Wind power generation industry carbon emission assessment method and related device

Abstract

The invention relates to a wind power generation industry carbon emission assessment method and a related device. The wind power generation industry carbon emission assessment method comprises the steps of S1, collecting carbon emission data, economic data and energy data of a full life cycle of a multi-region wind power industry as an initial data set; s2, preprocessing data in the initial data set by adopting a data cleaning and data estimation method to obtain a target data set; s3, constructing a wind power generation carbon emission evaluation model based on the target data set, and evaluating the carbon emission condition of wind power generation; and S4, performing uncertainty analysis on the calculation result of the wind power generation carbon emission evaluation model, and evaluating the influence of data acquisition and model hypothesis factors on the result. According to the method, uncertainty analysis is carried out on the model calculation result, influences of factors such as data acquisition and model hypothesis are fully considered, the reliability degree of the result is determined, and the effects of accurately reflecting the actual carbon emission condition of wind power generation and accurately evaluating the carbon emission result of the wind power industry are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a wind power industry carbon emission evaluation method and related device. BACKGROUND

[0002] The wind power industry is a renewable energy industry that utilizes natural wind energy to convert the kinetic energy of wind into electrical energy through wind turbines. It has the advantages of being clean, renewable, low-carbon, and environmentally friendly, and is of great significance for optimizing energy structure, reducing carbon emissions, promoting energy transition, and sustainable development.

[0003] At present, the carbon emission evaluation of the wind power industry is mostly based on the life cycle framework. Some typical regions or specific projects are usually selected to collect carbon emission data at the production, construction, and operation and maintenance stages. Some may include economic and energy-related data, but the coverage is limited and the update frequency is low. In data processing, simple filtering is used to remove obvious error values, and missing data is often directly excluded or filled with fixed values.

[0004] However, the evaluation of carbon emissions of the wind power industry fails to collect multi-regional life cycle carbon emissions, economic and energy data, lacks systematic cleaning and estimation methods for data preprocessing, and the evaluation model is not based on an effectively preprocessed data set. Moreover, the model calculation results are not analyzed for uncertainty factors such as data collection and model assumptions, making it difficult to accurately reflect the actual carbon emissions of wind power and obtain accurate carbon emission evaluation results of the wind power industry. SUMMARY

[0005] Based on the above problems in the prior art, the purpose of the embodiments of the present application is to provide a wind power industry carbon emission evaluation method and related device.

[0006] To achieve the above purpose, the present application adopts the following technical solutions:

[0007] A wind power industry carbon emission evaluation method, comprising:

[0008] S1, collecting multi-regional wind power industry life cycle carbon emission data, economic data and energy data as an initial data set;

[0009] S2, using data cleaning and data estimation methods to preprocess the data in the initial data set to obtain a target data set;

[0010] S3, constructing a wind power carbon emission evaluation model based on the target data set to evaluate the carbon emission of wind power;

[0011] S4, performing uncertainty analysis on the wind power carbon emission evaluation model calculation results to evaluate the influence of data collection and model assumption factors on the results.

[0012] The further improvement of the present application is that the collection of the carbon emission data, economic data and energy data of the whole life cycle of the multi-region wind power industry in S1 includes that the carbon emission data includes three aspects of data of the construction phase, operation phase and decommissioning phase; the economic data includes individual data of the wind power plant and regional industry data; and the energy data includes wind energy resource assessment data and power generation and energy substitution data.

[0013] The further improvement of the present application is that the data preprocessing of the data in the initial data set by using the data cleaning and data estimation method in S2 includes:

[0014] The data in the initial data set is identified for abnormal values by using a combination of the 3σ principle based on the statistical principle and the Isolation Forest algorithm.

[0015] The further improvement of the present application is that the initial data set after the abnormal value identification is standardized by using the Z-score standardization.

[0016] The further improvement of the present application is that the values after the data standardization are processed and compressed by using the Min-Max standardization.

[0017] The further improvement of the present application is that the carbon emission evaluation model of wind power generation is constructed based on the target data set in S3, and the carbon emission situation of wind power generation is evaluated, including that the Leontief inverse matrix model is introduced in the carbon emission evaluation model of wind power generation.

[0018] The further improvement of the present application is that the random forest algorithm is introduced to reduce the risk of model overfitting and improve the stability of regional carbon emission prediction.

[0019] The further improvement of the present application is that the neural network algorithm is introduced to deeply mine the complex nonlinear relationship contained in the output data of the random forest.

[0020] A wind power industry carbon emission evaluation device, comprising:

[0021] A data acquisition unit acquires carbon emission data, economic data and energy data of the whole life cycle of the multi-region wind power industry as an initial data set;

[0022] A data preprocessing unit preprocesses the data in the initial data set by using a data cleaning and data estimation method to obtain a target data set;

[0023] An evaluation unit constructs a wind power generation carbon emission evaluation model based on the target data set to evaluate the carbon emission situation of wind power generation;

[0024] An analysis unit performs uncertainty analysis on the calculation results of the wind power generation carbon emission evaluation model to evaluate the influence of data acquisition and model assumption factors on the results.

[0025] A network side server, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the wind power industry carbon emission evaluation method.

[0026] A computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of the wind power industry carbon emission evaluation method.

[0027] Compared with the prior art, the present application has at least the following beneficial technical effects:

[0028] The wind power industry carbon emission evaluation method provided by the embodiment of the present application collects carbon emission data, economic data and energy data of a full life cycle of a multi-region wind power industry as an initial data set; adopts a data cleaning and data estimation method to pre-process the data in the initial data set to obtain a target data set; constructs a wind power carbon emission evaluation model based on the target data set to evaluate the carbon emission of wind power; and performs uncertainty analysis on the calculation result of the wind power carbon emission evaluation model to evaluate the influence of data collection and model assumption factors on the result, so that the influence of data collection, model assumption and other factors is fully considered through the uncertainty analysis on the calculation result of the model, the reliability of the result is determined, and the effect of accurately reflecting the actual carbon emission of wind power and accurately evaluating the carbon emission result of the wind power industry is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the specific embodiments or the prior art, the drawings needed in the specific embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0030] Figure 1 A flowchart of the wind power industry carbon emission evaluation method in the present application.

[0031] Figure 2 A structural schematic diagram of the network side server provided by the second embodiment of the present application.

[0032] Figure 3 A structural block diagram of the wind power industry carbon emission evaluation device in the present application. DETAILED DESCRIPTION

[0033] In the following, only certain exemplary embodiments are simply described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the present application. Therefore, the drawings and description are to be regarded as illustrative in nature rather than restrictive.

[0034] In the description of the present application, it is to be understood that the terms "including", "comprising", "having" and "with" when used in this specification and in the following claims indicate the presence of the stated features, integers, steps, operations, elements, and / or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0035] It is also to be understood that the terminology used in the description of the present application is for the purpose of describing certain embodiments only and is not intended to be limiting of the present application. As used in this description and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0036] It will be further understood that the terms "and / or", as used in the specification and in the claims, mean one and / or any combination of the associated listed items can be present and all possible combinations thereof.

[0037] In the drawings, various structural schematic diagrams of the disclosed embodiments according to the present application are shown. These diagrams are not drawn to scale, in which certain details are exaggerated for clarity of presentation and can omit certain details. The shapes and relative sizes of the various regions, layers, and their relative positions illustrated in the drawings are merely exemplary and can deviate in actuality due to manufacturing tolerances or technical limitations, and regions / layers with different shapes, sizes, relative positions can be additionally designed by those skilled in the art according to actual needs.

[0038] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0039] The embodiment of the application provides a wind power industry carbon emission evaluation method, which collects carbon emission data, economic data and energy data of a full life cycle of a multi-region wind power industry as initial data sets; data in the initial data sets is preprocessed by adopting a data cleaning and data estimation method to obtain target data sets; a wind power carbon emission evaluation model is constructed based on the target data sets, and carbon emission of wind power is evaluated; uncertainty analysis is performed on a calculation result of the wind power carbon emission evaluation model, and influence of data collection and model assumption factors on the result is evaluated, carbon emission, economy and energy data of a full life cycle of a multi-region wind power industry are collected, a wide coverage and rich dimensions are provided, comprehensive basic data are provided for evaluation, and evaluation deviation caused by data loss is reduced. In the preprocessing stage, the data cleaning and estimation method is adopted, error and redundant data are effectively removed, and missing data is supplemented, data quality is further improved, and accuracy of subsequent evaluation is ensured. The evaluation model is constructed based on the high-quality target data sets after preprocessing, the actual situation of carbon emission of wind power can be more accurately reflected, the evaluation result is more valuable, and a reliable basis is provided for carbon emission management of the wind power industry. The uncertainty analysis is performed on the calculation result of the model, influence of data collection, model assumption and other factors is fully considered, reliability of the result is determined, the actual situation of carbon emission of wind power is accurately reflected, and the effect of accurately evaluating the carbon emission result of the wind power industry is achieved.

[0040] The implementation details of the wind power industry carbon emission evaluation method of the embodiment are specifically described below, and the following content is only provided for the implementation details for the convenience of understanding, and is not necessary for implementing the scheme.

[0041] Embodiment 1

[0042] Referring to Figure 1 The wind power industry carbon emission evaluation method provided by the application comprises the following steps.

[0043] S1, collecting carbon emission data, economic data and energy data of a full life cycle of a multi-region wind power industry as initial data sets.

[0044] Specifically, the carbon emission data includes three aspects of data in a construction stage, an operation stage and a decommissioning stage.

[0045] In the construction stage, direct carbon emission in production processes of steel, composite materials and electronic components and indirect carbon emission in smelting and chemical production processes need to be counted in the equipment manufacturing link; in the transportation and installation stage, land transportation and sea transportation distances of wind turbine components from a factory to a wind farm, fuel consumption of different transportation tools (such as heavy trucks and special ships) and corresponding carbon emission intensities need to be considered.

[0046] Operation stage: Fan maintenance involves operations such as lubricating oil replacement, part repair or replacement, etc. The carbon emissions from lubricating oil production and waste treatment, as well as the carbon footprint of replacing parts throughout their life cycle, need to be recorded. At the same time, the carbon emissions from the transportation of maintenance personnel and equipment to and from the wind farm should also be included in the statistics.

[0047] Retirement stage: During the disassembly process, not only the carbon emissions generated by the energy consumption of disassembled equipment need to be calculated, but also the carbon emissions difference between material recycling and landfill treatment, such as the impact of carbon fiber blade recycling technology on carbon emissions, need to be evaluated.

[0048] Economic data includes individual wind farm data and regional industry data.

[0049] Individual wind farm: Construction investment costs need to be divided into equipment procurement (wind turbines, tower, power transformation equipment, etc.), land acquisition, infrastructure construction (roads, power transformation stations), etc. Maintenance costs during the operation period include regular inspections, fault repairs, and part replacements. Electricity sales revenue is closely related to the on-grid electricity price, electricity sales volume, and power transmission loss. The revenue can be calculated based on different electricity trading market mechanisms (such as long-term trading, spot trading).

[0050] Regional industry: Employment benefits can be calculated based on job types (technical research and development, engineering construction, operation and management, etc.) and employment duration to calculate the number of jobs created. Tax benefits include corporate income tax, value-added tax, and land use tax, etc. to analyze the direct contribution of wind power enterprises to local finance. At the same time, the economic driving effect of wind power industry on upstream and downstream supporting enterprises (such as blade manufacturing and wind power operation and maintenance services) is further increased.

[0051] Energy data includes wind energy resource assessment data and power generation and energy substitution data.

[0052] Wind energy resource assessment: In addition to basic data such as wind speed, wind direction, and wind power density, the impact of turbulence intensity and wind shear index on wind turbine power generation efficiency needs to be considered. Long-term meteorological observation data combined with numerical simulation are used to establish a high-resolution wind energy resource map to evaluate the potential development value of wind farms.

[0053] Power generation and energy substitution: Record the actual power generation and power generation hours of different types of wind turbines, analyze the impact of seasonal and climatic factors on power generation fluctuations, and compare with traditional energy sources. When comparing with traditional energy sources, the coal consumption rate and carbon emission factor of thermal power, the submerged area and ecological impact of hydropower, and the environmental benefits of wind power in reducing fossil energy consumption and reducing greenhouse gas emissions are quantified. Carbon emission data collection in the production stage needs to be refined to the energy consumption and emissions of each type of raw material (such as rare earth permanent magnet materials used in generator manufacturing) mining, processing, and energy use during the assembly process of parts.

[0054] S2, pre-process the data in the initial data set by data cleaning and data estimation to obtain a target data set;

[0055] Step S21, identify the abnormal values in the initial data set by combining the 3σ principle based on statistical principles with the Isolation Forest algorithm.

[0056] 3σ principle: if the data follows a normal distribution, the data outside the range of mean ± 3 times standard deviation is considered as abnormal value, the specific formula is:

[0057] Lower Limit=μ-3σ

[0058] Upper Limit=μ+3σ

[0059] Where Lower Limit represents the lower limit of the data, i.e. the minimum value boundary of the normal data, Upper Limit represents the upper limit of the data, i.e. the maximum value boundary of the normal data, μ is the sample mean, representing the average level of the data, σ is the sample standard deviation, used to measure the dispersion degree of the data, the larger the value, the more dispersed the data, 3 is the multiple coefficient, which is fixed in the 3σ principle, used to define the abnormal value range.

[0060] Isolation Forest algorithm divides the feature space randomly, constructs multiple isolated trees, and the abnormal score of the sample is determined by its path length in the tree, the formula is:

[0061]

[0062] Where S(x,n) represents the abnormal score of sample x under the condition that the sample number is n, the closer the score is to 1, the more likely the sample is an abnormal value, x represents a single sample data, n is the sample number, i.e. the total number of samples participating in the construction of isolated trees, E(h(x)) is the average path length of sample x in all isolated trees, the shorter the path length, the more likely the sample is an abnormal value c(n) is the average path length correction coefficient of the tree, used to normalize the average path length, to ensure the comparability of abnormal scores under different sample numbers, 2 is a fixed constant in the formula.

[0063] Step S22, standardize the initial data set after abnormal value identification by Z-score standardization (data standardization).

[0064] Z-score standardization: map the data in the initial data set after abnormal value identification to a standard normal distribution with mean 0 and standard deviation 1, the formula is:

[0065]

[0066] wherein x ′ represents the data after Z-score standardization, i.e., the new value after Z-score transformation, x is the original data, i.e., the initial data without standardization processing, is the sample mean, used to determine the center position of the data distribution, and σ is the sample standard deviation, used to measure the dispersion degree of the data, and is used as a scaling factor in the standardization process.

[0067] In step S23, the data after standardization is processed and compressed by Min-Max standardization (deviation standardization).

[0068] Min-Max standardization: the data after standardization is compressed to the interval [0, 1], and the formula is:

[0069]

[0070] wherein x ′ represents the data after Min-Max standardization, with a value range of [0, 1], x is the original data after Z-score standardization, max(x) represents the maximum value in the data set, and min(x) represents the minimum value in the data set.

[0071] After preprocessing the data in the initial data set, the target data set is obtained.

[0072] S3, based on the target data set, a wind power carbon emission evaluation model is constructed to evaluate the carbon emission of wind power;

[0073] Step S31, introducing the Leontief inverse matrix model in the wind power carbon emission evaluation model.

[0074] Specifically, by introducing the Leontief inverse matrix model in the wind power carbon emission evaluation model, a regional linkage model is constructed based on mathematical modeling, revealing the upstream and downstream roles of different regions in the wind power industry supply chain, resource flow paths and economic contribution degrees.

[0075] In one embodiment, the Leontief inverse matrix model clearly identifies which regions mainly undertake wind power equipment manufacturing and which regions focus on power consumption, thereby providing data support for optimizing industrial layout and formulating low-carbon collaborative policies.

[0076] The formula of the Leontief inverse matrix is:

[0077] B=(I-A) -1

[0078] wherein B represents the Leontief inverse matrix, I is the unit matrix, and A is the direct consumption coefficient matrix.

[0079] The basic component formula of the carbon emission evaluation system is:

[0080]

[0081] wherein a ij Generally represents the direct consumption coefficient in input-output analysis, x ij represents the consumption of the product of the i-th department when the j-th department produces, x j represents the total output of the j-th department.

[0082] The basic component formula of the carbon emission evaluation system quantifies the direct consumption relationship between departments, mathematically relating economic activities and energy consumption.

[0083] The mutual influence between regional energy and economic activities is quantified by calculating the product of B and the final demand vector Y, i.e. X = BY, X representing the target variable or the result vector to be solved.

[0084] In step S32, the random forest algorithm is introduced to reduce the risk of model overfitting and improve the stability of regional carbon emission prediction.

[0085] Specifically, after using the Leontief inverse matrix formula to process the economic data related to the wind power industry, the carbon emission correlation matrix between industry departments is obtained. This matrix is integrated with the cleaned and standardized historical carbon emission data and the corresponding regional feature vector as input, and the prediction result is obtained through the random forest algorithm.

[0086] At the level of the random forest algorithm, a feature random selection strategy is introduced, that is, at each node of each decision tree, only the optimal feature is selected from a random subset of all features for splitting, rather than traversing all features.

[0087] In one embodiment, if there are N features in total, randomly select features as a candidate set, further enhancing the diversity of the model, avoiding the over-reliance of a single decision tree on some dominant features, thereby reducing the variance of the random forest model, reducing the risk of overfitting, and improving the generalization ability and stability of the model for regional carbon emission prediction.

[0088] The processed historical carbon emission data and the corresponding regional feature vector are used as input. During the model training process, multiple training sets are constructed through bootstrap sampling, and each training set is used to train a decision tree. When the decision tree node is split, the Gini impurity is used as the feature selection standard, and the calculation formula is:

[0089]

[0090] wherein Gini(t) represents the Gini coefficient at time t, t is a node, K is the number of classes, p t,k is the proportion of samples belonging to class k in node t,

[0091] The final prediction result is obtained through the voting mechanism of multiple decision trees (classification problem) or mean calculation (regression problem), which further reduces the risk of model overfitting and improves the stability of regional carbon emission prediction.

[0092] Step S33, the complex nonlinear relationship contained in the random forest output data is deeply mined by introducing a neural network algorithm.

[0093] Specifically, taking a multi-layer perception (MLP) as an example, it is assumed that the number of input layer neurons is determined as n according to the number of input features, the number of hidden layer neurons is set as m, and the number of output layer neurons is set as p according to the specific task (such as the number of carbon emission prediction values), the weight matrix w1 from the input layer to the hidden layer, the bias vector b1, and the weight matrix w2 from the hidden layer to the output layer, and the bias vector b2 are defined.

[0094] The prediction result of the model input data is calculated by forward propagation, and the formula is as follows:

[0095] h = σ (W1x + b1)

[0096] wherein x is an input vector, representing the original data input to the neural network, w1 is the weight matrix from the input layer to the hidden layer, b1 is the bias vector of the hidden layer, σ is the activation function using the rectified linear unit (Rectified Linear Unit), and h is the result of the hidden layer neuron processing the input data.

[0097] y = W2h + b2

[0098] wherein w2 is the weight matrix from the hidden layer to the output layer, b2 is the bias vector of the output layer, and y is the final output layer prediction value.

[0099] The neural network algorithm deeply mines the complex nonlinear relationship contained in the random forest output data through the above processing steps. For example, the complex correlation between the degree of equipment aging in the operation and maintenance phase, the feature importance evaluated by the random forest, and the carbon emission, so as to more accurately evaluate the carbon emission of the wind power industry and provide a reliable basis for energy saving and emission reduction decision-making.

[0100] S4, the uncertainty analysis of the wind power carbon emission evaluation model calculation result is carried out, and the influence of the data collection and model assumption factors on the result is evaluated.

[0101] Specifically, in the wind power carbon emission assessment, there are many potential variables in the data collection and model assumption link. In order to ensure the reliability of the assessment results, systematic uncertainty analysis needs to be carried out.

[0102] In terms of data collection, measurement errors, statistical deviations or missing values of raw data such as equipment life cycle energy consumption data, raw material production carbon emission coefficient and operation activity frequency may all lead to deviation from the true value; in terms of model assumption, subjective setting of key parameters such as technical evolution path, regional energy structure change and carbon capture efficiency will all introduce uncertainty.

[0103] Monte Carlo simulation is used to quantify the above influences. By setting the probability distribution of each input variable (such as normal distribution, triangular distribution), a large number of input combinations are generated based on random sampling, and the result probability distribution is formed through model iterative calculation, which intuitively shows the result fluctuation range and confidence interval, calculates the influence coefficient of each input variable change on the output result, draws the sensitivity curve, locates the variables that affect the carbon emission assessment results more than the threshold, and comprehensively evaluates the influence of data collection and model assumption factors on the results, thereby effectively improving the reliability of the assessment results.

[0104] The wind power carbon emission assessment method provided by the embodiment of the application collects carbon emission data, economic data and energy data of the wind power industry in multiple regions throughout the life cycle as initial data sets; uses data cleaning and data estimation methods to preprocess the data in the initial data sets to obtain target data sets; constructs a wind power carbon emission assessment model based on the target data sets to assess the carbon emission of wind power; and performs uncertainty analysis on the calculation results of the wind power carbon emission assessment model to evaluate the influence of data collection and model assumption factors on the results. By collecting carbon emission, economic and energy data of the wind power industry in multiple regions throughout the life cycle, the coverage is wide and the dimension is rich, which provides comprehensive basic data for the assessment and reduces the assessment deviation caused by data missing. In the preprocessing stage, the data cleaning and estimation methods are used to effectively remove errors and redundant data and supplement missing data, further improving the data quality and ensuring the accuracy of the subsequent assessment. Based on the high-quality target data sets obtained after preprocessing, the assessment model is constructed, which can more accurately reflect the actual carbon emission of wind power, making the assessment results more valuable and providing a reliable basis for carbon emission management of the wind power industry. The uncertainty analysis of the calculation results of the model fully considers the influence of data collection, model assumption and other factors, and clearly defines the reliability of the results.

[0105] Example 2

[0106] As Figure 2As shown, the network side server provided by the present application comprises at least one processor 302; and a memory 301 connected with the at least one processor 302 in communication; wherein the memory 301 stores instructions executable by the at least one processor 302, and the instructions are executed by the at least one processor 302 to enable the at least one processor 302 to execute the data processing method described above.

[0107] The memory 301 and the processor 302 are connected in a bus manner, the bus can include any number of interconnected buses and bridges, and the bus connects one or more processors 302 and various circuits of the memory 301 together. The bus can also connect various other circuits such as peripheral devices, voltage stabilizers and power management circuits together, which are well known in the art, and therefore, further description thereof will not be given herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements such as multiple receivers and transmitters, which provide units for communicating with various other devices on the transmission medium. The data processed by the processor 302 is transmitted on the wireless medium through the antenna, and further, the antenna also receives data and transmits the data to the processor 302.

[0108] The processor 302 is responsible for managing the bus and general processing, and can also provide various functions including timing, peripheral interface, voltage regulation, power management and other control functions. And the memory 301 can be used to store the data used by the processor 302 in executing operations.

[0109] Embodiment 3

[0110] As shown, the wind power industry carbon emission evaluation device provided by the present application comprises: Figure 3 A data acquisition unit acquires carbon emission data, economic data and energy data of a multi-region wind power industry throughout a life cycle as an initial data set;

[0111] A data preprocessing unit pre-processes the data in the initial data set by using a data cleaning and data estimation method to obtain a target data set;

[0112] An evaluation unit constructs a wind power carbon emission evaluation model based on the target data set to evaluate the carbon emission of wind power generation;

[0113] An analysis unit performs uncertainty analysis on the calculation results of the wind power carbon emission evaluation model to evaluate the influence of data acquisition and model assumption factors on the results.

[0114] Embodiment 3

[0115]

[0116] ​The application provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to realize the wind power generation industry carbon emission evaluation method in the first embodiment.

[0117] Those skilled in the art will appreciate that embodiments of the application can be supplied as methods, systems, or computer program products. Accordingly, the application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can be embodied in the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk memory, CD-ROM, optical memory, etc.) having computer usable program code embodied therein.

[0118] The application is described with reference to flowcharts and / or block diagrams of methods, systems and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing apparatus, generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 a system to perform the functions specified in one or more flows and / or blocks.

[0119] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer readable memory produce a manufacture product including an instruction device, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 a system to perform the functions specified in one or more flows and / or blocks.

[0120] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a process for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 a system to perform the functions specified in one or more flows and / or blocks.

[0121] The foregoing merely illustrates the principles of the application and application of its leading features. This application is not limited to the exact details shown above and described herein, and obvious modifications will occur to those skilled in the art upon reading the foregoing description. Therefore, the scope of the application is not to be determined by such specific details but only by the claims which follow, and any equivalents thereof. Any figure reference herein shall not be construed as limiting the scope of the claims to which it is directed.

[0122] Furthermore, it should be understood that although the description above relates to embodiments, not every embodiment contains only one independent technical solution, and the description above is only for the sake of clarity, and those skilled in the art should understand the description as a whole, and the technical solutions in each embodiment can be appropriately combined to form other embodiments that those skilled in the art can understand. The above is only to illustrate the technical idea of the present application, and cannot limit the protection scope of the present application. Any modification made on the basis of the technical solutions according to the present application falls within the protection scope of the claims of the present application.

Claims

1. A method for assessing carbon emissions of the wind power industry, characterized in that, The method comprises the following steps: S1, collecting carbon emission data, economic data and energy data of the whole life cycle of the multi-region wind power industry as an initial data set; S2, pre-processing the data in the initial data set by using data cleaning and data estimation methods to obtain a target data set; S3, constructing a wind power carbon emission evaluation model based on the target data set to evaluate the carbon emission of wind power generation; S4, performing uncertainty analysis on the calculation results of the wind power carbon emission evaluation model to evaluate the influence of data collection and model assumption factors on the results.

2. The method for evaluating carbon emissions of the wind power industry according to claim 1, characterized in that, In S1, the carbon emission data, economic data and energy data of the whole life cycle of the multi-region wind power industry are collected, including: carbon emission data including three aspects of construction phase, operation phase and decommissioning phase; economic data including individual data of wind farms and regional industry data; and energy data including wind energy resource assessment data and power generation and energy substitution data.

3. The method of claim 2, wherein, In S2, the data in the initial data set is pre-processed by using data cleaning and data estimation methods, including: Using a combination of the 3σ principle based on statistical principles and the Isolation Forest algorithm to identify outliers in the initial data set.

4. The method of claim 3, wherein the method further comprises: Using Z-score standardization to standardize the initial data set after outlier identification.

5. The method of claim 4, wherein, Using Min-Max standardization to process and compress the values after data standardization.

6. The method of claim 1, wherein, In S3, the wind power carbon emission evaluation model is constructed based on the target data set to evaluate the carbon emission of wind power generation, including: introducing the Leontief inverse matrix model in the wind power carbon emission evaluation model.

7. The method of claim 6, wherein, By introducing the random forest algorithm, the risk of model overfitting is reduced, and the stability of regional carbon emission prediction is improved; By introducing the neural network algorithm, the complex nonlinear relationship contained in the random forest output data is deeply mined.

8. A wind power industry carbon emission assessment device, characterized by, The method comprises: a data collection unit that collects carbon emission data, economic data and energy data of the whole life cycle of the multi-region wind power industry as an initial data set; a data preprocessing unit that pre-processes the data in the initial data set by using data cleaning and data estimation methods to obtain a target data set; an evaluation unit that constructs a wind power carbon emission evaluation model based on the target data set to evaluate the carbon emission of wind power generation; an analysis unit that performs uncertainty analysis on the calculation results of the wind power carbon emission evaluation model to evaluate the influence of data collection and model assumption factors on the results.

9. A network side server, characterized by, The method comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the wind power industry carbon emission evaluation method according to any one of claims 1 to 7.

10. A computer readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the wind power industry carbon emission evaluation method according to any one of claims 1 to 7.

Images