Regional carbon emission reduction potential analysis method based on electric power big data

Abstract

The invention provides a regional carbon emission reduction potential analysis method based on electric power big data, and relates to the technical field of carbon emission reduction. The method comprises the following steps: collecting historical power data and real-time monitoring data of a target area; and calculating the initial carbon emission according to the influence coefficient to obtain a carbon emission reduction potential scheme. And calculating the power consumption behavior data and the traffic data according to a power alternating current carbon measurement method to obtain target carbon emission data. And outputting an adjustment strategy by using the input-output model optimized by the crayfish optimization algorithm, and adjusting the carbon emission reduction potential scheme to obtain a carbon emission reduction strategy. And establishing a monitoring evaluation mechanism, judging an effect according to a preset interval, if the result reaches the standard, implementing, otherwise, re-outputting an adjustment strategy. According to the method, the carbon emission reduction potential is evaluated in multiple aspects, the input-output model is optimized, the adjustment strategy is generated and used for formulating and evaluating the carbon emission reduction strategy, and the beneficial effects of improving the carbon emission reduction analysis precision, optimizing the carbon emission reduction strategy and improving the energy utilization efficiency and the management level are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission reduction, and in particular to a method for analyzing regional carbon emission reduction potential based on power big data. Background Art

[0002] As the global climate change problem becomes increasingly serious, reducing carbon emissions and achieving carbon neutrality has become a common goal for countries around the world. As one of the main sources of carbon emissions, the power industry’s accurate accounting of carbon emissions and effective assessment of carbon reduction potential are crucial to the formulation of scientific and reasonable carbon reduction strategies.

[0003] In terms of carbon emission accounting, first of all, the use of electricity carbon emission factors is not uniform. Different regions and different studies have different values ​​for carbon emission factors for green electricity (such as wind power, photovoltaics, etc.), which leads to large errors in calculating indirect carbon emissions on the electricity consumption side. For example, some studies directly use the national average electricity carbon emission factor without taking into account the impact of factors such as energy structure, power structure, and power generation technology level in different regions on carbon emissions, resulting in accounting results that are inconsistent with actual conditions. Secondly, the existing accounting methods rely on actual enterprise data, but in actual operations, the data of some enterprises, especially small and medium-sized enterprises, are missing, inaccurate or incomplete, making it difficult for carbon emission accounting to fully and accurately reflect actual emissions. In addition, existing accounting often only focuses on carbon emissions in the power generation link, while ignoring the carbon emissions corresponding to the losses generated by the power grid in the process of transmitting and distributing electricity, resulting in an insufficiently comprehensive accounting dimension and inaccurate results.

[0004] For the assessment of carbon emission reduction potential, the existing methods are not comprehensive and standardized. On the one hand, the assessment process does not fully consider the comprehensive impact of multiple factors on carbon emission reduction, such as energy structure adjustment, energy efficiency improvement, changes in electricity consumption behavior, electrification in the transportation sector, and emerging technologies (such as carbon capture and storage technology). For example, when assessing the potential for energy structure adjustment, factors such as resource limitations, technical bottlenecks, and policy support for the development of renewable energy are not fully considered, resulting in inaccurate assessment of the structural emission reduction potential. On the other hand, the lack of unified assessment standards and methods means that the assessment results between different regions and different studies lack comparability, making it difficult to form a scientific and systematic carbon emission reduction potential assessment system.

[0005] In terms of carbon emission reduction strategy formulation, existing strategies lack pertinence and scientificity. Due to inaccurate carbon emission accounting and incomplete assessment of carbon emission reduction potential, the formulated carbon emission reduction strategies cannot accurately target the main sources and key links of carbon emissions in the region. For example, some carbon emission reduction strategies may blindly propose the development of renewable energy without fully considering factors such as local energy resource conditions, economic development levels, and social acceptance, making it difficult for the strategies to achieve the expected results during implementation. In addition, existing strategies often do not fully consider the synergistic effects between different policy measures (such as carbon markets, subsidy policies, energy standards, etc.), resulting in conflicts between policies or the inability to form a joint force, reducing the efficiency and effectiveness of the implementation of carbon emission reduction strategies.

[0006] In summary, the existing regional carbon emission reduction potential analysis methods based on power big data have obvious defects in carbon emission accounting, carbon emission reduction potential assessment and carbon emission reduction strategy formulation. There is an urgent need for a more accurate, comprehensive and scientific analysis method to guide regional carbon emission reduction work and achieve sustainable development goals. Summary of the invention

[0007] The present invention provides a regional carbon emission reduction potential analysis method based on power big data, which is used to solve the defects of inaccurate carbon emission accounting, insufficient comprehensive standards for carbon emission reduction potential assessment, and lack of pertinence and scientificity in carbon emission reduction strategy formulation in the prior art.

[0008] The present invention provides a method for analyzing regional carbon emission reduction potential based on power big data, comprising: S1: Collect historical power data in the carbon emission reduction target area, monitor the target area, and obtain real-time monitoring data. Historical power data includes power generation data, grid data, load data, and meteorological data.

[0009] S2: According to the carbon emission accounting method, the power generation data and power grid data are processed to obtain the preliminary carbon emissions in the target area. The impact coefficient on carbon emissions is obtained according to the degree of influence of meteorological data on load data. The preliminary carbon emissions are calculated based on the impact coefficient to obtain the carbon emission reduction potential plan.

[0010] S3: Extract electricity consumption behavior data and transportation data from the real-time monitoring data, and calculate the electricity consumption behavior data and transportation data according to the electricity and transportation carbon measurement method to obtain the target carbon emission data.

[0011] S4: Construct an input-output model, and use the crayfish optimization algorithm to optimize the hyperparameters of the input-output model to obtain an optimized input-output model. Input the target carbon emission data into the optimized input-output model, output the adjustment strategy, and adjust the carbon emission reduction potential plan according to the adjustment strategy to obtain the carbon emission reduction strategy.

[0012] S5: Establish a carbon emission reduction monitoring and evaluation mechanism to determine whether the implementation effect of the carbon emission reduction strategy has achieved the expected goal at preset time intervals. If so, continue to implement the carbon emission reduction strategy; otherwise, re-output the adjustment strategy.

[0013] According to a method for analyzing regional carbon emission reduction potential based on power big data provided by the present invention, the steps of obtaining preliminary carbon emissions include: The power generation data and power grid data are cleaned to remove data records with serious duplication, errors and missing values, and standardized to obtain power generation data and power grid data.

[0014] The power generation data is classified according to different power generation methods, and the corresponding power generation of different power generation methods within a preset time period is counted to obtain a variety of power data, and the carbon emissions of different power generation methods within the preset time period are calculated based on the multiple power data and the corresponding carbon emission factors to obtain the power generation carbon emissions.

[0015] The grid loss amount is obtained by analyzing the losses caused by the transmission and distribution of electricity within a preset time period. The average carbon emission factor is calculated based on the carbon emissions of power generation and power generation data. The grid loss amount is multiplied by the average carbon emission factor to obtain the grid loss carbon emissions.

[0016] The preliminary carbon emissions are obtained by adding the carbon emissions from power generation to the carbon emissions from grid losses.

[0017] According to a method for analyzing regional carbon emission reduction potential based on power big data provided by the present invention, the step of obtaining the influence coefficient includes: The meteorological data is grouped according to preset intervals to obtain multiple meteorological groups, the load data under different meteorological groups are compared, and the load change rate is calculated.

[0018] Observe the changing trends of load change rate and meteorological grouping, obtain the correlation data between meteorological factors and load data, and compare the size of load change rate under multiple meteorological factors to obtain the main meteorological factors affecting the load.

[0019] According to the energy structure and carbon emission factors in the target area, the proportional relationship of carbon emission change corresponding to the load change is calculated, and the influence coefficient is obtained according to the main meteorological factors combined with the proportional relationship.

[0020] According to a regional carbon emission reduction potential analysis method based on power big data provided by the present invention, the steps of obtaining a carbon emission reduction potential solution include: Based on the analysis of the renewable energy development plan in the target area, the expected changes in the proportion of renewable energy in the energy structure are obtained, and the structural emission reduction is calculated based on the expected changes and the carbon emission factors of different energy sources.

[0021] The energy efficiency improved by the technology upgrades and management optimization measures implemented in various industries within the target area is summarized to obtain the energy efficiency improvement ratio. The efficiency emission reduction is calculated based on the electricity consumption of each industry, the energy efficiency improvement ratio and the corresponding carbon emission factor.

[0022] The emission reductions caused by other factors include the reduction in electricity compliance after implementing peak-valley electricity prices, promoting energy-saving appliances and strengthening energy management measures, analyzing the impact of electrification in the transportation sector on electricity demand and carbon emissions, and the carbon emission reduction effect caused by the application of carbon capture and storage technology.

[0023] The emission reductions caused by structural emission reductions, efficiency emission reductions and other factors are summarized to obtain the total emission reductions, which are then compared with the preliminary carbon emissions to calculate the carbon emission reduction potential ratio.

[0024] The carbon emission reduction potential of the target area is evaluated according to the carbon emission reduction ratio to obtain the carbon emission reduction potential evaluation result, and a carbon emission reduction potential plan is formulated based on the evaluation result.

[0025] According to a method for analyzing regional carbon emission reduction potential based on power big data provided by the present invention, the step of obtaining target carbon emission data includes: The electricity consumption behavior data is classified according to industry and time period, the electricity consumption under different classifications is calculated, and the changing trends and patterns of electricity consumption are analyzed. The transportation electricity consumption generated by different modes of transportation under transportation data is counted.

[0026] According to the energy structure of the target area, the emission factors of different electricity sources are determined. According to the electricity consumption and emission factors, the behavioral emission data generated by different electricity consumption behaviors are calculated. The behavioral emission data generated in different time periods are summarized to obtain the carbon emissions of electricity consumption behaviors.

[0027] For different modes of transportation, the corresponding traffic emission factors are determined, and the transportation carbon emissions are calculated based on the transportation volume, mileage and traffic emission factors of different modes of transportation.

[0028] Add the carbon emissions from electricity consumption and transportation to get the target carbon emissions data.

[0029] According to a method for analyzing regional carbon emission reduction potential based on power big data provided by the present invention, the steps of obtaining an optimized input-output model include: S41: Determine the hyperparameters of the input-output model, and determine the value range of each hyperparameter to randomly generate multiple crayfish individuals to form an initial population.

[0030] S42: Construct a fitness function based on the correlation between various industrial sectors and their impact mechanisms on carbon emissions.

[0031] S43: Calculate the fitness value of each crayfish individual in the initial population according to the fitness function to obtain the individual fitness value.

[0032] S44: Each crayfish individual updates its own position according to the position update formula, simulating the foraging behavior to obtain an updated individual.

[0033] S45: Calculate the fitness value of the updated individual according to the fitness function to obtain the updated fitness value, and determine whether the updated fitness value is less than the individual fitness value. If so, the crayfish individual is equal to the updated individual, otherwise, communicate in the initial population to obtain the optimal individual.

[0034] S46: Repeat steps S41 to S45 until the preset number of iterations is reached, select the hyperparameter represented by the optimal individual with the smallest fitness value as the optimal hyperparameter, and bring the optimal hyperparameter into the input-output model to obtain the optimized input-output model.

[0035] According to a regional carbon emission reduction potential analysis method based on power big data provided by the present invention, the fitness function formula is expressed as:

[0036] In the formula, is the sample size, is the hyperparameter The input-output model is The predicted value of samples, It is The actual value of the samples.

[0037] According to a regional carbon emission reduction potential analysis method based on power big data provided by the present invention, the formula for updating individuals is expressed as:

[0038] In the formula, It is Crayfish individuals The updated position at each moment is the step size control parameter. is a random number between [0,1], is The optimal individual position in the population at that moment, is Moment The location of each crayfish individual, is the step size control parameter.

[0039] According to a method for analyzing regional carbon emission reduction potential based on power big data provided by the present invention, the step of obtaining an adjustment strategy includes: The target carbon emission data is input into the optimized input-output model and run to obtain the output results, which are used to determine the main source industries and key links of carbon emissions in the current economic system.

[0040] Different adjustment scenarios are set according to the output results. According to different adjustment scenarios, the corresponding parameters are modified in the optimization input-output model. Then, the optimization input-output model is re-run to simulate the operation changes of the economic system and the changes in carbon emissions under the scenario to obtain multiple scenario results.

[0041] According to the carbon emission reduction indicators, the effects of different scenario results on achieving the target carbon emissions are compared, and the mutual influence and feedback mechanism between various industrial sectors are analyzed. The scenario results that effectively achieve the target carbon emissions and have the least impact on the economy and society are selected, and the adjustment strategy is specified.

[0042] According to a method for analyzing regional carbon emission reduction potential based on power big data provided by the present invention, the steps of obtaining a carbon emission reduction strategy include: Classify the policy measures, technical measures and market mechanism measures in the adjustment strategy to obtain multi-measure data, and clarify the goals and expected results.

[0043] Compare and analyze the various measures in the carbon emission reduction potential plan with the multi-measure data, extract the measures with good effects, and modify and improve the existing measures in the carbon emission reduction potential plan to obtain adjustment measures.

[0044] According to the adjustment measures, the resources required for the time carbon emission reduction target are re-evaluated, and the resource allocation is adjusted accordingly to obtain the optimized carbon emission reduction potential plan, and the optimized input-output model is used to evaluate the effect of the optimized carbon emission reduction potential plan to obtain the effect evaluation results. According to the effect evaluation results, the optimized carbon emission reduction potential plan is optimized and improved to obtain the carbon emission reduction strategy document.

[0045] The present invention provides a regional carbon emission reduction potential analysis method based on power big data, which collects historical power data and real-time monitoring data in the carbon emission reduction target area, cleans, classifies and standardizes the data, comprehensively considers the impact of meteorological factors on load data, evaluates carbon emission reduction potential from multiple aspects such as renewable energy development planning, technology upgrading, and management optimization, formulates and evaluates carbon emission reduction strategies, and establishes a carbon emission reduction monitoring and evaluation mechanism, solves the problems of incomplete data, uneven quality, inaccurate carbon emission calculation, incomplete carbon emission reduction potential evaluation, insufficient model accuracy, unscientific adjustment strategy generation, and difficult implementation effect evaluation, and achieves the beneficial effects of improving carbon emission reduction analysis accuracy, optimizing carbon emission reduction strategies, realizing dynamic monitoring and evaluation of carbon emission reduction targets, promoting renewable energy development and energy structure optimization, and improving energy utilization efficiency and management level. In addition, the input-output model is constructed and optimized, and an effective adjustment strategy is generated, so that the carbon emission reduction strategy is more targeted and effective, which helps to achieve regional carbon emission reduction targets while minimizing the impact on the economy and society. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 This is one of the flow charts of a method for analyzing regional carbon emission reduction potential based on power big data provided by an embodiment of the present invention; Figure 2 This is the second flow chart of a method for analyzing regional carbon emission reduction potential based on power big data provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Combine the following Figure 1-Figure 2 The present invention describes a method for analyzing regional carbon emission reduction potential based on power big data.

[0050] like Figure 1As shown, an embodiment of the present invention provides a method for analyzing regional carbon emission reduction potential based on power big data, including: S1: Collect historical power data in the carbon emission reduction target area, monitor the target area, and obtain real-time monitoring data. Historical power data includes power generation data, grid data, load data, and meteorological data.

[0051] S2: According to the carbon emission accounting method, the power generation data and power grid data are processed to obtain the preliminary carbon emissions in the target area. The impact coefficient on carbon emissions is obtained according to the degree of influence of meteorological data on load data. The preliminary carbon emissions are calculated based on the impact coefficient to obtain the carbon emission reduction potential plan.

[0052] In step S2, the step of obtaining preliminary carbon emissions includes: The power generation data and power grid data are cleaned to remove data records with serious duplication, errors and missing values, and standardized to obtain power generation data and power grid data.

[0053] The power generation data is classified according to different power generation methods, and the corresponding power generation of different power generation methods within a preset time period is counted to obtain a variety of power data, and the carbon emissions of different power generation methods within the preset time period are calculated based on the multiple power data and the corresponding carbon emission factors to obtain the power generation carbon emissions.

[0054] The grid loss amount is obtained by analyzing the losses caused by the transmission and distribution of electricity within a preset time period. The average carbon emission factor is calculated based on the carbon emissions of power generation and power generation data. The grid loss amount is multiplied by the average carbon emission factor to obtain the grid loss carbon emissions.

[0055] The preliminary carbon emissions are obtained by adding the carbon emissions from power generation to the carbon emissions from grid losses.

[0056] The steps to obtain the influence coefficient include: The meteorological data is grouped according to preset intervals to obtain multiple meteorological groups, the load data under different meteorological groups are compared, and the load change rate is calculated.

[0057] Observe the changing trends of load change rate and meteorological grouping, obtain the correlation data between meteorological factors and load data, and compare the size of load change rate under multiple meteorological factors to obtain the main meteorological factors affecting the load.

[0058] According to the energy structure and carbon emission factors in the target area, the proportional relationship of carbon emission change corresponding to the load change is calculated, and the influence coefficient is obtained according to the main meteorological factors combined with the proportional relationship.

[0059] The steps to obtain carbon reduction potential options include: Based on the analysis of the development plan of renewable energy in the target area, the expected change in the proportion of renewable energy in the energy structure is obtained. The structural emission reduction is calculated based on the expected change and the carbon emission factors of different energy sources. The formula is expressed as follows:

[0060] In the formula, is the structural emission reduction, is the power generation data, F1 is the average carbon emission factor of the original energy structure, and F2 is the average carbon emission factor of the adjusted energy structure.

[0061] The energy efficiency improved by the technology upgrades and management optimization measures implemented in various industries in the target area is summarized to obtain the energy efficiency improvement ratio. Based on the electricity consumption, energy efficiency improvement ratio and corresponding carbon emission factors of each industry, the efficiency emission reduction is calculated. The formula is expressed as follows:

[0062] In the formula, is the efficiency reduction, It is the electricity consumption of the industry. is the number of industries, is the energy efficiency improvement ratio, is the corresponding carbon emission factor.

[0063] The reduction in electricity consumption caused by the implementation of peak-valley electricity prices, the promotion of energy-saving appliances and the strengthening of energy management measures, the impact of electrification in the transportation sector on electricity demand and carbon emissions, and the carbon reduction effect of the application of carbon capture and storage technology are analyzed as the emission reduction caused by other factors. The degree of influence of the influence coefficient on the emission reduction caused by other factors is also considered.

[0064] The emission reductions caused by structural emission reductions, efficiency emission reductions and other factors are combined to obtain the total emission reductions. The total emission reductions are compared with the preliminary carbon emissions to calculate the carbon emission reduction potential ratio. The formula is expressed as:

[0065] In the formula, is the total emission reduction, is the initial carbon emissions, is the carbon emission reduction ratio.

[0066] The carbon emission reduction potential of the target area is evaluated according to the carbon emission reduction ratio to obtain the carbon emission reduction potential evaluation result, and a carbon emission reduction potential plan is formulated based on the evaluation result.

[0067] S3: Extract electricity consumption behavior data and transportation data from the real-time monitoring data, and calculate the electricity consumption behavior data and transportation data according to the electricity and transportation carbon measurement method to obtain the target carbon emission data.

[0068] The steps to obtain target carbon emissions data include: The electricity consumption behavior data is classified according to industry and time period, the electricity consumption under different classifications is calculated, and the changing trends and patterns of electricity consumption are analyzed. The transportation electricity consumption generated by different modes of transportation under transportation data is counted.

[0069] According to the energy structure of the target area, the emission factors of different electricity sources are determined. According to the electricity consumption and emission factors, the behavioral emission data generated by different electricity consumption behaviors are calculated. The behavioral emission data generated in different time periods are summarized to obtain the carbon emissions of electricity consumption behaviors.

[0070] For different modes of transportation, the corresponding traffic emission factors are determined, and the transportation carbon emissions are calculated based on the transportation volume, mileage and traffic emission factors of different modes of transportation.

[0071] Add the carbon emissions from electricity consumption and transportation to get the target carbon emissions data.

[0072] S4: Construct an input-output model, and use the crayfish optimization algorithm to optimize the hyperparameters of the input-output model to obtain an optimized input-output model. Input the target carbon emission data into the optimized input-output model, output the adjustment strategy, and adjust the carbon emission reduction potential plan according to the adjustment strategy to obtain the carbon emission reduction strategy.

[0073] like Figure 2 As shown, the steps of obtaining the optimized input-output model include: S41: Determine the hyperparameters of the input-output model and the value range of each hyperparameter to randomly generate multiple crayfish individuals to form an initial population. ,in is the position of the first crayfish individual at the initial moment, is the position of the second crayfish individual at the initial moment, It is The positions of individual crayfish at the initial moment.

[0074] S42: Construct a fitness function based on the correlation between various industrial sectors and their impact mechanisms on carbon emissions.

[0075] In step S42, the fitness function is expressed as:

[0076] In the formula, is the sample size, is the hyperparameter The input-output model is The predicted value of samples, It is The actual value of the samples.

[0077] S43: Calculate the fitness value of each crayfish individual in the initial total group according to the fitness function to obtain the individual fitness value.

[0078] S44: Each crayfish individual updates its own position according to the position update formula, simulating the foraging behavior to obtain an updated individual.

[0079] In step S44, the formula for updating the individual is expressed as:

[0080] In the formula, It is Crayfish individuals The updated position at each moment is the step size control parameter. is a random number between [0,1], is The optimal individual position in the population at that moment, is Moment The location of each crayfish individual, is the step size control parameter.

[0081] S45: Calculate the fitness value of the updated individual according to the fitness function to obtain the updated fitness value, and determine whether the updated fitness value is less than the individual fitness value. If so, the crayfish individual is equal to the updated individual, otherwise, communicate in the initial population to obtain the optimal individual.

[0082] S46: Repeat steps S41 to S45 until the preset number of iterations is reached, select the hyperparameter represented by the optimal individual with the smallest fitness value as the optimal hyperparameter, and bring the optimal hyperparameter into the input-output model to obtain the optimized input-output model.

[0083] The steps to obtain the adjustment strategy include: The target carbon emission data is input into the optimized input-output model and run to obtain the output results, which are used to determine the main source industries and key links of carbon emissions in the current economic system.

[0084] Different adjustment scenarios are set according to the output results. According to different adjustment scenarios, the corresponding parameters are modified in the optimization input-output model. Then, the optimization input-output model is re-run to simulate the operation changes of the economic system and the changes in carbon emissions under the scenario to obtain multiple scenario results.

[0085] According to the carbon emission reduction indicators, the effects of different scenario results on achieving the target carbon emissions are compared, and the mutual influence and feedback mechanism between various industrial sectors are analyzed. The scenario results that effectively achieve the target carbon emissions and have the least impact on the economy and society are selected, and the adjustment strategy is specified.

[0086] Steps to derive a carbon reduction strategy include: Classify the policy measures, technical measures and market mechanism measures in the adjustment strategy to obtain multi-measure data, and clarify the goals and expected results.

[0087] Compare and analyze the various measures in the carbon emission reduction potential plan with the multi-measure data, extract the measures with good effects, and modify and improve the existing measures in the carbon emission reduction potential plan to obtain adjustment measures.

[0088] According to the adjustment measures, the resources required for the time carbon emission reduction target are re-evaluated, and the resource allocation is adjusted accordingly to obtain the optimized carbon emission reduction potential plan, and the optimized input-output model is used to evaluate the effect of the optimized carbon emission reduction potential plan to obtain the effect evaluation results. According to the effect evaluation results, the optimized carbon emission reduction potential plan is optimized and improved to obtain the carbon emission reduction strategy document.

[0089] S5: Establish a carbon emission reduction monitoring and evaluation mechanism to determine whether the implementation effect of the carbon emission reduction strategy has achieved the expected goal at preset time intervals. If so, continue to implement the carbon emission reduction strategy; otherwise, re-output the adjustment strategy.

[0090] In summary, this embodiment provides a regional carbon emission reduction potential analysis method based on power big data. By processing the power generation data and power grid data according to the carbon emission accounting method, the preliminary carbon emissions in the target area can be obtained, which can solve the defects of inaccurate carbon emission accounting caused by not fully considering the differences in power generation methods and ignoring the carbon emissions of power grid losses, improve the accuracy of carbon emission accounting, and provide a reliable basis for carbon emission reduction strategies. The crayfish optimization algorithm is used to optimize the input-output model hyperparameters to solve the problem that the existing analysis model is not fine enough and does not fully consider the real-time balance of the power grid, multi-energy complementarity and other factors, and obtain a more accurate optimized input-output model, which can more accurately evaluate the carbon emission potential and provide strong support for the formulation of scientific carbon emission reduction strategies. The measures in the adjustment strategy are classified and compared with the carbon emission reduction potential plan to solve the problem of lack of policy coordination considerations when formulating strategies, formulate more scientific, reasonable and comprehensive carbon emission reduction strategies, improve the pertinence and operability of the strategy, promote the synergy between various policies, and help achieve carbon emission reduction goals.

[0091] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0092] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing regional carbon emission reduction potential based on power big data, characterized in that: include: S1: Collect historical electricity data in the carbon emission reduction target area, monitor the target area, and obtain real-time monitoring data; The historical power data includes power generation data, power grid data, load data and meteorological data; S2: Processing the power generation data and the grid data according to the carbon emission accounting method to obtain the preliminary carbon emission in the target area, obtaining the influence coefficient on carbon emission according to the influence degree of the meteorological data on the load data, and calculating the preliminary carbon emission according to the influence coefficient to obtain the carbon emission reduction potential plan; S3: extracting electricity consumption behavior data and transportation data from the real-time monitoring data, and calculating the electricity consumption behavior data and the transportation data according to the electricity-transportation carbon measurement method to obtain target carbon emission data; S4: construct an input-output model, and use the crayfish optimization algorithm to optimize the hyperparameters of the input-output model to obtain an optimized input-output model, input the target carbon emission data into the optimized input-output model, output an adjustment strategy, and adjust the carbon emission reduction potential plan according to the adjustment strategy to obtain a carbon emission reduction strategy; S5: Establish a carbon emission reduction monitoring and evaluation mechanism to determine whether the implementation effect of the carbon emission reduction strategy has achieved the expected goal at preset time intervals. If yes, continue to implement the carbon emission reduction strategy; otherwise, re-output the adjustment strategy.

2. According to claim 1, a method for analyzing regional carbon emission reduction potential based on power big data is characterized in that: In step S2, the step of obtaining the preliminary carbon emissions includes: Cleaning the power generation data and the power grid data, removing duplicate and erroneous data records, and performing standardization processing to obtain power generation data and power grid data; The power generation data is classified according to different power generation methods, and the power generation of different power generation methods in a preset time period is counted to obtain a plurality of power data, and the carbon emissions of different power generation methods in the preset time period are calculated according to the plurality of power data and the corresponding carbon emission factors to obtain the power generation carbon emissions; Analyze the power grid data for the losses caused by the transmission and distribution of electricity during the preset time period to obtain a power grid loss amount, calculate an average carbon emission factor based on the power generation carbon emissions and the power generation data, and multiply the power grid loss amount by the average carbon emission factor to obtain a power grid loss carbon emission amount; The preliminary carbon emissions are obtained by adding the power generation carbon emissions and the grid loss carbon emissions.

3. According to claim 2, a method for analyzing regional carbon emission reduction potential based on power big data is characterized in that: In step S2, the step of obtaining the influence coefficient includes: The meteorological data is grouped according to a preset interval to obtain a plurality of meteorological groups, and the load data under different meteorological groups are compared to calculate the load change rate; Observe the change trend of the load change rate and the meteorological grouping to obtain the correlation data between the meteorological factors and the load data, and compare the magnitude of the load change rate under multiple meteorological factors to obtain the main meteorological factors affecting the load; According to the energy structure in the target area and the average carbon emission factor, the change in carbon emissions corresponding to the load change is calculated to obtain a proportional relationship, and the influence coefficient is obtained according to the main meteorological factors combined with the proportional relationship.

4. According to claim 1, a method for analyzing regional carbon emission reduction potential based on power big data is characterized in that: In step S2, the step of obtaining the carbon emission reduction potential solution includes: Analyze the development plan of renewable energy in the target area to obtain the expected change in the proportion of renewable energy in the energy structure, and calculate the structural emission reduction according to the expected change and the carbon emission factors of different energy sources; Summarize the energy efficiency improved by the technology upgrades and management optimization measures implemented in various industries in the target area to obtain the energy efficiency improvement ratio, and calculate the efficiency emission reduction according to the electricity consumption of each industry, the energy efficiency improvement ratio and the corresponding carbon emission factor; The reduction in electricity consumption caused by the implementation of peak-valley electricity prices, the promotion of energy-saving appliances and the strengthening of energy management measures, the impact of electrification of the transportation sector on electricity demand and carbon emissions, and the carbon reduction effect of the application of carbon capture and storage technology are analyzed as the emission reduction caused by other factors; Summarizing the structural emission reduction, the efficiency emission reduction and the emission reduction caused by other factors to obtain a total emission reduction, comparing the total emission reduction with the preliminary carbon emissions, and calculating the carbon emission reduction potential ratio; The carbon emission reduction potential of the target area is evaluated according to the carbon emission reduction ratio to obtain a carbon emission reduction potential evaluation result, and the carbon emission reduction potential plan is formulated according to the evaluation result.

5. According to claim 1, a method for analyzing regional carbon emission reduction potential based on power big data is characterized in that: In step S3, the step of obtaining the target carbon emission data includes: Classify the electricity consumption behavior data according to industry and time period, calculate the electricity consumption under different classifications, analyze the changing trends and rules of the electricity consumption, and count the transportation electricity consumption generated by different transportation modes under the transportation data; According to the energy structure of the target area, the emission factors of different electricity sources are determined, and according to the electricity consumption and the emission factors, the behavioral emission data generated by different electricity consumption behaviors are calculated, and the behavioral emission data generated in different time periods are summarized to obtain the carbon emissions of electricity consumption behaviors; Determine the corresponding transportation emission factors for different modes of transportation, and calculate the transportation carbon emissions based on the transportation volume, mileage and the transportation emission factors of different modes of transportation; The target carbon emission data is obtained by adding the electricity consumption carbon emission and the transportation carbon emission.

6. According to claim 1, a method for analyzing regional carbon emission reduction potential based on power big data is characterized in that: In step S4, the step of obtaining the optimized input-output model includes: S41: Determine the hyperparameters of the input-output model, and determine the value range of each hyperparameter to randomly generate a plurality of crayfish individuals to form an initial population; S42: Construct a fitness function based on the relationship between various industrial sectors and their impact mechanisms on carbon emissions; S43: calculating the fitness value of each individual crayfish in the initial population according to the fitness function to obtain an individual fitness value; S44: Each of the crayfish individuals updates its own position according to a position update formula, simulating foraging behavior to obtain an updated individual; S45: calculating the fitness value of the updated individual according to the fitness function to obtain an updated fitness value, and judging whether the updated fitness value is less than the individual fitness value, if so, the crayfish individual is equal to the updated individual, otherwise, communicating in the initial population to obtain the optimal individual; S46: Repeat steps S41 to S45 until a preset number of iterations is reached, select the hyperparameter represented by the optimal individual with the smallest fitness value as the optimal hyperparameter, and bring the optimal hyperparameter into the input-output model to obtain the optimized input-output model.

7. The method for analyzing regional carbon emission reduction potential based on power big data according to claim 6 is characterized in that: In step S42, the fitness function is expressed as: In the formula, is the sample size, is the hyperparameter The input-output model is The predicted value of samples, It is The actual value of the samples.

8. The method for analyzing regional carbon emission reduction potential based on power big data according to claim 6 is characterized in that: In step S44, the formula for updating the individual is expressed as: In the formula, It is Crayfish individuals The updated position at each moment is the step size control parameter. is a random number between [0,1], is The optimal individual position in the population at that moment, is Moment The location of each crayfish individual, is the step size control parameter.

9. The method for analyzing regional carbon emission reduction potential based on power big data according to claim 1 is characterized in that: In step S4, the step of obtaining the adjustment strategy includes: Input the target carbon emission data into the optimized input-output model and run it to obtain an output result, wherein the output result is used to determine the main source industries and key links of carbon emissions in the current economic system; Different adjustment scenarios are set according to the output results. For different adjustment scenarios, corresponding parameters are modified in the optimization input-output model. Then, the optimization input-output model is re-run to simulate the operation changes of the economic system and the changes of carbon emissions under the scenarios to obtain multiple scenario results. Compare the effects of different scenario results on achieving target carbon emissions based on the carbon emission reduction indicators, analyze the mutual influence and feedback mechanism between various industrial sectors, select the scenario results that effectively achieve the target carbon emissions and have the least impact on the economy and society, and specify adjustment strategies.

10. The method for analyzing regional carbon emission reduction potential based on power big data according to claim 1 is characterized in that: In step S4, the step of obtaining the carbon emission reduction strategy includes: Classify the policy measures, technical measures and market mechanism measures in the adjustment strategy to obtain multi-measure data, and clarify the goals and expected effects; Compare and analyze the various measures in the carbon emission reduction potential plan with the multi-measure data, extract the measures with good effects, and modify and improve the existing measures in the carbon emission reduction potential plan to obtain adjustment measures; According to the adjustment measures, the resources required for the time carbon emission reduction target are re-evaluated, and the resource allocation is adjusted accordingly to obtain an optimized carbon emission reduction potential plan, and the optimized input-output model is used to evaluate the effectiveness of the optimized carbon emission reduction potential plan to obtain an effect evaluation result, and according to the effect evaluation result, the optimized carbon emission reduction potential plan is optimized and improved to obtain the carbon emission reduction strategy document.

Images