A carbon emission influencing factor identification method and system for power transmission and transformation projects
By collecting, detecting, and resampling data to generate an enhanced dataset, a carbon emission calculation model is constructed, which solves the complexity of identifying carbon emission factors in power transmission and transformation projects, and realizes scientific carbon emission reduction management and accurate identification of key factors.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID ECONOMIC TECH RES INST CO LTD
- Filing Date
- 2026-03-13
- Publication Date
- 2026-06-16
AI Technical Summary
Existing methods for identifying carbon emission factors rely heavily on static statistics and expert experience, which are difficult to adapt to the complex scenarios of multi-stage power transmission and transformation projects. This results in a lack of accurate basis for carbon emission reduction strategies and low management efficiency.
Data on carbon emission influencing factors throughout the entire lifecycle of power transmission and transformation projects are collected. An enhanced dataset is generated through distribution consistency detection and resampling. A carbon emission calculation model is constructed to conduct random sampling simulations, quantify the impact of influencing factors at each stage on carbon emissions, and identify key influencing factors.
It enables scientific and efficient management of carbon emissions from power transmission and transformation projects, adapts to complex scenarios at multiple stages, accurately identifies key influencing factors, and provides theoretical support and decision-making basis for carbon emission reduction optimization.
Smart Images
Figure CN122222192A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power transmission and transformation engineering technology, and in particular to a method and system for identifying carbon emission influencing factors in power transmission and transformation engineering. Background Technology
[0002] Against the backdrop of increasing global pressure on climate change, promoting energy structure optimization and carbon emission control has become a national strategic priority. With the continued advancement of new power system construction, power grid companies face the dual challenges of stricter policy regulation and adjustments to electricity pricing mechanisms, necessitating the establishment of a scientific and systematic carbon emission management mechanism.
[0003] Existing methods for identifying carbon emission factors mostly rely on static statistics, expert experience, or qualitative judgments, which are difficult to adapt to the complex scenarios of multi-stage power transmission and transformation projects. This results in a lack of accurate basis for carbon emission reduction strategies and low management efficiency.
[0004] Therefore, how to effectively identify the factors affecting carbon emissions from power transmission and transformation projects and promote the efficient implementation of scientific carbon emission reduction has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention
[0005] This invention provides a method and system for identifying carbon emission influencing factors in power transmission and transformation projects. It addresses how to coordinate data updates, probabilistic simulations, and sensitivity analysis to identify influencing factors, thereby achieving scientific and efficient carbon reduction management of the power grid.
[0006] To address the aforementioned technical problems, embodiments of the present invention provide a method for identifying carbon emission influencing factors in power transmission and transformation projects, comprising: Collect data on carbon emission influencing factors at each stage of the entire life cycle of power transmission and transformation projects; The data on carbon emission influencing factors are subjected to distribution consistency detection, and the data on carbon emission influencing factors are updated based on the detection results; The updated dataset of carbon emission influencing factors is resampled to generate augmented datasets for each stage. Based on the enhanced dataset, construct carbon emission calculation models for each stage, and use the carbon emission calculation models to perform random sampling simulations to obtain the sample sets to be identified for each stage. The impact of each stage's influencing factors on carbon emissions is quantified based on the sample set to be identified, in order to identify the key influencing factors corresponding to each stage.
[0007] Furthermore, the step of performing distribution consistency detection on the carbon emission influencing factor data and updating the carbon emission influencing factor data based on the detection results includes: Based on the data on carbon emission influencing factors, a sliding window and a reference window are defined respectively; The data distribution distance between the sliding window and the reference window is used as a deviation metric to detect drift in the carbon emission influencing factor data. The carbon emission influencing factors data are updated based on the drift detection results.
[0008] Furthermore, updating the carbon emission influencing factor data based on the drift detection results includes: During drift detection, when the data distribution distance exceeds a preset offset threshold, the carbon emission influencing factor data within the sliding window is replaced. When the data distribution distance is detected to be no more than a preset offset threshold, a rolling update is performed on the reference window.
[0009] Furthermore, the updated dataset of carbon emission influencing factors is resampled to generate augmented datasets for each stage, including: The updated dataset of carbon emission influencing factors is assigned weights that follow a Dirichlet distribution, and the sampling probability is defined by the weights. The updated dataset of carbon emission influencing factors is subjected to Bayesian bootstrap resampling using the sampling probability to generate the augmented dataset.
[0010] Furthermore, the step of constructing carbon emission calculation models for each stage based on the enhanced dataset, and using the carbon emission calculation models to perform random sampling simulations to obtain the sample sets to be identified for each stage, includes: Fit the corresponding probability distribution to the influencing factors for each sample point in the enhanced dataset, and construct the carbon emission calculation model that reflects the mapping relationship between the influencing factors and carbon emissions; Input samples are randomly drawn from the probability distribution, and the input samples are substituted into the carbon emission calculation model for simulation to iteratively generate the sample set to be identified.
[0011] Furthermore, the step of quantifying the impact of influencing factors at each stage on carbon emissions based on the sample set to be identified, in order to identify the key influencing factors corresponding to each stage, includes: Based on the sample set to be identified, calculate the first-order partial variance of each influencing factor; The sensitivity index of the influencing factors is defined by the first-order partial variance decomposition, and the sensitivity index is used to characterize the contribution of changes in a single influencing factor to carbon emissions. Factors that cause the sensitivity index to exceed a preset sensitivity threshold are identified as key influencing factors.
[0012] Furthermore, before performing distribution consistency detection on the carbon emission influencing factor data, the method further includes: An interpolation method is introduced to expand the data on the factors influencing carbon emissions.
[0013] Another embodiment of the present invention provides a carbon emission influencing factor identification system for power transmission and transformation projects, comprising: The data acquisition module is used to collect data on carbon emission influencing factors at each stage of the entire life cycle of power transmission and transformation projects; The consistency detection module is used to perform distribution consistency detection on the carbon emission influencing factor data and update the carbon emission influencing factor data based on the detection results. The data augmentation module is used to resample the updated dataset of carbon emission influencing factors to generate augmented datasets for each stage. The sampling module is used to construct carbon emission calculation models for each stage based on the augmented dataset, and to perform random sampling simulations using the carbon emission calculation models to obtain the sample sets to be identified for each stage. The identification module is used to quantify the impact of each stage's influencing factors on carbon emissions based on the sample set to be identified, in order to identify the key influencing factors corresponding to each stage.
[0014] Another embodiment of the present invention provides a computer device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the carbon emission impact factor identification method for power transmission and transformation projects as described above.
[0015] In another embodiment of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, the method for identifying carbon emission influencing factors for power transmission and transformation projects as described above is implemented.
[0016] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following: This invention first collects data on carbon emission influencing factors throughout the entire lifecycle of power transmission and transformation projects, providing comprehensive input for analysis. Then, it performs distribution consistency detection and updates on the data, effectively identifying and adapting to conceptual drift in data distribution, avoiding the failure of subsequent carbon emission calculation models due to changes in engineering conditions. Next, it resamples the updated data to generate an enhanced dataset, significantly improving the problems of sample scarcity and data structure bias. Furthermore, it constructs a carbon emission probability model based on the enhanced set and conducts stochastic simulations, accurately quantifying the carbon emission distribution characteristics under uncertain conditions in power transmission and transformation projects. Finally, it quantifies the influence degree of each factor through sensitivity analysis, achieving accurate identification of key influencing factors and providing theoretical support and decision-making basis for carbon emission reduction optimization. Attached Figure Description
[0017] Figure 1 This is a schematic flowchart of a method for identifying carbon emission influencing factors in power transmission and transformation projects according to one embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of a carbon emission influencing factor identification system for power transmission and transformation projects in one embodiment of the present invention; Figure 3 This is a structural block diagram of a preferred embodiment of a computer device provided by the present invention. Detailed Implementation
[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0019] In the description of this application, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.
[0020] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components. The terms "vertical," "horizontal," "left," "right," "upper," "lower," and similar expressions used herein are for illustrative purposes only and do not indicate or imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.
[0021] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing specific embodiments only and is not intended to limit the invention. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.
[0022] Research on carbon emissions from power transmission and transformation projects is limited by their multi-stage monitoring cycles, often facing challenges such as difficulty in obtaining actual data, limited sample sizes, and discontinuous time series data. This is especially true during the initial design and decommissioning phases, where carbon emission data is scarce, severely restricting the ability to identify influencing factors. Therefore, one embodiment of this invention provides a method for identifying carbon emission influencing factors in power transmission and transformation projects. For details, please refer to... Figure 1 , Figure 1 The diagram shown is a flowchart of a method for identifying carbon emission influencing factors in power transmission and transformation projects according to one embodiment of the present invention, including the following steps: S1. Collect data on carbon emission influencing factors at each stage of the entire life cycle of power transmission and transformation projects.
[0023] Power transmission and transformation projects are characterized by long construction periods, large phase spans, and complex types of links, covering multiple life cycle stages such as design, construction, commissioning, and decommissioning.
[0024] In this embodiment, key factors influencing carbon emissions are identified throughout the entire lifecycle of a power transmission and transformation project, encompassing design, construction, commissioning, and decommissioning. First, initial carbon emission influencing factor data for these four stages of the power transmission and transformation project's lifecycle are collected and denoted as follows: ; In the formula, These correspond to the four stages of design, construction, commissioning, and decommissioning, respectively. k represents the different stages in which the data in this dataset is located; j represents the time point of the carbon emission influencing factor data; and d represents the dimension of the carbon emission influencing factor data. This represents the data value of the d-th influencing factor at time point j in stage k.
[0025] To address the data gaps caused by monitoring blind spots at various stages, this embodiment introduces interpolation methods to expand the data on carbon emission influencing factors. In one implementation of this embodiment, at each sample point... Construct a field nearby And new sample points are extracted from them to expand the sample size. Specifically, during the expansion process, sample points located at different time points are... Introducing parameters To adjust the size of its neighborhood, different asymmetric neighborhood formulas are used for the endpoints and intermediate points of the initial carbon emission influencing factor data for differentiated processing. The specific neighborhood formulas are as follows: Endpoint domain ( , ): Midpoint domain : For the construction domain New sample points extracted from different time points are used to perform classification interpolation calculations and take the mean, thereby generating multiple new data points to expand the sample size. In this embodiment, the carbon emission influencing factor data of different stages of power transmission and transformation projects obtained after expansion by interpolation are denoted as: .
[0026] For example, data on factors influencing carbon emissions include: the number of design personnel and man-days input during the design phase; the organizational structure of construction personnel, labor intensity and working hours, actual arrival quantities of various materials, transportation distances and transportation equipment, and fuel or electricity consumption of various machinery during the construction phase; the man-days and scheduling strategies of operation and maintenance personnel, SF6 and other gas leakage rates, and the amount of equipment parts replaced during the commissioning phase, as well as the load rate and line loss rate of main transformers; and the personnel input and dismantling precision during the decommissioning phase, the amount of waste materials recycled and the recycling of high-carbon materials, and the energy consumption of dismantling and transportation machinery. These factors affect the carbon emissions generated by power transmission and transformation projects.
[0027] S2. Perform distribution consistency testing on the carbon emission influencing factor data, and update the carbon emission influencing factor data based on the test results.
[0028] It is understandable that, given the long cycle and large investment involved in power transmission and transformation projects, the relationship between the data on carbon emission influencing factors and carbon emissions at each stage will change as the power transmission and transformation projects progress, i.e., data drift occurs. This drift will lead to a decrease in the reliability of subsequent predictions or identifications.
[0029] Based on this, this embodiment performs conceptual drift detection on the distribution consistency of carbon emission influencing factor data. First, a sliding window and a reference window are defined according to the carbon emission influencing factor data. The data distribution distance between the sliding window and the reference window is used as a deviation metric to detect drift in the carbon emission influencing factor data. For example: for the expanded carbon emission influencing factor data at each stage k, a sliding window based on continuous real-time time series data is constructed. and a reference window based on historical stable operating conditions Two data windows are used, and the statistical distance between key carbon emission factors in the two windows is measured. Preferably, the Wasserstein distance is used as a measure of distribution deviation. Calculate the minimum average moving distance of each data point in the reference window when it is transformed into each data point in the sliding window. If The larger size indicates that the current sliding window is larger. Data and historical stability reference window Compared to the previous data, not only may the mean have shifted, but the shape of its distribution (such as the range of fluctuation and tail characteristics) has also changed significantly. Among them, changes in tail characteristics refer to a significant increase or decrease in the probability of extreme values (outliers) in the data, and the "tail" of the distribution curve becomes thicker or thinner; changes in the range of fluctuation indicate that the dispersion of the data (such as variance) has changed, that is, the fluctuations have become larger or more stable.
[0030] For example, during the construction phase, under "historically stable operating conditions," the daily fuel consumption of excavators may remain stable at 100±10 liters with minimal fluctuations. However, within the "real-time sliding window," due to frequent rushing to meet deadlines or encountering severe geological conditions, fuel consumption may fluctuate dramatically between 70 and 130 liters, with a significantly increased range of fluctuations. This indicates that the construction schedule becomes unstable, and energy consumption patterns become more unpredictable. Similarly, during the commissioning phase, equipment energy consumption: under historically stable operating conditions, the transformer load rate is typically between 70% and 80%, with a very low probability of extremely high loads (thin tail). If the power grid experiences sustained extreme high temperatures, abnormal data points frequently appear in the current window, indicating that transformers are operating at over 95% load for extended periods due to a surge in air conditioning load (thick tail, increased extreme values).
[0031] Furthermore, the carbon emission influencing factor data is updated based on the drift detection results. Specifically, during the drift detection process, when the detected data distribution distance exceeds a preset offset threshold, the carbon emission influencing factor data within the sliding window is replaced; conversely, when the detected data distribution distance does not exceed the preset offset threshold, a rolling update is performed on the reference window. For example, the offset threshold can be manually set based on the performance of power transmission and transformation projects and experience. If set to 0.2, when... In cases where significant conceptual drift exists in the carbon emission influencing factors data for stage k, it is deemed necessary to establish the data in the sliding window as a new benchmark, i.e., directly replace the data, to ensure that subsequently generated data conforms to the latest engineering construction environment. When this occurs... In the case of no significant concept drift in the carbon emission influencing factors dataset of stage k, it is considered that the data distribution is relatively stable. Only a recursive update needs to be performed on the data, that is, keep the reference window unchanged, move the latest collected data within one week in the sliding window into the reference window through queue pushing, and remove the oldest data of the same amount in the reference window.
[0032] After completing the above steps, the carbon emission influencing factors data for different stages after the concept drift detection update will be recorded as: .
[0033] S3. Perform resampling on the updated carbon emission impact factor dataset to generate augmented datasets for each stage.
[0034] This step aims to augment the updated data on carbon emission impact factors, specifically: First, the updated carbon emission influencing factor dataset is assigned weights following a Dirichlet distribution. Within the interval (0, 1), n-1 uniformly distributed random numbers are generated in stages based on the updated carbon emission influencing factor data for each stage, denoted as . .
[0035] Secondly, sort the random numbers from smallest to largest, satisfying the following formula: Finally, the weighted intervals are calculated using the finite difference method. , represented as: The Bayes weights of carbon emission influencing factors at each stage are obtained using the above formula. , denoted as: in, The data follow a Dirichlet distribution and the Bayes weights of the carbon emission influencing factors at each stage all satisfy the following conditions. ; These correspond to the four stages of design, construction, commissioning, and decommissioning, respectively. This indicates the different stages in which the data contained in the dataset is located; For being in the first One of the influencing factors of a dimension. In order to be in The corresponding stage The weights of various influencing factors.
[0036] Sampling probabilities are defined by weights, and Bayesian bootstrap resampling is performed on the updated carbon emission impact factor dataset using these probabilities to generate an augmented dataset. Specifically, firstly, the previously generated Bayesian weights, which follow a Dirichlet distribution, are... Defined as each sample point The probability distribution of being selected in the resampling process satisfies .
[0037] Secondly, let the number of resampling times, D, be equal to the sample size of the carbon emission influencing factors data for the current stage. Based on the above probability distribution, for Perform D random samplings with replacement. In each sampling, the probability of each sample point being selected is determined by its weight. Decision. This allows us to obtain enhanced datasets for each stage of the power transmission and transformation project. In this embodiment, the enhanced datasets are denoted as: .
[0038] For example, during the construction phase ( ), Let's set up a dataset of carbon emission influencing factors. Include Each sample, based on weight A defined probability distribution is used for 1000 draws with replacement. If a certain sample (e.g., data representing "high fuel consumption at high altitude and low temperature") is assigned a higher weight (e.g., ... If the sample weight is 0.001, then the expected number of times it will be selected will be higher than that of the sample with the average weight (0.001). Therefore, augmenting the dataset... The data density of key patterns has been improved.
[0039] S4. Construct carbon emission calculation models for each stage based on the augmented dataset, and use the carbon emission calculation models to perform random sampling simulations to obtain the sample sets to be identified for each stage.
[0040] In this embodiment, the Monte Carlo simulation algorithm is preferred during the random sampling simulation process. Specifically, firstly, the probability distributions corresponding to the influencing factors for each sample point in the enhanced dataset are fitted, and a carbon emission calculation model reflecting the mapping relationship between the influencing factors and carbon emissions is constructed. In one implementation of this embodiment, the calculation formula for the carbon emission calculation model is defined as follows: In the formula, For carbon emissions, This represents the carbon emission factor (tCO2e / unit amount) corresponding to different carbon emission influencing factors. This refers to the data value of the influencing factor at time point j in stage k.
[0041] Understandably, each sample point in the augmented dataset contains specific values for a series of influencing factors (i.e., These values and their respective determined emission factors By multiplying and summing the results, a specific carbon emission can be calculated.
[0042] In one implementation of the probability distribution calculation, for the data of various influencing factors in the four stages of power transmission and transformation engineering—design, construction, commissioning, and decommissioning—a probability distribution function based on the carbon emission influencing factors of power transmission and transformation is constructed. Specifically, it is expressed as: in, This represents the mean. It represents the standard deviation.
[0043] Input samples are randomly drawn from the above probability distribution and substituted into the carbon emission calculation model for Monte Carlo simulation, iteratively generating a sample set to be identified. Specifically, for each sample point, M sets of random sample sequences are simulated according to its probability distribution, where M is ≥ 10000. For the i-th simulation, sample values are drawn from these sequences and substituted into the carbon emission calculation model to obtain the carbon emission amount under the i-th simulation. This process is repeated N times to obtain the carbon emission simulation result sequence. That is, the sample set to be identified.
[0044] S5. Based on the sample set to be identified, quantify the degree of influence of each stage on carbon emissions in order to identify the key influencing factors corresponding to each stage.
[0045] After obtaining the sample set to be identified, sensitivity analysis is further performed to accurately identify the key influencing factors of carbon emissions from power transmission and transformation projects.
[0046] This embodiment preferably uses the Sobol global sensitivity analysis algorithm. First, based on the sample set to be identified, the first-order partial variance of each influencing factor is calculated. Specifically, the Sobol model is used to perform global sensitivity analysis, and the total variance output by the carbon emission calculation model at each stage is calculated. The decomposition into the first-order partial variance of individual carbon emission influencing factors and the partial variance of the interaction between influencing factors is expressed as follows: for This formula represents when a single influencing factor When fixed, conditional expectation The variance. The average contribution of individual factor variations to the total output variance is called the first-order (main effect) partial variance.
[0047] for This formula represents when two influencing factors and When both are fixed, the variance of the conditional expectation is calculated. Subtracting the first-order partial variances of each factor from this variance yields the partial variance resulting from the interaction of these two influencing factors. .
[0048] Sensitivity indices for influencing factors are defined using first-order partial variance decomposition. In this embodiment, the sensitivity index is used to characterize the contribution of changes in a single influencing factor to carbon emissions. Specifically, the sensitivity index includes a first-order sensitivity index that measures the direct contribution (first-order effect) of a single influencing factor. , represented as: And, the sensitivity index for the total effect that measures the total contribution of a single influencing factor. It is composed of direct contributions as well as contributions through all other factors. Contribution of interaction Composition, represented as: Factors that cause the sensitivity index to exceed a preset sensitivity threshold are identified as key influencing factors. Specifically, it is expressed as follows: In the formula, This is the sensitivity threshold, which is usually set to 0.05.
[0049] Taking the construction phase of power transmission and transformation projects as an example, this paper demonstrates the identification results of key factors affecting carbon emissions and their engineering application value.
[0050] Based on the analysis and calculation of the enhanced dataset during the construction phase, the "real-time diesel consumption of large hoisting and pile foundation construction machinery" was determined to be a first-order sensitivity index. Sensitivity index of total effect All are significantly higher than the set threshold. =0.05 Key Influencing Factor. Understandably, this factor was selected as a key influencing factor because its own numerical fluctuations have a significant contribution rate (first-order effect) to direct carbon emissions from construction, and it has a significant interaction effect with other factors such as "type of work on the day", "type of machinery", "machinery shifts", and "geological conditions of the work site", which together constitute the main source of carbon emission uncertainty at this stage.
[0051] In some implementations of this embodiment, the identified key influencing factors can be applied to the following engineering practices: For example, during the construction organization design phase, "real-time consumption of mechanical diesel fuel" is used as a core optimization indicator. Different construction processes, equipment selections, and work group operation plans are simulated and compared, and the scheme with lower expected consumption is adopted first, so as to achieve forward-looking control of construction carbon emissions.
[0052] Furthermore, at the construction site, real-time fuel consumption monitoring terminals are installed on key machinery, dynamically coupling the monitoring data stream with the aforementioned carbon emission model. When actual data deviates from the baseline model and triggers a concept drift warning, the system can automatically prompt for checking equipment operating conditions or adjusting the construction pace, achieving rapid response and closed-loop management of abnormal carbon emission fluctuations.
[0053] In summary, this embodiment achieves data updates by performing probability drift distribution consistency detection on carbon emission influencing factor data; and then sequentially performs Bayesian self-sampling, Monte Carlo simulation, and global sensitivity analysis on the updated data to identify key influencing factors corresponding to different power transmission and transformation stages. This provides reliable data support for constructing scientific carbon emission reduction strategies and pathways, and can adapt to carbon emission identification tasks under multi-source heterogeneous data input and complex operating conditions in different types of power transmission and transformation projects.
[0054] One embodiment of the present invention provides a carbon emission influencing factor identification system for power transmission and transformation projects. For details, please refer to [link to relevant documentation]. Figure 2 , Figure 2 The diagram shown is a schematic representation of a carbon emission impact factor identification system for power transmission and transformation projects according to one embodiment of the present invention, comprising: Data acquisition module M1 is used to collect data on carbon emission influencing factors at each stage of the entire life cycle of power transmission and transformation projects; The consistency detection module M2 is used to perform distribution consistency detection on the carbon emission influencing factor data and update the carbon emission influencing factor data based on the detection results. Data augmentation module M3 is used to resample the updated dataset of carbon emission influencing factors to generate augmented datasets for each stage; The sampling module M4 is used to construct carbon emission calculation models for each stage based on the augmented dataset, and to perform random sampling simulations using the carbon emission calculation models to obtain the sample sets to be identified for each stage. The identification module M5 is used to quantify the degree of influence of each stage's influencing factors on carbon emissions based on the sample set to be identified, so as to identify the key influencing factors corresponding to each stage.
[0055] This invention also provides a computer device; for details, please refer to [link / reference needed]. Figure 3The diagram shown is a structural block diagram of a preferred embodiment of a computer device provided by the present invention. The computer device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method described above.
[0056] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2, ...), and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.
[0057] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or the processor can be any conventional processor. The processor is the control center of the terminal device, connecting various parts of the terminal device through various interfaces and lines.
[0058] The memory mainly includes a program storage area and a data storage area. The program storage area can store the operating system, applications required for at least one function, etc., while the data storage area can store related data, etc. Furthermore, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard drive, a SmartMedia Card (SMC), a Secure Digital (SD) card, and a Flash Card, or other volatile solid-state storage devices.
[0059] It should be noted that the aforementioned terminal devices may include, but are not limited to, processors and memory, as will be understood by those skilled in the art. Figure 3The structural block diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown, or combine certain components, or use different components. Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.
[0060] Accordingly, embodiments of the present invention provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the steps in the method of the above embodiments, for example... Figure 1 Steps S1 to S5 as described above.
[0061] The technical features and effects of the carbon emission influencing factor identification system for power transmission and transformation projects proposed in this embodiment are the same as those of the carbon emission influencing factor identification method for power transmission and transformation projects proposed in this embodiment, and will not be repeated here.
[0062] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.
Claims
1. A method for identifying carbon emission influencing factors in power transmission and transformation projects, characterized in that, include: Collect data on carbon emission influencing factors at each stage of the entire life cycle of power transmission and transformation projects; The data on carbon emission influencing factors are subjected to distribution consistency detection, and the data on carbon emission influencing factors are updated based on the detection results; The updated dataset of carbon emission influencing factors is resampled to generate augmented datasets for each stage. Based on the enhanced dataset, construct carbon emission calculation models for each stage, and use the carbon emission calculation models to perform random sampling simulations to obtain the sample sets to be identified for each stage. The impact of each stage's influencing factors on carbon emissions is quantified based on the sample set to be identified, in order to identify the key influencing factors corresponding to each stage.
2. The method for identifying carbon emission influencing factors for power transmission and transformation projects as described in claim 1, characterized in that, The step of performing distribution consistency detection on the carbon emission influencing factor data and updating the carbon emission influencing factor data based on the detection results includes: Based on the data on carbon emission influencing factors, a sliding window and a reference window are defined respectively; The data distribution distance between the sliding window and the reference window is used as a deviation metric to detect drift in the carbon emission influencing factor data. The carbon emission influencing factors data are updated based on the drift detection results.
3. The method for identifying carbon emission influencing factors for power transmission and transformation projects as described in claim 2, characterized in that, The step of updating the carbon emission influencing factor data based on the drift detection results includes: During drift detection, when the data distribution distance exceeds a preset offset threshold, the carbon emission influencing factor data within the sliding window is replaced. When the data distribution distance is detected to be no more than a preset offset threshold, a rolling update is performed on the reference window.
4. The method for identifying carbon emission influencing factors for power transmission and transformation projects as described in claim 1, characterized in that, The process of resampling the updated dataset of carbon emission influencing factors to generate augmented datasets for each stage includes: The updated dataset of carbon emission influencing factors is assigned weights that follow a Dirichlet distribution, and the sampling probability is defined by the weights. The updated dataset of carbon emission influencing factors is subjected to Bayesian bootstrap resampling using the sampling probability to generate the augmented dataset.
5. The method for identifying carbon emission influencing factors for power transmission and transformation projects as described in claim 1, characterized in that, The process involves constructing carbon emission calculation models for each stage based on the enhanced dataset, and then using these models to perform random sampling simulations to obtain the sample sets to be identified for each stage, including: Fit the corresponding probability distribution to the influencing factors for each sample point in the enhanced dataset, and construct the carbon emission calculation model that reflects the mapping relationship between the influencing factors and carbon emissions; Input samples are randomly drawn from the probability distribution, and the input samples are substituted into the carbon emission calculation model for simulation to iteratively generate the sample set to be identified.
6. The method for identifying carbon emission influencing factors for power transmission and transformation projects as described in claim 1, characterized in that, The step of quantifying the impact of influencing factors at each stage on carbon emissions based on the sample set to be identified, in order to identify the key influencing factors corresponding to each stage, includes: Based on the sample set to be identified, calculate the first-order partial variance of each influencing factor; The sensitivity index of the influencing factors is defined by the first-order partial variance decomposition, and the sensitivity index is used to characterize the contribution of changes in a single influencing factor to carbon emissions. Factors that cause the sensitivity index to exceed a preset sensitivity threshold are identified as key influencing factors.
7. The method for identifying carbon emission influencing factors for power transmission and transformation projects as described in claim 1, characterized in that, Before performing distribution consistency detection on the carbon emission influencing factor data, the method further includes: An interpolation method is introduced to expand the data on the factors influencing carbon emissions.
8. A carbon emission influencing factor identification system for power transmission and transformation projects, characterized in that, include: The data acquisition module is used to collect data on carbon emission influencing factors at each stage of the entire life cycle of power transmission and transformation projects; The consistency detection module is used to perform distribution consistency detection on the carbon emission influencing factor data and update the carbon emission influencing factor data based on the detection results. The data augmentation module is used to resample the updated dataset of carbon emission influencing factors to generate augmented datasets for each stage. The sampling module is used to construct carbon emission calculation models for each stage based on the augmented dataset, and to perform random sampling simulations using the carbon emission calculation models to obtain the sample sets to be identified for each stage. The identification module is used to quantify the impact of each stage's influencing factors on carbon emissions based on the sample set to be identified, in order to identify the key influencing factors corresponding to each stage.
9. A computer device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the method for identifying carbon emission influencing factors for power transmission and transformation projects as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the method for identifying carbon emission influencing factors for power transmission and transformation projects as described in any one of claims 1 to 7.