and comprehensive evaluation of operation and maintenance costs, and solves the problems mentioned in the prior art, such as complex calculation rules and inconsistent cost classification standards, which lead to confusion and inconsistency in the evaluation process. The statistical caliber often does not match the actual situation on the site, and the impact of multiple factors on operation and maintenance costs is not considered, which causes a large deviation between the evaluation results and the actual costs. It seriously restricts the efficiency and accuracy of operation and maintenance management of new energy stations.

[0066] In one embodiment, Figure 2 As shown, the method of obtaining multiple parameter variables required for operating cost evaluation of new energy stations according to energy business and setting variable levels includes:

[0067] Step S201: determining the power generation type of the new energy station, and determining the energy business of the new energy station according to the power generation type, wherein the power generation type includes photovoltaic power and wind power;

[0068] Step S202: Acquire production operation information and financial information of the new energy station based on the energy business, and analyze the production operation information and financial information;

[0069] Step S203: obtaining a plurality of parameter variables required for operating cost evaluation of the new energy station according to the analysis results;

[0070] Step S204: classify multiple parameter variables required for operating cost evaluation into four levels according to production operation and financial related criteria.

[0071] In this embodiment, the initial operation and maintenance cost parameter variables are classified into four levels, wherein the first level includes seven categories: production costs, labor costs, technical transformation costs, safety generation costs, management costs, regional centralized control costs and other costs; the second level includes: maintenance and repair, material procurement, information construction, fixed asset depreciation, intangible asset amortization, site management personnel and other twenty-six categories; as well as nearly one hundred third-level classification parameters and twenty-five fourth-level classifications.

[0072] The beneficial effect of the above technical solution is that for each subdivided cost parameter variable, the system has been standardized and classified. This means that no matter which new energy station, a unified standard can be used for classification and accounting when evaluating operation and maintenance costs. This standardized classification not only improves the standardization and comparability of cost assessment, but also provides strong support for subsequent cost control, optimization and decision-making. A comprehensive cost assessment framework has been established, covering all major cost categories in the operation and maintenance process of new energy stations. This framework not only helps to fully understand the operation and maintenance cost structure of new energy stations, but also provides an important reference for formulating scientific operation and maintenance strategies, optimizing resource allocation, and improving economic benefits. By deeply understanding the actual operation of new energy stations, it is ensured that each subdivided cost can accurately reflect the actual cost on site, thereby improving the practicality and reliability of cost assessment. The problem of mismatch between the actual statistical caliber subjects and the actual classification granularity on site is avoided.

[0073] In one embodiment, after obtaining a plurality of parameter variables required for evaluating the operating costs of the new energy station according to the energy business, the method further includes:

[0074] The Pearson test is used to test the correlation between the parameter variables required for the evaluation of various operating expenses, and the correlation coefficient between the parameter variables required for the evaluation of various operating expenses is determined based on the correlation;

[0075] The parameter variables whose correlation coefficients are greater than or equal to the preset threshold are merged.

[0076] In this embodiment, the correlation coefficient between parameter variables is defined as:

[0077]

[0078] Where r is the sample correlation coefficient, is the sum of squares of the deviations from the mean of X, It is the sum of squares of the deviations from the mean of Y. If the parameter variables show positive or negative correlation, they are combined to a limited extent according to their correlation R.

[0079] The beneficial effects of the above technical solution are: simplifying the types of parameter variables, facilitating the establishment of an effective and unified parameter collection system in the later stage, and mathematically verifying whether the initial parameter variables established according to financial or work habits have the best statistical classification significance.

[0080] In one embodiment, the distribution function analysis is performed on each parameter variable in each level, and a cost dynamic change probability model of each parameter variable is constructed according to the analysis result, including:

[0081] Obtain a discrete sequence of each parameter variable, perform power spectrum analysis on each parameter variable according to the discrete sequence, and obtain analysis results;

[0082] Determine the actual distribution state of each parameter variable according to the analysis results, and determine the distribution function equation of each parameter variable according to the actual distribution state;

[0083] The distribution function equation of each parameter variable is analyzed according to different power station types to obtain the probability distribution state of all basic data of each parameter variable;

[0084] Obtain the rated standard of each parameter variable under each probability distribution state and set it as the standard fixed-rate operation and maintenance fee of each parameter variable;

[0085] A dynamic cost change probability model for each parameter variable is constructed based on the standard fixed operation and maintenance costs of each parameter variable under each probability distribution state and the probability distribution state of basic data.

[0086] In this embodiment, the power spectrum is the power spectrum density function, which is a discrete non-periodic sequence X n , the square of its amplitude spectrum |X n | 2 The sequence is defined as:

[0087]

[0088] Under the orthogonality conditions of COSINE and SINE, the variance equation is expressed as:

[0089]

[0090] in, is the coefficient of the periodic change of the t-th sample variance, and The value also represents the periodic ordinate value measured through the sample space N. The periodogram can be written as:

[0091]

[0092] The beneficial effects of the above technical solution are: the distribution function equation for each parameter variable can effectively help us obtain the probability distribution state of the data sample space, and provide the probability distribution state of each parameter variable for the next step of establishing an operation and maintenance prediction and evaluation model. The probability distribution of operation and maintenance costs can be indirectly obtained from the distribution state of each parameter, providing basic data support for predicting and evaluating operation and maintenance costs. Furthermore, by constructing a dynamic cost change probability model for each parameter variable, the operation and maintenance cost changes of each parameter variable under different conditional parameters and their occurrence probabilities can be comprehensively determined through the model, thereby ensuring the comprehensiveness of the data.

[0093] In one embodiment, Figure 3 As shown, the operation and maintenance variable coupling time series prediction model based on time series analysis and high-frequency dynamic algorithm is constructed according to the correlation coefficient between the core parameter variables and the non-core parameter variables and the cost dynamic change probability model of each parameter variable, including:

[0094] Step S301, obtaining a mathematical model relationship between core parameter variables and non-core parameter variables through a nonlinear model;

[0095] Step S302, determining the correlation coefficient between the core parameter variables and the non-core parameter variables through a probability density function equation according to the mathematical model relationship;

[0096] Step S303, extracting trend, linear, and periodic change data features corresponding to the time series data of each parameter variable;

[0097] Step S304: construct an autoregressive and high-frequency dynamic change rolling prediction model for each parameter variable based on the data characteristics, the correlation coefficients between the core parameter variables and the non-core parameter variables, and the cost dynamic change probability model of each parameter variable.

[0098] In this embodiment, the probability density function equation is:

[0099]

[0100] Here, b and μ are the proportion and location variables, respectively. μ can be either the median or the mean, with the median usually chosen to reflect the most flexible measure.

[0101] The beneficial effect of the above technical solution is: by determining the correlation coefficient between the core parameter variables and the non-core parameter variables, the change in the operation and maintenance cost of the non-core variables under the condition of the core variables can be determined, and then a dynamic change model of the cost of each parameter variable under the impression of the non-core variables can be quickly constructed.

[0102] In one embodiment, determining the estimated value of the operation and maintenance cost of each parameter variable under the current probability condition parameter by coupling the operation and maintenance variable with the time series prediction model includes:

[0103] The operation and maintenance cost estimation prediction value range of each parameter variable under different probability conditions is determined through the operation and maintenance variable coupling time series prediction model;

[0104] Obtain the current probability condition parameters, and determine the operation and maintenance cost probability curve of each parameter variable under the current probability condition parameters according to the current probability condition parameters and the operation and maintenance cost estimation prediction value interval of each parameter variable under different probability conditions;

[0105] Determine the estimated value of the operation and maintenance cost under different probabilities under the current condition parameters of each parameter variable according to the operation and maintenance cost probability curve;

[0106] Based on the estimated values ​​of operation and maintenance costs under different probabilities under the current condition parameters of each parameter variable and the basic information, personnel information and asset information of the new energy station, a cost assessment report is generated through a preset cost assessment model.

[0107] The beneficial effect of the above technical solution is that through probability analysis, technicians can obtain the possible distribution range and confidence interval of operation and maintenance costs, which provides station managers with more comprehensive and accurate operation and maintenance cost information, helping them make more scientific and reasonable decisions.

[0108] In one embodiment, it further includes:

[0109] Generate periodic evaluation data for each parameter variable through the operation and maintenance variable coupling time series prediction model;

[0110] Import periodic evaluation data and actual cost statistics into the operation and maintenance variable coupling time series forecasting model and compare them to obtain Gaussian distribution;

[0111] The prediction accuracy is determined according to the Gaussian distribution, and the offset probability number is added to the parameter value of the operation and maintenance variable coupling time series prediction model according to the prediction accuracy to complete the parameter tuning.

[0112] The beneficial effect of the above technical solution is that the cost classification and evaluation standards can be adjusted and improved according to actual conditions to ensure the timeliness and accuracy of the cost evaluation system.

[0113] In one embodiment, determining the actual distribution state of each parameter variable according to the analysis result includes:

[0114] Determine the data range of each parameter variable based on the analysis results, and determine the data jump frequency based on the data range;

[0115] The discrete sequence data of each parameter variable is divided into several unit arrays based on the data jump frequency;

[0116] Determine the array boundaries of each unit array and compile a frequency distribution table based on the data boundaries;

[0117] Determine the actual distribution status of each parameter variable based on the frequency distribution table.

[0118] The beneficial effect of the above technical solution is: determining the actual distribution state of the data to judge which type of distribution function the data conforms to, so that the final function evaluation result is more accurate.

[0119] In one embodiment, it further includes:

[0120] Collect geographical environment parameters around the construction site of new energy stations and determine the operation and maintenance difficulty index based on the geographical environment parameters;

[0121] Set the geographical environment coefficient of new energy stations based on the operation and maintenance difficulty index and the conversion rules between the geographical environment coefficient and freight costs;

[0122] According to the conversion rules, the estimated value of the operation and maintenance costs of the new energy station is calculated to obtain the final cost assessment value.

[0123] The beneficial effect of the above technical solution is that by setting the geographical environment coefficient, the difference in operation and maintenance costs of new energy stations in different geographical environments can be more accurately evaluated, and then the most accurate cost assessment value can be determined for the geographical environment of the new energy station, ensuring the accuracy and reliability of the cost calculation data.

[0124] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0125] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for evaluating the operation and maintenance costs of new energy stations based on business classification and prediction model, characterized in that: The following steps are involved: Obtain multiple parameter variables required for operating cost evaluation of new energy stations based on energy business and set variable levels; Perform distribution function analysis on each parameter variable in each level, and build a dynamic cost change probability model for each parameter variable based on the analysis results; According to the correlation coefficient between core parameter variables and non-core parameter variables and the dynamic change probability model of the cost of each parameter variable, a time series prediction model for operation and maintenance variables coupling based on time series analysis and high-frequency dynamic algorithm is constructed; The estimated value of operation and maintenance cost of each parameter variable under the current probability condition parameters is determined through the operation and maintenance variable coupling time series prediction model.

2. The new energy station operation and maintenance cost assessment method based on business classification and prediction model according to claim 1 is characterized in that: The step of obtaining multiple parameter variables required for operating cost evaluation of new energy stations according to energy business and setting variable levels includes: Determine the power generation type of the new energy station, and determine the energy business of the new energy station according to the power generation type, the power generation type includes: photovoltaic and wind power; Based on the energy business, obtain the production and operation information and financial information of new energy stations, and analyze the production and operation information and financial information; Obtaining multiple parameter variables required for operating cost evaluation of new energy stations based on the analysis results; The parameter variables required for evaluating multiple operating expenses are divided into four categories based on production operations and financial related criteria.

3. The new energy station operation and maintenance cost assessment method based on business classification and prediction model according to claim 1 is characterized in that: After obtaining multiple parameter variables required for operating cost evaluation of new energy stations based on energy business, it also includes: The Pearson test is used to test the correlation between the parameter variables required for the evaluation of various operating expenses, and the correlation coefficient between the parameter variables required for the evaluation of various operating expenses is determined based on the correlation; The parameter variables whose correlation coefficients are greater than or equal to the preset threshold are merged.

4. The new energy station operation and maintenance cost assessment method based on business classification and prediction model according to claim 1 is characterized in that: The distribution function analysis is performed on each parameter variable in each level, and a cost dynamic change probability model of each parameter variable is constructed according to the analysis result, including: Obtain a discrete sequence of each parameter variable, perform power spectrum analysis on each parameter variable according to the discrete sequence, and obtain analysis results; Determine the actual distribution state of each parameter variable according to the analysis results, and determine the distribution function equation of each parameter variable according to the actual distribution state; The distribution function equation of each parameter variable is analyzed according to different power station types to obtain the probability distribution state of all basic data of each parameter variable; Obtain the rated standard of each parameter variable under each probability distribution state and set it as the standard fixed-rate operation and maintenance fee of each parameter variable; A dynamic cost change probability model for each parameter variable is constructed based on the standard fixed operation and maintenance costs of each parameter variable under each probability distribution state and the probability distribution state of basic data.

5. The new energy station operation and maintenance cost assessment method based on business classification and prediction model according to claim 1 is characterized in that: The method of constructing an operation and maintenance variable coupling time series prediction model based on time series analysis and high-frequency dynamic algorithm according to the correlation coefficient between the core parameter variables and the non-core parameter variables and the cost dynamic change probability model of each parameter variable includes: Obtain the mathematical model relationship between core parameter variables and non-core parameter variables through non-linear models; According to the mathematical model relationship, the correlation coefficient between the core parameter variables and the non-core parameter variables is determined through the probability density function equation; Extract the trend, linear and periodic change data features corresponding to the time series data of each parameter variable; According to the data characteristics and the correlation coefficients between the core parameter variables and the non-core parameter variables and the probability model of the dynamic change of the cost of each parameter variable, a rolling prediction model of the autoregression and high-frequency dynamic change of each parameter variable is constructed.

6. The new energy station operation and maintenance cost assessment method based on business classification and prediction model according to claim 1 is characterized in that: The operation and maintenance cost estimation value of each parameter variable under the current probability condition parameter is determined by coupling the operation and maintenance variable with the time series prediction model, including: The operation and maintenance cost estimation prediction value range of each parameter variable under different probability conditions is determined through the operation and maintenance variable coupling time series prediction model; Obtain the current probability condition parameters, and determine the operation and maintenance cost probability curve of each parameter variable under the current probability condition parameters according to the current probability condition parameters and the operation and maintenance cost estimation prediction value interval of each parameter variable under different probability conditions; Determine the estimated value of the operation and maintenance cost under different probabilities under the current condition parameters of each parameter variable according to the operation and maintenance cost probability curve; Based on the estimated values ​​of operation and maintenance costs under different probabilities under the current condition parameters of each parameter variable and the basic information, personnel information and asset information of the new energy station, a cost assessment report is generated through a preset cost assessment model.

7. The new energy station operation and maintenance cost assessment method based on business classification and prediction model according to claim 1 is characterized in that: Also includes: Generate periodic evaluation data for each parameter variable through the operation and maintenance variable coupling time series prediction model; Import periodic evaluation data and actual cost statistics into the operation and maintenance variable coupling time series forecasting model and compare them to obtain Gaussian distribution; The prediction accuracy is determined according to the Gaussian distribution, and the offset probability number is added to the parameter value of the operation and maintenance variable coupling time series prediction model according to the prediction accuracy to complete the parameter tuning.

8. The new energy station operation and maintenance cost assessment method based on business classification and prediction model according to claim 4 is characterized in that: Determining the actual distribution state of each parameter variable according to the analysis results includes: Determine the data range of each parameter variable based on the analysis results, and determine the data jump frequency based on the data range; The discrete sequence data of each parameter variable is divided into several unit arrays based on the data jump frequency; Determine the array boundaries of each unit array and compile a frequency distribution table based on the data boundaries; Determine the actual distribution status of each parameter variable based on the frequency distribution table.

9. The new energy station operation and maintenance cost assessment method based on business classification and prediction model according to claim 1 is characterized in that: Also includes: Collect geographical environment parameters around the construction site of new energy stations and determine the operation and maintenance difficulty index based on the geographical environment parameters; Set the geographical environment coefficient of new energy stations based on the operation and maintenance difficulty index and the conversion rules between the geographical environment coefficient and freight costs; According to the conversion rules, the estimated value of the operation and maintenance costs of the new energy station is calculated to obtain the final cost assessment value.

Images