Carbon footprint evaluation method and device

Abstract

The invention relates to the technical field of environment management, and discloses a carbon footprint evaluation method and device, and the method comprises the steps: carrying out the modeling of the probability distribution corresponding to the preprocessed activity data and background data based on a Bayesian statistical model, carrying out the sampling from the posterior distribution of the Bayesian statistical model through a Markov chain Monte Carlo method, and carrying out the sampling of the probability distribution of the Bayesian statistical model, probability distribution corresponding to the activity data is generated, carbon footprint calculation is carried out through target Monte Carlo simulation, random sampling is carried out in the probability distribution, an input variable combination is generated, distribution of carbon footprint calculation results is analyzed, and uncertainty analysis results are obtained; calculating the first-order sensitivity index and the total effect sensitivity index corresponding to the input variables, analyzing key variables in the carbon footprint evaluation result, and generating a global sensitivity analysis result; and constructing a carbon footprint evaluation model based on the uncertainty analysis result and the global sensitivity analysis result, and generating a carbon footprint evaluation result based on the carbon footprint evaluation model.

Description

Technical Field

[0001] The present application relates to the field of environmental management technology, and in particular to a carbon footprint assessment method and device. Background Art

[0002] Carbon footprint assessment is a tool to measure the total amount of greenhouse gases emitted by a product, organization or activity during its life cycle. Carbon footprint assessment is widely used in environmental protection, policy making, corporate management and public awareness raising. Accurate carbon footprint assessment is of great significance to the formulation of emission reduction strategies and environmental policies.

[0003] Traditional carbon footprint assessment methods usually include the following steps: 1. Boundary setting: determine the boundaries of the assessment object, including time boundaries, spatial boundaries and process boundaries; 2. Data collection: collect activity data, emission factors and background data required for the assessment; 3. Carbon emission calculation: based on the collected data, use relevant formulas to calculate greenhouse gas emissions; 4. Result analysis: analyze the assessment results and identify the main sources and influencing factors of carbon emissions. However, carbon footprint assessment involves a large amount of input data and model parameters, which are uncertain and may affect the accuracy and reliability of the assessment results.

[0004] In view of this, how to provide a real-time carbon footprint assessment method and effectively conduct uncertainty and sensitivity analysis has become a technical problem that needs to be urgently solved in carbon footprint assessment. Summary of the invention

[0005] The embodiments of the present application provide a carbon footprint assessment method, a carbon footprint assessment device and a computer storage medium, which are used to solve the problem that uncertainty and sensitivity cannot be analyzed in current carbon footprint assessments.

[0006] In a first aspect of an embodiment of the present application, a carbon footprint assessment method is provided, comprising:

[0007] Collecting activity data and background data corresponding to the carbon footprint activities of the target object in real time, and preprocessing the activity data and the background data;

[0008] Modeling the probability distributions corresponding to the activity data and the background data based on the Bayesian statistical model, sampling from the posterior distribution of the Bayesian statistical model using the Markov chain Monte Carlo method to generate the probability distribution corresponding to the activity data, randomly sampling from the probability distribution through target Monte Carlo simulation to generate input variable combinations for carbon footprint calculation, and obtaining uncertainty analysis results by analyzing the distribution of the carbon footprint calculation results;

[0009] By calculating the first-order sensitivity index and the total effect sensitivity index corresponding to the input variables, analyzing the key variables in the carbon footprint assessment results, and generating global sensitivity analysis results, wherein the key variables are the activity data and background data that have an impact on the assessment results;

[0010] Based on the uncertainty analysis results and the global sensitivity analysis results, a carbon footprint assessment model is constructed, and based on the carbon footprint assessment model, a carbon footprint assessment result is generated.

[0011] In a second aspect of an embodiment of the present application, a carbon footprint assessment device is provided, comprising:

[0012] A preprocessing module is configured to collect activity data and background data corresponding to the carbon footprint activity of the target object in real time, and preprocess the activity data and the background data;

[0013] The first analysis module is configured to model the probability distributions corresponding to the activity data and the background data respectively based on a Bayesian statistical model, sample from the posterior distribution of the Bayesian statistical model using a Markov chain Monte Carlo method to generate a probability distribution corresponding to the activity data, randomly sample from the probability distribution through a target Monte Carlo simulation to generate an input variable combination for carbon footprint calculation, and obtain an uncertainty analysis result by analyzing the distribution of the carbon footprint calculation result;

[0014] A second analysis module is configured to analyze key variables in the carbon footprint assessment result by calculating a first-order sensitivity index and a total effect sensitivity index corresponding to the input variables, and generate a global sensitivity analysis result, wherein the key variables are activity data and background data that have an impact on the assessment result;

[0015] A generation module is configured to construct a carbon footprint assessment model based on the uncertainty analysis result and the global sensitivity analysis result, and generate a carbon footprint assessment result based on the carbon footprint assessment model.

[0016] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned carbon footprint assessment method are implemented.

[0017] The present application provides a carbon footprint assessment method with strong system and versatility, which can be applied to different assessment objects and scenarios and has wide application value. Specifically, first, the activity data and background data corresponding to the carbon footprint activity of the target object are collected in real time, and the activity data and the background data are preprocessed; then, the probability distribution corresponding to the activity data and the background data is modeled based on the Bayesian statistical model, and the Markov chain Monte Carlo method is used to sample from the posterior distribution of the Bayesian statistical model to generate the probability distribution corresponding to the activity data, and through the target Monte Carlo simulation, random sampling is performed in the probability distribution to generate an input variable combination for carbon footprint calculation, and the distribution of the carbon footprint calculation result is analyzed to obtain the uncertainty analysis result; secondly, by calculating the first-order sensitivity index and the total effect sensitivity index corresponding to the input variable, the key variables in the carbon footprint assessment result are analyzed to generate a global sensitivity analysis result, wherein the key variables are the activity data and background data that have an influence on the assessment result; finally, based on the uncertainty analysis result and the global sensitivity analysis result, a carbon footprint assessment model is constructed, and based on the carbon footprint assessment model, a carbon footprint assessment result is generated.

[0018] The carbon footprint method adopted in the embodiment of the present application solves the problems of high computational complexity, difficulty in processing large-scale data, insufficient accuracy and reliability of evaluation results, lack of systematicness and versatility in the prior art through improved Monte Carlo simulation, Bayesian statistical model, adaptive simulation technology and global sensitivity analysis. In addition, the method can be applied to different evaluation objects and scenarios and has wide application value.

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0021] Figure 1 A schematic diagram of a carbon footprint assessment method provided in an embodiment of the present application;

[0022] Figure 2 A schematic diagram of the structure of a carbon footprint assessment device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0024] In traditional carbon footprint assessment methods, input data and model parameters are usually regarded as deterministic values, ignoring the impact of their uncertainty on the assessment results. With the increase in data quality and quantity, uncertainty analysis and sensitivity analysis methods are gradually applied to carbon footprint assessment to improve the accuracy and reliability of the results.

[0025] The existing uncertainty and sensitivity analysis methods mainly include the following:

[0026] The main implementation steps of Monte Carlo simulation include: setting probability distribution for each input variable; generating a large number of input variable combinations through random sampling; calculating carbon footprint for each combination to generate a large number of results; statistically analyzing the distribution characteristics of the results and evaluating uncertainty. However, its disadvantages are: high computational complexity, requiring a lot of computing resources and time, and low efficiency, especially when processing large-scale data.

[0027] The main implementation steps of global sensitivity analysis include: setting different input variable ranges and performing multiple simulation calculations; using Sobol' index or variance decomposition technology to evaluate the relative importance of each input variable to the output result; identifying key influencing factors, and conducting key analysis and optimization. However, its disadvantage is that although it can evaluate the importance of input variables, it also faces the problem of high computational complexity when dealing with complex models and large-scale data.

[0028] The main implementation steps of scenario analysis include: setting different scenarios and changing the values ​​of input variables; calculating the carbon footprint for each scenario and analyzing the changes in the results; comparing the evaluation results under different scenarios and identifying sensitive variables and sources of uncertainty. However, its disadvantages are: scenario analysis depends on the set scenarios, cannot fully quantify uncertainty and sensitivity, and has limited quantitative analysis capabilities for the results.

[0029] In addition, in the Monte Carlo simulation and global sensitivity analysis methods, the structural composition of the technical solution mainly includes the following parts: 1. Data input module: collect and preprocess activity data, emission factors and background data; set the probability distribution or range of input variables. 2. Simulation calculation module: generate a large number of input variable combinations through random sampling (Monte Carlo simulation) or setting variable range (global sensitivity analysis); use the carbon footprint calculation model to calculate each combination. 3. Result analysis module: statistically analyze the distribution characteristics of simulation results and evaluate uncertainty (Monte Carlo simulation); use Sobol' index or variance decomposition technology to evaluate the importance of input variables (global sensitivity analysis). 4. Optimization module: based on result analysis, identify key influencing factors, optimize input data and model parameters; put forward improvement suggestions and optimization measures.

[0030] Based on the current Monte Carlo simulation and global sensitivity analysis method technical solutions, this application proposes an improved carbon footprint assessment method based on uncertainty and sensitivity analysis. By introducing Bayesian statistical models and adaptive simulation technology, the computational complexity is reduced, the accuracy and reliability of the assessment results are improved, and large-scale data can be effectively processed.

[0031] See also Figure 1 , Figure 1 A flow chart of a carbon footprint assessment method provided in an embodiment of the present application. Figure 1 As shown, the specific steps include the following steps.

[0032] Step S102: collecting activity data and background data corresponding to the carbon footprint activity of the target object in real time, and preprocessing the activity data and the background data.

[0033] It should be noted that the activity data here may be data such as energy consumption and electricity usage of a certain enterprise. In the embodiment of the present application, AD is used to represent the activity data.

[0034] The background data here may be data such as emission factors, and the embodiment of the present application uses BD to represent the background data.

[0035] In an embodiment of the present application, the preprocessing of the activity data and the background data includes: filling missing values ​​of the activity data and / or the background data based on the expected value calculated from the observed data according to the Bayesian multiple interpolation method to obtain first activity data and / or first background data; eliminating outliers from the activity data and / or the background data based on the standard deviation method to obtain second activity data and / or second background data; obtaining activity data based on the first activity data and the second activity data, and standardizing the activity data based on the standard deviation and mean corresponding to the activity data; obtaining background data based on the first background data and the second background data, and standardizing the background data based on the standard deviation and mean corresponding to the background data.

[0036] In carbon footprint assessment, data integrity and accuracy are key. This application proposes a set of data collection and preprocessing methods to ensure data quality.

[0037] Among them, the data preprocessing method proposed in this application includes: missing value filling, outlier removal and data standardization.

[0038] Specifically, the missing values ​​in the activity data AD and the background data BD are filled using the Bayesian multiple interpolation method. Taking the activity data AD as an example, the specific method of filling the missing values ​​is as follows:

[0039]

[0040] Among them, IE (ADobserved data) is the expected value calculated based on the observed data.

[0041] For outliers in activity data AD and background data BD, the three-times standard deviation method is used to eliminate outliers. Taking activity data AD as an example, the specific method for eliminating outliers is as follows:

[0042] AD i is an outlier if|AD i -μ AD |>3σAD;

[0043] Among them, μ AD is the mean of the activity data; σAD is the standard deviation of the activity data.

[0044] In order to eliminate the influence between different dimensions, the data is standardized. The method of standardizing the data includes:

[0045] Step S104: Model the probability distributions corresponding to the activity data and the background data respectively based on the Bayesian statistical model, use the Markov chain Monte Carlo method to sample from the posterior distribution of the Bayesian statistical model, generate the probability distribution corresponding to the activity data, perform random sampling in the probability distribution through target Monte Carlo simulation, generate input variable combinations for carbon footprint calculation, and obtain uncertainty analysis results by analyzing the distribution of the carbon footprint calculation results.

[0046] It should be noted that the purpose of uncertainty analysis is to quantify the impact of uncertainty in input variables and model parameters on the carbon footprint calculation results.

[0047] In the embodiments of the present application, on the one hand, a Bayesian statistical model is introduced to model the probability distribution of input data and emission factors; on the other hand, the Markov chain Monte Carlo method is used to sample from the posterior distribution to generate the probability distribution of the input variables; on the other hand, through the improved Monte Carlo simulation, a large number of input variable combinations are generated, the carbon footprint calculation is performed, the distribution characteristics of the results are statistically analyzed, and the uncertainty is comprehensively evaluated.

[0048] Specifically, the probability distributions corresponding to the activity data and the background data are modeled based on a Bayesian statistical model, wherein the Bayesian statistical model includes:

[0049] π(θX)∝π(θ)·L(Xθ)

[0050] Among them, θ is the model parameter (the model parameters here include the probability distribution parameters of activity data and emission factors); π(θ) is the prior distribution (i.e., the initial guess of the model parameters); L(X|θ) is the likelihood function (i.e., the probability of the data given the model parameters); π(θ|X) is the posterior distribution (i.e., the parameter distribution after the data is given).

[0051] The accuracy of input data can be improved by using Bayesian statistical models to model the probability distribution of input data and emission factors.

[0052] A Markov Chain Monte Carlo method (MCMC) is used to sample from the posterior distribution of the Bayesian statistical model to generate a probability distribution corresponding to the activity data, wherein the Markov Chain Monte Carlo method includes:

[0053]

[0054] Among them, θ (t) is the parameter value of the tth iteration; ∈ is the step size; ▽logπ(θ (t) X) is the gradient of the posterior distribution; η is a random variable of standard normal distribution.

[0055] The accuracy of uncertainty analysis can be enhanced by sampling from the posterior distribution through the MCMC method to generate the probability distribution of the input variables.

[0056] Through the target Monte Carlo simulation, random sampling is performed in the probability distribution to generate input variable combinations for carbon footprint calculation, wherein the carbon footprint calculation formula includes:

[0057]

[0058] Among them, CF i is the carbon footprint result of the ith simulation; AD ij is the j-th activity data in the i-th simulation; EF j is the jth background data.

[0059] By improving the Monte Carlo simulation method and combining it with the Bayesian statistical model and adaptive simulation technology, the computational complexity is reduced and the evaluation efficiency is significantly improved. By introducing uncertainty analysis, the uncertainty of input data and model parameters is quantified and evaluated, thereby improving the accuracy and reliability of the evaluation results.

[0060] Step S106: By calculating the first-order sensitivity index and the total effect sensitivity index corresponding to the input variables, the key variables in the carbon footprint assessment result are analyzed to generate a global sensitivity analysis result, wherein the key variables are the activity data and background data that have an impact on the assessment result.

[0061] It should be noted that global sensitivity analysis is used to identify the key variables that have the greatest impact on the carbon footprint assessment results.

[0062] In the embodiment of the present application, on the one hand, the Sobol' index and variance decomposition technology are used to quantify the relative importance of input variables to output results, analyze the key variables in carbon footprint assessment, and identify the key variables that have the greatest impact on the assessment results; on the other hand, global sensitivity analysis is used to identify the key variables that have the greatest impact on the assessment results, and the model is optimized based on this.

[0063] Specifically, based on the first-order sensitivity index calculation formula, the first-order sensitivity index corresponding to the input variable is calculated, wherein the first-order sensitivity index calculation formula includes:

[0064]

[0065] Among them, S i The input variable X i The first-order sensitivity index of; V(Y) is the total variance of the output result Y; The input variable X i The variance contribution of .

[0066] Based on the total effect sensitivity index calculation formula, the total effect sensitivity index corresponding to the input variable is calculated, wherein the total effect sensitivity index calculation formula includes:

[0067]

[0068] Among them, S Ti The input variable X i The total effect sensitivity index of; V(Y) is the total variance of the output result Y; is the variance contribution of other variables except Xi.

[0069] Based on the first-order sensitivity index and the total effect sensitivity index, the key variables in the carbon footprint assessment result are analyzed, and the global sensitivity analysis result is generated by analyzing the initial samples corresponding to the input variables and the disturbance samples corresponding to the key variables.

[0070] Specifically, the Sobol' sequence is used to generate sampling points X and X', and the first-order sensitivity index Y and the total effect sensitivity index Y' are calculated, where Y = f(X); Y' = f(X'), where X is the initial sample of the input variable; and X' is the perturbation sample of the input variable.

[0071] Step S108: constructing a carbon footprint assessment model based on the uncertainty analysis result and the global sensitivity analysis result, and generating a carbon footprint assessment result based on the carbon footprint assessment model.

[0072] Based on the results of uncertainty analysis and global sensitivity analysis, the carbon footprint assessment model is optimized to improve the accuracy and reliability of the assessment.

[0073] Firstly, the probability distribution and interaction of key variables are introduced, the carbon footprint calculation formula is optimized, and the probability distribution and interaction of key variables are introduced.

[0074] Specifically, based on the probability distribution and mutual relationship of the key variables generated in the carbon footprint assessment results, the carbon footprint calculation formula is optimized, wherein the optimized carbon footprint calculation formula includes:

[0075]

[0076] Among them, CF is carbon footprint; AD j is the jth activity data; EF j is the jth background data; AD k is the kth activity data; EF i is the i-th background data; β kl For variable AD k and EF l The interaction coefficient between .

[0077] Secondly, the adaptive step-size algorithm is used to dynamically adjust simulation parameters and sampling strategies to improve computational efficiency.

[0078] Specifically, the simulation parameters and sampling strategy of the optimized carbon footprint calculation formula are adjusted by using an adaptive step size algorithm to generate a carbon footprint assessment result, wherein the adaptive step size algorithm includes:

[0079] Δt i+1 =Δt i +η·(∈ i -∈ target )

[0080] Among them, Δt i is the step size of the i-th iteration; η is the learning rate; ∈ i is the current error; ∈ target is the target error.

[0081] In another embodiment, the method further includes: generating improvement measures by analyzing the assessment results and the original assessment results. That is, based on the carbon footprint assessment results, specific measures and decision-making methods for reducing carbon emissions are eliminated, the carbon footprint assessment method is applied to actual enterprise cases, and the effect of the method is evaluated by comparing the carbon emission data before and after the application.

[0082] Taking the carbon footprint assessment of a certain enterprise as an example, the enterprise's activity data AD such as energy consumption and electricity usage are collected, and missing values ​​are filled, outliers are eliminated and data is standardized; Bayesian statistical modeling is performed on the enterprise's activity data and emission factors, and the MCMC method is used to sample from the posterior distribution to generate the probability distribution of input variables, and carbon footprint calculation and uncertainty quantification are performed; the Sobol' index is used to analyze the key variables in the enterprise's carbon footprint assessment, and the activity data and emission factors that have the greatest impact on the assessment results are identified; based on the results of uncertainty and sensitivity analysis, the carbon footprint assessment model is optimized, the probability distribution and interaction of key variables are introduced, and the simulation parameters and sampling strategies are adjusted to improve the accuracy and reliability of the assessment; based on the optimized carbon footprint assessment results, specific measures and decision-making recommendations for reducing carbon emissions are proposed to help enterprises formulate practical emission reduction plans.

[0083] The carbon footprint method adopted in the embodiment of the present application solves the problems of high computational complexity, difficulty in processing large-scale data, insufficient accuracy and reliability of evaluation results, lack of systematicness and versatility in the prior art through improved Monte Carlo simulation, Bayesian statistical model, adaptive simulation technology and global sensitivity analysis. In addition, the method can be applied to different evaluation objects and scenarios and has wide application value.

[0084] Corresponding to the above method embodiment, this specification also provides a carbon footprint assessment device embodiment, Figure 2 This is a schematic diagram of the structure of a carbon footprint assessment device provided in an embodiment of the present application. Figure 2 As shown, the device 200 includes:

[0085] The preprocessing module 202 is configured to collect activity data and background data corresponding to the carbon footprint activity of the target object in real time, and preprocess the activity data and the background data;

[0086] The first analysis module 204 is configured to model the probability distributions corresponding to the activity data and the background data respectively based on the Bayesian statistical model, sample from the posterior distribution of the Bayesian statistical model using the Markov chain Monte Carlo method to generate the probability distribution corresponding to the activity data, randomly sample from the probability distribution through target Monte Carlo simulation to generate input variable combinations for carbon footprint calculation, and obtain uncertainty analysis results by analyzing the distribution of the carbon footprint calculation results;

[0087] The second analysis module 206 is configured to analyze the key variables in the carbon footprint assessment result by calculating the first-order sensitivity index and the total effect sensitivity index corresponding to the input variables, and generate a global sensitivity analysis result, wherein the key variables are the activity data and background data that have an impact on the assessment result;

[0088] The generation module 208 is configured to construct a carbon footprint assessment model based on the uncertainty analysis result and the global sensitivity analysis result, and generate a carbon footprint assessment result based on the carbon footprint assessment model.

[0089] In an optional embodiment, the preprocessing module 202 is further configured to:

[0090] According to the Bayesian multiple interpolation method, based on the expected value calculated from the observed data, the missing values ​​of the activity data and / or the background data are filled to obtain the first activity data and / or the first background data;

[0091] Based on the standard deviation method, outliers are eliminated from the activity data and / or the background data to obtain second activity data and / or second background data;

[0092] Obtaining activity data according to the first activity data and the second activity data, and performing standardization processing on the activity data based on a standard deviation and a mean value corresponding to the activity data;

[0093] Background data is obtained according to the first background data and the second background data, and the background data is standardized based on a standard deviation and a mean value corresponding to the background data.

[0094] In an optional embodiment, the first analysis module 204 is further configured to:

[0095] Modeling the probability distributions corresponding to the activity data and the background data respectively is performed based on a Bayesian statistical model, wherein the Bayesian statistical model includes:

[0096] π(θX)∝π(θ)·L(Xθ)

[0097] Among them, θ is the model parameter; π(θ) is the prior distribution; L(X|θ) is the likelihood function; π(θ|X) is the posterior distribution;

[0098] The Markov chain Monte Carlo method is used to sample from the posterior distribution of the Bayesian statistical model to generate a probability distribution corresponding to the activity data, wherein the Markov chain Monte Carlo method includes:

[0099]

[0100] Among them, θ (t) is the parameter value of the tth iteration; ∈ is the step size; ▽logπ(θ (t) X) is the gradient of the posterior distribution; η is a random variable of the standard normal distribution;

[0101] Through the target Monte Carlo simulation, random sampling is performed in the probability distribution to generate input variable combinations for carbon footprint calculation, wherein the carbon footprint calculation formula includes:

[0102]

[0103] Among them, CF i is the carbon footprint result of the ith simulation; AD ij is the j-th activity data in the i-th simulation; EF j is the jth background data.

[0104] In an optional embodiment, the second analysis module 206 is further configured to:

[0105] Based on the first-order sensitivity index calculation formula, the first-order sensitivity index corresponding to the input variable is calculated, wherein the first-order sensitivity index calculation formula includes:

[0106]

[0107] Among them, V(Y) is the total variance of the output result Y; The input variable X i The variance contribution of

[0108] Based on the total effect sensitivity index calculation formula, the total effect sensitivity index corresponding to the input variable is calculated, wherein the total effect sensitivity index calculation formula includes:

[0109]

[0110] Among them, V(Y) is the total variance of the output result Y; is the variance contribution of other variables except Xi;

[0111] Based on the first-order sensitivity index and the total effect sensitivity index, the key variables in the carbon footprint assessment result are analyzed, and the global sensitivity analysis result is generated by analyzing the initial samples corresponding to the input variables and the disturbance samples corresponding to the key variables.

[0112] In an optional embodiment, the generating module 208 is further configured to:

[0113] Based on the probability distribution and mutual relationship of the key variables generated in the carbon footprint assessment results, the carbon footprint calculation formula is optimized, wherein the optimized carbon footprint calculation formula includes:

[0114]

[0115] Among them, CF is carbon footprint; AD j is the jth activity data; EF j is the jth background data; AD k is the kth activity data; EF i is the i-th background data; β kl For variable AD k and EF l The interaction coefficient between ;

[0116] The simulation parameters and sampling strategy of the optimized carbon footprint calculation formula are adjusted by using an adaptive step size algorithm to generate a carbon footprint assessment result, wherein the adaptive step size algorithm includes:

[0117] Δt i+1 =Δt i +η·(∈ i -∈ target )

[0118] Among them, Δt i is the step size of the i-th iteration; η is the learning rate; ∈ i is the current error; ∈ target is the target error.

[0119] In an optional embodiment, the device 200 is further configured to:

[0120] The improvement module 210 is configured to generate improvement measures by analyzing the evaluation results and the original evaluation results.

[0121] The carbon footprint device adopted in the embodiment of the present application solves the problems of high computational complexity, difficulty in processing large-scale data, insufficient accuracy and reliability of evaluation results, lack of systematicness and versatility in the prior art through improved Monte Carlo simulation, Bayesian statistical model, adaptive simulation technology and global sensitivity analysis. In addition, the method can be applied to different evaluation objects and scenarios and has wide application value.

[0122] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the carbon footprint assessment device, since it is basically similar to the carbon footprint assessment method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the carbon footprint assessment method embodiment.

[0123] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned carbon footprint assessment method.

[0124] It should be noted that the above is a description of a specific embodiment of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of the present specification.

[0125] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0126] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A carbon footprint assessment method, characterized in that: include: Collecting activity data and background data corresponding to the carbon footprint activities of the target object in real time, and preprocessing the activity data and the background data; Modeling the probability distributions corresponding to the activity data and the background data based on the Bayesian statistical model, sampling from the posterior distribution of the Bayesian statistical model using the Markov chain Monte Carlo method to generate the probability distribution corresponding to the activity data, randomly sampling from the probability distribution through target Monte Carlo simulation to generate input variable combinations for carbon footprint calculation, and obtaining uncertainty analysis results by analyzing the distribution of the carbon footprint calculation results; By calculating the first-order sensitivity index and the total effect sensitivity index corresponding to the input variables, analyzing the key variables in the carbon footprint assessment results, and generating global sensitivity analysis results, wherein the key variables are the activity data and background data that have an impact on the assessment results; Based on the uncertainty analysis results and the global sensitivity analysis results, a carbon footprint assessment model is constructed, and based on the carbon footprint assessment model, a carbon footprint assessment result is generated.

2. The method according to claim 1, characterized in that The preprocessing of the activity data and the background data includes: According to the Bayesian multiple interpolation method, based on the expected value calculated from the observed data, the missing values ​​of the activity data and / or the background data are filled to obtain the first activity data and / or the first background data; Based on the standard deviation method, outliers are eliminated from the activity data and / or the background data to obtain second activity data and / or second background data; Obtaining activity data according to the first activity data and the second activity data, and performing standardization processing on the activity data based on a standard deviation and a mean value corresponding to the activity data; Background data is obtained according to the first background data and the second background data, and the background data is standardized based on a standard deviation and a mean value corresponding to the background data.

3. The method according to claim 1, characterized in that The method includes: modeling the probability distributions corresponding to the activity data and the background data based on the Bayesian statistical model, sampling from the posterior distribution of the Bayesian statistical model using the Markov chain Monte Carlo method to generate the probability distribution corresponding to the activity data, and randomly sampling from the probability distribution through target Monte Carlo simulation to generate an input variable combination for carbon footprint calculation, including: Modeling the probability distributions corresponding to the activity data and the background data respectively is performed based on a Bayesian statistical model, wherein the Bayesian statistical model includes: π(θX)∝π(θ)·L(Xθ) Among them, θ is the model parameter; π(θ) is the prior distribution; L(X|θ) is the likelihood function; π(θ|X) is the posterior distribution; The Markov chain Monte Carlo method is used to sample from the posterior distribution of the Bayesian statistical model to generate a probability distribution corresponding to the activity data, wherein the Markov chain Monte Carlo method includes: Among them, θ (t) is the parameter value of the tth iteration; ∈ is the step size; is the gradient of the posterior distribution; η is a random variable of the standard normal distribution; Through the target Monte Carlo simulation, random sampling is performed in the probability distribution to generate input variable combinations for carbon footprint calculation, wherein the carbon footprint calculation formula includes: Among them, CF i is the carbon footprint result of the ith simulation; AD ij is the jth activity data in the i-th simulation; EF j is the jth background data.

4. The method according to claim 1, characterized in that: The first-order sensitivity index and the total effect sensitivity index corresponding to the input variables are calculated, and the key variables in the carbon footprint assessment results are analyzed to generate global sensitivity analysis results, including: Based on the first-order sensitivity index calculation formula, the first-order sensitivity index corresponding to the input variable is calculated, wherein the first-order sensitivity index calculation formula includes: Among them, V(Y) is the total variance of the output result Y; The input variable X i The variance contribution of Based on the total effect sensitivity index calculation formula, the total effect sensitivity index corresponding to the input variable is calculated, wherein the total effect sensitivity index calculation formula includes: Among them, V(Y) is the total variance of the output result Y; is the variance contribution of other variables except Xi; Based on the first-order sensitivity index and the total effect sensitivity index, the key variables in the carbon footprint assessment result are analyzed, and the global sensitivity analysis result is generated by analyzing the initial samples corresponding to the input variables and the disturbance samples corresponding to the key variables.

5. The method according to claim 1, characterized in that The step of constructing a carbon footprint assessment model based on the uncertainty analysis result and the global sensitivity analysis result, and generating a carbon footprint assessment result based on the carbon footprint assessment model includes: Based on the probability distribution and mutual relationship of the key variables generated in the carbon footprint assessment results, the carbon footprint calculation formula is optimized, wherein the optimized carbon footprint calculation formula includes: Among them, CF is carbon footprint; AD j is the jth activity data; EF j is the jth background data; AD k is the kth activity data; EF i is the i-th background data; β kl For variable AD k and EF l The interaction coefficient between ; The simulation parameters and sampling strategy of the optimized carbon footprint calculation formula are adjusted by using an adaptive step size algorithm to generate a carbon footprint assessment result, wherein the adaptive step size algorithm includes: Δt i+1 =Δt i +η·(∈ i -∈ target ) Among them, Δt i is the step size of the i-th iteration; η is the learning rate; ∈ i is the current error; ∈ target is the target error.

6. The method according to claim 1, characterized in that The method further comprises: By analyzing the evaluation results and the original evaluation results, improvement measures are generated.

7. A carbon footprint assessment device, characterized in that: include: A preprocessing module is configured to collect activity data and background data corresponding to the carbon footprint activity of the target object in real time, and preprocess the activity data and the background data; The first analysis module is configured to model the probability distributions corresponding to the activity data and the background data respectively based on a Bayesian statistical model, sample from the posterior distribution of the Bayesian statistical model using a Markov chain Monte Carlo method to generate a probability distribution corresponding to the activity data, randomly sample from the probability distribution through a target Monte Carlo simulation to generate an input variable combination for carbon footprint calculation, and obtain an uncertainty analysis result by analyzing the distribution of the carbon footprint calculation result; A second analysis module is configured to analyze key variables in the carbon footprint assessment result by calculating a first-order sensitivity index and a total effect sensitivity index corresponding to the input variables, and generate a global sensitivity analysis result, wherein the key variables are activity data and background data that have an impact on the assessment result; A generation module is configured to construct a carbon footprint assessment model based on the uncertainty analysis result and the global sensitivity analysis result, and generate a carbon footprint assessment result based on the carbon footprint assessment model.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images