Regional power carbon emission reduction potential assessment method considering green power transaction contract

Abstract

The invention relates to a regional electric power carbon emission reduction potential evaluation method considering a green power transaction contract. The method comprises the steps of obtaining a current electric power carbon emission of a target region in a current time period; determining a plurality of current carbon emission influence indexes corresponding to the current power carbon emission according to the current power carbon emission and a pre-established system dynamics model; performing analysis and prediction processing on each current carbon emission influence index to obtain a target carbon emission influence index prediction value of each current carbon emission influence index in the next time period of the current time period; and analyzing and processing each target carbon emission influence index prediction value to obtain the predicted power carbon emission of the target area in the next time period. Through the method, factors influencing regional power carbon emission change such as new energy power generation facility construction and green power transaction are deeply analyzed, and prediction of the power carbon emission of the target region in the next time period is realized from fine granularity consideration of the region level.

Description

Technical Field

[0001] The present invention relates to the field of carbon emissions in power systems, and in particular to a method for evaluating the potential for carbon emission reduction in regional electricity taking into account green electricity trading contracts. Background Art

[0002] The power system is one of the main sources of carbon emissions, and a refined assessment of the carbon emission reduction potential of the power system is crucial for the clean planning and management of the power system. The current power system includes multiple energy generation types such as coal power, hydropower, wind power, and solar power, and the network topology is complex.

[0003] At present, the energy yearbook and power yearbook published by the state usually use data aggregation to obtain the carbon emissions of regional power systems. There is a lack of analysis on the evolution trend of carbon emissions of power systems. The relevant prediction method theory has not been perfected, and has the following shortcomings:

[0004] 1) The existing electricity carbon emission calculation method does not adequately consider the impact and evolution trend of factors such as new energy construction and green electricity trading and consumption, and there is a lag in evaluating the impact of new energy development on the power system; 2) The current electricity carbon emission calculation process mainly considers electricity consumption, lacks the assessment of factors such as changes in energy consumption of social production and living behaviors, technological progress, and policy adjustments, which is not conducive to comprehensive analysis and measurement of low-carbon development trends in the power system; 3) The data sources of the influencing factors of changes in electricity carbon emissions are complex and the data samples with analytical value are small. It is difficult to quantify the data evolution relationship and the degree of impact, which in turn affects the reliability of the prediction of electricity carbon emissions. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method for evaluating the regional electricity carbon emission reduction potential taking into account green electricity trading contracts, aiming to solve at least one of the above technical problems.

[0006] In the first aspect, the technical solution of the present invention to solve the above technical problem is as follows: a method for evaluating the potential of regional electricity carbon emission reduction considering green electricity trading contracts, the method comprising:

[0007] Obtain the current electricity carbon emissions of the target area in the current time period;

[0008] According to the current electricity carbon emissions and a pre-established system dynamics model, a plurality of current carbon emissions impact indicators corresponding to the current electricity carbon emissions are determined, wherein the system dynamics model is established based on different electricity carbon emissions corresponding to different regions in the process of electricity production and consumption and a plurality of carbon emissions impact indicators corresponding to each of the electricity carbon emissions, wherein the plurality of carbon emissions impact indicators include an impact indicator corresponding to green electricity trading;

[0009] Analyze and predict each of the current carbon emission impact indicators to obtain a predicted value of a target carbon emission impact indicator for each of the current carbon emission impact indicators in the next time period of the current time period;

[0010] The predicted values ​​of the influencing indicators of each target carbon emission are analyzed and processed to obtain the predicted electricity carbon emission of the target area in the next time period.

[0011] The beneficial effect of the present invention is: the application scheme constructs a system dynamics model based on system dynamics through in-depth analysis of factors affecting changes in regional electricity carbon emissions, such as the construction of new energy power generation facilities and green electricity trading (also known as green electricity trading), which is used to analyze multiple current carbon emission influencing indicators that affect current electricity carbon emissions, and consider the fine-grained electricity carbon emissions at the regional level to achieve the prediction of electricity carbon emissions in the target area in the next time period, thereby improving the lag in evaluating the impact of new energy development on the power system.

[0012] Based on the above technical solution, the present invention can also be improved as follows.

[0013] Furthermore, the system dynamics model is established based on the following method:

[0014] Acquire historical data within multiple historical time periods, each of the historical time periods including multiple historical carbon emission related data and historical electricity carbon emissions, and for each of the historical time periods, the multiple historical carbon emission related data within the historical time period include carbon emission related data corresponding to different regions during the electricity production and consumption process of the historical time period, and the historical electricity carbon emissions within the historical time period include electricity carbon emissions corresponding to different regions during the electricity production and consumption process of the historical time period;

[0015] For each of the historical time periods, determining the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions within the historical time period;

[0016] For each of the historical time periods, according to the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions, determine the target historical carbon emission related data corresponding to the historical time period from the plurality of historical carbon emission related data;

[0017] The system dynamics model is established according to the target historical carbon emission related data and the historical electricity carbon emissions corresponding to each of the historical time periods.

[0018] The beneficial effect of adopting the above further scheme is that in the process of establishing the system dynamics model, the correlation between each historical carbon emission related data and the historical electricity carbon emissions in each historical time period is taken into account, so that the influence of each historical carbon emission related data on the historical electricity carbon emissions can be analyzed, so that the established system dynamics model can more accurately analyze how each carbon emission influencing indicator affects electricity carbon emissions.

[0019] Furthermore, the multiple historical carbon emission related data include the total electricity consumption of the whole society, thermal power generation, wind power generation, solar power generation, standard coal consumption for power generation, line loss electricity and residents' daily electricity consumption intensity.

[0020] The beneficial effect of adopting the above further scheme is that multiple historical carbon emission-related data including total social electricity consumption, thermal power generation, wind power generation, solar power generation, standard coal consumption for power generation, line loss and residents' daily electricity consumption intensity can accurately reflect from different aspects how carbon emission-related data affect electricity carbon emissions.

[0021] Furthermore, the system dynamics model is established according to the target historical carbon emission related data and the historical electricity carbon emissions corresponding to each of the historical time periods, including:

[0022] For each of the historical time periods, extracting the historical carbon emission impact indicators of different regions within the historical time period according to the target historical carbon emission related data;

[0023] For each of the historical time periods, determine the degree of influence of each historical carbon emissions impact indicator of each of the regions on the historical electricity carbon emissions within the historical time period;

[0024] For each of the historical time periods, the initial model is trained according to the historical carbon emission impact indicators of each of the regions within the historical time period, the historical electricity carbon emissions, and the degree of influence of each historical carbon emission impact indicator corresponding to each of the regions within the historical time period on the historical electricity carbon emissions, to obtain the predicted electricity carbon emissions for the next historical time period of the historical time period;

[0025] For each of the historical time periods, determine the loss value corresponding to the historical time period according to the predicted electricity carbon emissions in the next historical time period of the historical time period and the historical electricity carbon emissions in the next historical time period of the historical time period;

[0026] According to the loss values ​​corresponding to each of the historical time periods, the training of the initial model is completed to obtain the system dynamics model.

[0027] The beneficial effect of adopting the above further scheme is that in the process of establishing the system dynamics model, the influence relationship between the historical electricity carbon emissions and the historical electricity carbon emissions corresponding to each of the said regions within the historical time period and the historical carbon emissions influencing indicators is taken into account, so that the determined system dynamics model can more accurately analyze how each carbon emission influencing indicator affects electricity carbon emissions.

[0028] Furthermore, multiple historical carbon emission impact indicators of each of the regions include power energy structure, green electricity trading volume, power supply and demand relationship, transmission and distribution losses, industrial production conditions, social electricity intensity, green technology innovation degree and green electricity policy.

[0029] The beneficial effect of adopting the above further scheme is that since the multiple historical carbon emission influencing indicators of each of the regions include power energy structure, green electricity trading volume, power supply and demand relationship, transmission and distribution losses, industrial production conditions, social electricity consumption intensity, green technology innovation level and green electricity policy, based on the above information, a key indicator system of power carbon emissions that takes into account green electricity can be established to obtain a system dynamics model.

[0030] Further, the analyzing and predicting processing of each current carbon emission impact indicator to obtain a predicted value of a target carbon emission impact indicator of each current carbon emission impact indicator in the next time period of the current time period includes:

[0031] Analyze and predict each of the current carbon emission impact indicators using a grayscale prediction algorithm to obtain a first carbon emission impact indicator prediction value for each of the current carbon emission impact indicators in the next time period of the current time period;

[0032] Analyze and predict each of the current carbon emission impact indicators using a support vector machine algorithm to obtain a second carbon emission impact indicator prediction value for each of the current carbon emission impact indicators in the next time period of the current time period;

[0033] The first carbon emission impact index prediction value and the second carbon emission impact index prediction value are fused to obtain the target carbon emission impact index prediction value.

[0034] The beneficial effect of adopting the above further scheme is that the grayscale prediction algorithm has a certain robustness to outliers and noise to a certain extent, and performs better on small sample data; the support vector machine algorithm has a strong fitting ability and can effectively handle the situation of relatively small sample size. Combining the two can break through the limitations of their respective methods, improve the generalization ability of carbon emission influencing factor analysis, and correct the evaluation error caused by data inaccuracy. To this end, the present invention is designed to combine the advantages of the grayscale prediction algorithm and the support vector machine algorithm to improve the feature analysis ability and prediction accuracy of small sample data, and realize the deduction of the changing trend of small sample carbon emission reduction influencing factor data.

[0035] Further, the analysis and processing of the predicted values ​​of the target carbon emission impact indicators to obtain the predicted electricity carbon emission of the target area in the next time period includes:

[0036] By using a pre-trained regional power system carbon emission reduction potential assessment model, the predicted values ​​of each target carbon emission impact indicator are analyzed and processed to obtain the predicted electricity carbon emissions of the target area in the next time period. The regional power system carbon emission reduction potential assessment model is a model obtained by training a neural network based on historical carbon emission data, and the historical carbon emission data includes historical electricity carbon emissions and historical carbon emission impact indicators.

[0037] The beneficial effect of adopting the above further scheme is to explore the correlation between carbon emission reduction influencing factors and carbon emissions based on the in-depth analysis of historical carbon emission data by convolutional neural network algorithm technology, and establish a regional power system carbon emission reduction potential assessment model that considers multiple factors and error correction. The convolutional neural network algorithm is a data-driven neural network algorithm that performs better in dealing with multivariate time series regression problems. It can capture the degree of influence of different factors on electricity carbon emissions and the evolution pattern through the identification and analysis of historical carbon emission related data, so as to accurately predict the predicted electricity carbon emissions in the next time period.

[0038] In a second aspect, in order to solve the above technical problems, the present invention also provides a regional electricity carbon emission reduction potential assessment device considering green electricity trading contracts, the device comprising:

[0039] An acquisition module, used to acquire the current electricity carbon emissions of the target area in the current time period;

[0040] An impact index determination module is used to determine a plurality of current carbon emission impact indicators corresponding to the current electricity carbon emission according to the current electricity carbon emission and a pre-established system dynamics model, wherein the system dynamics model is established based on different electricity carbon emissions corresponding to different regions in the process of electricity production and consumption and a plurality of carbon emission impact indicators corresponding to each of the electricity carbon emissions, wherein the plurality of carbon emission impact indicators include an impact indicator corresponding to green electricity trading;

[0041] An impact index value prediction module is used to analyze and predict each of the current carbon emission impact indicators to obtain a target carbon emission impact index prediction value of each of the current carbon emission impact indicators in the next time period of the current time period;

[0042] The power carbon emission prediction module is used to analyze and process the predicted values ​​of the influencing indicators of each target carbon emission to obtain the predicted power carbon emission of the target area in the next time period.

[0043] In the third aspect, in order to solve the above-mentioned technical problems, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for evaluating the regional electricity carbon emission reduction potential considering green electricity trading contracts of the present application is implemented.

[0044] In a fourth aspect, in order to solve the above-mentioned technical problems, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for evaluating the regional electricity carbon emission reduction potential considering green electricity trading contracts of the present application is implemented.

[0045] Additional aspects and advantages of the present application will be partially given in the following description, which will become apparent from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for describing the embodiments of the present invention are briefly introduced below.

[0047] Figure 1 A flow chart of a method for evaluating the potential for carbon emission reduction in regional electricity considering green electricity trading contracts provided by one embodiment of the present invention;

[0048] Figure 2 A flow chart of another method for evaluating the potential of regional electricity carbon emission reduction considering green electricity trading contracts provided by an embodiment of the present invention;

[0049] Figure 3A schematic diagram of a relationship map of factors affecting carbon emissions of electricity provided by an embodiment of the present invention;

[0050] Figure 4 A schematic diagram of the structure of a device for evaluating the potential of regional electricity carbon emission reduction considering green electricity trading contracts provided by one embodiment of the present invention;

[0051] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The principles and features of the present invention are described below. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0053] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0054] The solution provided by the embodiment of the present invention can be applied to any application scenario where electricity carbon emissions prediction is required. The solution provided by the embodiment of the present invention can be executed by any electronic device, for example, it can be a user's terminal device, including at least one of the following: a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart TV, and a smart car device.

[0055] In order to facilitate the understanding of this solution, the relevant technical terms involved in this application are explained:

[0056] Carbon emissions: refers to the total amount of greenhouse gases such as carbon dioxide (CO2) released into the atmosphere by human activities, such as burning fossil fuels and land use changes. Since carbon dioxide accounts for the largest proportion of these gases, the term "carbon emissions" is often used as an abbreviation for "carbon dioxide emissions".

[0057] Electricity carbon accounting: refers to a method used to assess carbon emissions generated during the production and use of electricity. It aims to quantify greenhouse gas emissions from the power system, mainly carbon dioxide (CO2), to identify high-emission links and sources, and provide a basis for formulating emission reduction strategies.

[0058] Carbon emission factor: refers to the amount of carbon emissions generated per unit of energy during the combustion or use of each energy source. The carbon emission factor for electricity refers to the amount of carbon emissions generated per kilowatt-hour of electricity used.

[0059] The embodiment of the present invention provides a possible implementation method, such as Figure 1As shown, a flowchart of a method for evaluating the potential of regional electricity carbon reduction considering green electricity trading contracts is provided. The scheme can be executed by any electronic device, for example, a terminal device, or jointly executed by a terminal device and a server. For the convenience of description, the method provided by the embodiment of the present invention will be described below by taking the terminal device as the execution subject as an example. Figure 1 and Figure 2 The method may include the following steps:

[0060] Step S10, obtaining the current electricity carbon emissions of the target area in the current time period;

[0061] Step S20, determining a plurality of current carbon emission impact indicators corresponding to the current electricity carbon emission according to the current electricity carbon emission and a pre-established system dynamics model, wherein the system dynamics model is established based on different electricity carbon emissions corresponding to different regions in the process of electricity production and consumption and a plurality of carbon emission impact indicators corresponding to each of the electricity carbon emissions, wherein the plurality of carbon emission impact indicators include an impact indicator corresponding to green electricity trading;

[0062] Step S30, analyzing and predicting each of the current carbon emission impact indicators to obtain a predicted value of a target carbon emission impact indicator for each of the current carbon emission impact indicators in the next time period of the current time period;

[0063] Step S40: analyzing and processing the predicted values ​​of the target carbon emission impact indicators to obtain the predicted electricity carbon emission of the target area in the next time period.

[0064] Through the method of the present invention, through in-depth analysis of factors affecting changes in regional electricity carbon emissions such as construction of new energy power generation facilities and green electricity trading (also known as green electricity trading), a system dynamics model based on system dynamics is constructed to analyze multiple current carbon emission influencing indicators that affect current electricity carbon emissions. From the perspective of fine-grained electricity carbon emissions at the regional level, the electricity carbon emissions of the target area in the next time period are predicted, thereby improving the lag in evaluating the impact of new energy development on the power system.

[0065] The solution of the present invention is further described below in conjunction with the following specific embodiments. In this embodiment, a method for evaluating the regional electricity carbon emission reduction potential considering green electricity trading contracts may include the following steps:

[0066] Step S10, obtaining the current electricity carbon emissions of the target area in the current time period;

[0067] The target area refers to the area where electricity carbon emissions need to be measured, such as a city or an urban area of ​​a city. The current time period refers to a period of time, such as a year or a month. Electricity carbon emissions refer to the total amount of carbon dioxide emitted into the atmosphere after using electricity resources.

[0068] Step S20, determining a plurality of current carbon emission impact indicators corresponding to the current electricity carbon emission according to the current electricity carbon emission and a pre-established system dynamics model, wherein the system dynamics model is established based on different electricity carbon emissions corresponding to different regions in the process of electricity production and consumption and a plurality of carbon emission impact indicators corresponding to each of the electricity carbon emissions, wherein the plurality of carbon emission impact indicators include an impact indicator corresponding to green electricity trading;

[0069] Among them, system dynamics is a structured analysis method used to describe the interactions and influences between various factors in a system. Therefore, in this application scheme, a system dynamics model is constructed based on system dynamics to deeply understand how different carbon emission influencing indicators affect electricity carbon emissions.

[0070] In addition, in the present application, the construction of the system dynamics model fully considers the impact between electricity carbon emissions and carbon emissions influencing indicators in the process of electricity production and consumption, which enables the system dynamics model to analyze the current electricity carbon emissions more accurately and comprehensively.

[0071] Among them, green electricity trading refers to green electricity trading. In simple terms, users can purchase electricity from new energy sources such as wind power and photovoltaic power generation through electricity trading. Electricity carbon emissions will also be generated during the production and consumption of new energy sources. Therefore, in this application, the carbon emissions impact indicators and electricity carbon emissions generated by green electricity trading are fully considered, making the analysis of current electricity carbon emissions more comprehensive and accurate.

[0072] Optionally, a possible implementation of step S20 is as follows:

[0073] Based on the current electricity carbon emissions and a pre-established carbon emission causal relationship map, obtain the various carbon emission impact indicators that affect the current electricity carbon emissions, and the degree of impact on the current electricity carbon emissions, wherein the carbon emission causal relationship map is used to describe the degree of impact of each carbon emission impact indicator on the electricity carbon emissions;

[0074] Based on the impact degree and the current electricity carbon emissions, a plurality of current carbon emissions impact indicators corresponding to the current electricity carbon emissions are determined through a pre-established system dynamics model.

[0075] Optionally, the above system dynamics model is established based on the following method:

[0076] S1, obtaining historical data within a plurality of historical time periods, wherein the historical data of each historical time period includes a plurality of historical carbon emission-related data and a historical electricity carbon emission amount, and for each historical time period, the plurality of historical carbon emission-related data within the historical time period includes carbon emission-related data corresponding to different regions during the electricity production and consumption process of the historical time period, and the historical electricity carbon emission amount within the historical time period includes electricity carbon emission amounts corresponding to different regions during the electricity production and consumption process of the historical time period;

[0077] Optionally, the above historical data can be collected from the China Energy Statistical Yearbook, China Electricity Yearbook, Electric Power Industry Statistical Data Compilation, China Regional Power Grid Baseline Emission Factors, as well as typical provincial statistical yearbooks, provincial energy big data centers, and power carbon monitoring platforms.

[0078] After obtaining the historical data, in order to reduce the influence of interference factors in the historical data, before executing S2, the method further includes: analyzing the historical data in multiple historical time periods ( Figure 2 The data preprocessing can be completed through three stages: standardization, cleaning and reduction.

[0079] Among them, standardization is to process the structure and type of historical data obtained from multiple historical time periods to ensure that the data has a unified format; cleaning is to filter and "denoise" the historical data obtained from multiple historical time periods, extract valid data and mark the confidence level; reduction is to delete redundant content from the historical data obtained from multiple historical time periods, thereby improving the data value density.

[0080] Data standardization includes defining the data types, character restrictions, measurement units, value ranges, etc. of different fields. Taking the influencing factor "power generation" as an example, the measurement units of the values ​​obtained from different sources are different, including 100 million kWh, 10,000 kWh, and megawatt-hours, etc., and the relevant data needs to be unified using data standardization methods.

[0081] In data cleaning, missing values ​​are processed by filling in the missing values, where numerical data is filled in by the mean method, and categorical data is filled in by the value with the most categories. Since some outliers may be caused by specific business actions, the retention principle is used to process outliers.

[0082] It should be noted that the above three processing methods of standardization, cleaning and reduction can be performed sequentially without limiting the execution order.

[0083] More specifically, the pre-processed carbon emission related data (ie, carbon emission influencing factors) and electricity carbon emission data can be organized into a tabular form, as shown in Table 1.

[0084] Table 1

[0085]

[0086] Optionally, the multiple historical carbon emission related data include total social electricity consumption, thermal power generation, wind power generation, solar power generation, standard coal consumption for power generation, line loss electricity and residential electricity intensity. These data are analog time series values, which need to be aligned with timestamps, and the time scale is monthly or annual.

[0087] Carbon emission impact indicators that affect historical electricity carbon emissions can be extracted from historical carbon emission related data. One historical carbon emission related data corresponds to one historical electricity carbon emission.

[0088] S2, for each of the historical time periods, determining the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions within the historical time period;

[0089] Among them, the size of the correlation reflects the impact of historical carbon emission related data on historical electricity carbon emissions. The larger the correlation, the greater the impact. Conversely, the smaller the correlation, the smaller the impact.

[0090] Optionally, one possible implementation of S2 is as follows:

[0091] For each of the historical time periods, the Pearson correlation coefficient method is used to determine the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions in the historical time period. Specifically, the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions in the historical time period is determined using the first formula, wherein the first formula is:

[0092]

[0093] Among them, r is used to represent data correlation, which can also be called correlation coefficient. Its value range is between -1 and 1. The larger the value, the higher the correlation. i Represents the i-th historical carbon emission related data. i Represents the historical electricity carbon emissions corresponding to the i-th historical carbon emission related data. represents the mean of the corresponding variable sample, and n represents the total number of historical carbon emission related data.

[0094] After calculating the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions within the historical time period, a Pearson correlation coefficient matrix can be obtained. Each element in the matrix represents the correlation coefficient between two variables, which can be used to measure the degree of linear correlation between the two variables.

[0095] S3, for each of the historical time periods, determining the target historical carbon emission related data corresponding to the historical time period from a plurality of the historical carbon emission related data according to the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions;

[0096] The target historical carbon emission related data is the historical carbon emission related data which has a greater correlation with the historical electricity carbon emissions among various historical carbon emission related data, and may be at least one of various historical carbon emission related data.

[0097] Specifically, one possible implementation of S3 is as follows:

[0098] For each of the historical time periods, based on the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions, the historical carbon emission related data with a correlation within a set range (for example, 0.6-0.8) among the multiple historical carbon emission related data are determined as the target historical carbon emission related data corresponding to the historical time period.

[0099] As an example, based on the analysis results of the Pearson correlation coefficient, all historical carbon emission related data are sorted from large to small according to the correlation of electricity carbon emissions, and historical carbon emission related data with a correlation greater than 0.8 are selected as the target historical carbon emission related data for further analysis. Through the investigation of multiple literatures, when |r|>0.8, it is considered that there is an extremely strong correlation between the two variables; when 0.6<|r|≤0.8, it is considered that there is a strong correlation between the two variables; when 0.4<|r|≤0.6, it is considered that there is a moderate degree of correlation between the two variables; when 0.2<|r|≤0.4, it is considered that there is a weak correlation between the two variables; when |r|≤0.2, it is considered that there is an extremely weak correlation or no correlation between the two variables. Among the various correlations, the historical carbon emission related data corresponding to 0.4<|r|≤0.6 can be selected as the target historical carbon emission related data.

[0100] S4: establishing the system dynamics model according to the target historical carbon emission related data and the historical electricity carbon emissions corresponding to each of the historical time periods.

[0101] Optionally, an implementation of the above S4 is:

[0102] S41, for each of the historical time periods, extracting historical carbon emission impact indicators of different regions within the historical time period according to the target historical carbon emission related data;

[0103] Optionally, multiple historical carbon emission impact indicators for each of the regions include power energy structure, green electricity trading volume, power supply and demand relationship, transmission and distribution losses, industrial production conditions, social electricity intensity, green technology innovation level and green electricity policy.

[0104] Among them, the power energy structure refers to the power generation of various power generation equipment used in the region in the power system, including thermal power, hydropower, nuclear power, wind power, and photovoltaic power stations. This indicator is quantified into five data items: thermal power generation, hydropower generation, nuclear power generation, wind power generation, and photovoltaic power generation, which are input into the power carbon emission prediction model. Changes in energy conditions such as increasing the installed capacity of renewable energy (such as wind power, photovoltaic power stations, etc.) and reducing the proportion of coal-fired power generation can improve the utilization rate of clean energy, reduce dependence on high-carbon energy, and help reduce carbon emissions from electricity.

[0105] Green electricity trading volume refers to the amount of renewable energy used in the region traded through the power trading platform in the power system. This indicator is quantified as the total amount of renewable energy traded by users in the region. Increasing the amount of green electricity trading can increase the proportion of renewable energy in the regional power system, thereby reducing carbon emissions from electricity.

[0106] The power supply and demand relationship refers to the relationship between the power supplied by the power system and the actual demand of users. This indicator can be quantified as the ratio of "power generation / total social power demand". The balance of power supply and demand is of great significance to the low-carbon operation of the power system and helps to improve the economic efficiency of the power system.

[0107] Transmission and distribution loss refers to the energy loss caused by resistance, inductance, capacitance and other factors during the transmission and distribution of electricity. This indicator can be quantified as line loss. Reducing transmission and distribution loss and improving the transmission efficiency of electric energy can effectively reduce carbon emissions from electricity.

[0108] Industrial production refers to the electricity consumption of industrial production in a certain region, which can be quantified as the total industrial electricity consumption of the society. Through the analysis of historical data from the China Electricity Yearbook, it is found that industrial production electricity accounts for more than 80% of the total social electricity consumption all year round. When the industrial industry in a region changes, the carbon emissions of the region will also change accordingly.

[0109] Social power intensity refers to the amount of electricity consumed in a region and is an important indicator for measuring regional power efficiency. This indicator is calculated by "annual power consumption / annual GDP (kWh / 10,000 yuan)". A reduction in social power intensity means an increase in the utilization rate of power resources.

[0110] The degree of green technology innovation refers to the scientific and technological technologies used in the power system to promote green development, including efficient green power generation technology, intelligent management of power systems, etc. This indicator can be quantified as the number of invention patents accepted. Technological innovation can improve energy efficiency, reduce the demand for high-carbon energy, and play a positive role in reducing carbon emissions from electricity.

[0111] Green power policy refers to the policies and measures issued by the government to support green power generation, including subsidies, preferential policies, etc. This indicator can be quantified as the number of policy documents issued by provincial and municipal government departments. A good policy environment can promote the development of renewable energy and reduce carbon emissions from electricity.

[0112] S42, for each of the historical time periods, determining the degree of influence of each historical carbon emission impact indicator of each of the regions on the historical electricity carbon emissions within the historical time period; the degree of influence can be represented based on the carbon emission causal relationship map described above, see for details Figure 3 , the impact includes positive feedback (through Figure 3 The "+" in the Figure 3 The “-” in the figure indicates that positive feedback indicates that the historical carbon emissions influencing index has an impact on the historical electricity carbon emissions that increases the electricity carbon emissions, and negative feedback indicates that the historical carbon emissions influencing index has an impact on the historical electricity carbon emissions that reduces the electricity carbon emissions.

[0113] Among them, the carbon emission cause and effect map can be drawn on the Vens im platform. Figure 3 As shown, the key state variables (carbon emission impact indicators) are represented as boxes, and the information feedback is represented by curves with arrows, distinguishing between positive feedback and negative feedback.

[0114] As an example, an increase in the intensity of social electricity consumption may lead to an increase in fossil fuel consumption, which in turn increases carbon emissions from electricity. This is a positive feedback loop, meaning the impact is positive feedback. At the same time, increasing the volume of green electricity trading can reduce the proportion of fossil energy in the power energy structure and reduce carbon emissions from electricity, forming a negative feedback loop, meaning the impact is negative feedback.

[0115] S43, for each of the historical time periods, according to the historical carbon emission impact indicators of each of the regions within the historical time period, the historical electricity carbon emissions, and the degree of influence of each of the historical carbon emission impact indicators corresponding to each of the regions within the historical time period on the historical electricity carbon emissions, the initial model is trained to obtain the predicted electricity carbon emissions for the next historical time period of the historical time period;

[0116] The above initial model is established based on system dynamics. System dynamics is a structured analysis method used to describe the interactions and influences between various factors in a system. It can deeply understand how different factors (carbon emission influencing indicators) affect electricity carbon emissions. The boundaries of the system dynamics model are limited to the process of electricity production and consumption, focusing on the penetration rate of renewable energy. The key state variables of the system dynamics model include power energy structure, green electricity trading volume, carbon emissions, etc., and create stocks and flows for key state variables, where the stock is the accumulated amount in the system at a certain moment, and the flow is the inflow or outflow that causes the stock to change. For example, in the method of this embodiment, the carbon emissions of the power system are the stocks in the system, and its rate of change over time is the flow. A recursive relationship between stocks and flows is established based on historical data as the initial model in the scheme of this application.

[0117] Optionally, the above initial model can be expressed based on the following second formula:

[0118] L(t+1)=L(t)+γ·(G(t)-L(t)) (2)

[0119] Among them, L(t) is the stock at time t; G(t) is a function that generates flow, which is used to indicate the rate of change of the stock affected by other variables in the system. For example, every increase of 1 unit of power generation may result in an increase of 0.5 units of carbon emissions; γ is the feedback coefficient, which indicates the intensity of feedback. The stock is the accumulated amount in the system at a certain moment, and the flow is the inflow or outflow that causes the stock to change. In this scheme, the carbon emissions of electricity are the stocks in the system, and the rate of change of the carbon emissions of electricity over time is the flow. Thus, in the scheme of this application, L(t) represents the historical carbon emissions of electricity in a historical time period, G(t) represents the degree of influence of each historical carbon emission influencing index corresponding to each of the said regions in the historical time period on the historical carbon emissions of electricity, which can be represented by a carbon emission causal relationship map, and L(t+1) represents the predicted carbon emissions of electricity in the next historical time period of the historical time period.

[0120] S44, for each of the historical time periods, determine the loss value corresponding to the historical time period according to the predicted carbon emissions of electricity in the next historical time period of the historical time period and the historical carbon emissions of electricity in the next historical time period of the historical time period;

[0121] S45, completing the training of the initial model according to the loss values ​​corresponding to each of the historical time periods to obtain the system dynamics model.

[0122] The establishment process of the above system dynamics model can correspond to Figure 2 As shown in the figure, the correlation between the factors affecting electricity carbon emissions (carbon emission influencing indicators) is analyzed based on system dynamics, and a key influencing indicator system for electricity carbon emissions is designed.

[0123] Step S30, analyzing and predicting each of the current carbon emission impact indicators to obtain a predicted value of a target carbon emission impact indicator for each of the current carbon emission impact indicators in the next time period of the current time period;

[0124] Optionally, the above S30 can be obtained based on a GRAY-SVM hybrid deep learning method, wherein GRAY represents a grayscale prediction algorithm and SVM represents a support vector machine algorithm.

[0125] Since the original data on factors affecting carbon emission reduction in the power system (such as the relationship between power supply and demand, social electricity consumption intensity, etc.) are mostly released regularly by relevant management departments with long intervals, the amount of data that can be collected is small, resulting in poor generalization ability when learning the impact relationship between key indicator factors and carbon emissions, and unable to fully reflect the correlation characteristics between data, thereby reducing the accuracy of the analysis and making it difficult to deduce the evolution trend of factors affecting carbon emission reduction in future years.

[0126] The grayscale prediction algorithm is robust to outliers and noise to a certain extent and performs well on small sample data; the support vector machine algorithm has strong fitting capabilities and can effectively handle situations with relatively small sample sizes. Combining the two can break through the limitations of their respective methods, improve the generalization ability of carbon emission influencing factor analysis, and correct evaluation errors caused by data inaccuracy.

[0127] Based on the above principle, the hybrid deep learning method is used to analyze and predict each of the current carbon emission impact indicators to obtain the target carbon emission impact indicator prediction value of each of the current carbon emission impact indicators in the next time period of the current time period, which can be specifically as follows:

[0128] S301, analyzing and predicting each of the current carbon emission impact indicators by using a grayscale prediction algorithm to obtain a first carbon emission impact indicator prediction value of each of the current carbon emission impact indicators in the next time period of the current time period;

[0129] S302, analyzing and predicting each of the current carbon emission impact indicators by using a support vector machine algorithm to obtain a second carbon emission impact indicator prediction value of each of the current carbon emission impact indicators in the next time period of the current time period;

[0130] S303: fusing the first carbon emission impact index prediction value and the second carbon emission impact index prediction value to obtain the target carbon emission impact index prediction value.

[0131] The data analysis method based on the GRAY-SVM hybrid algorithm in the present invention fully combines the advantages of the grayscale prediction algorithm and the support vector machine algorithm to improve the feature analysis capability and prediction accuracy of small sample data, and realizes the deduction of the changing trend of small sample carbon emission reduction influencing factor data.

[0132] Furthermore, one implementation of the above S301 is:

[0133] By using the third formula corresponding to the grayscale prediction algorithm, each of the current carbon emission impact indicators is analyzed and predicted to obtain a first carbon emission impact indicator prediction value of each current carbon emission impact indicator in the next time period of the current time period, wherein the third formula is:

[0134]

[0135] in, is the predicted value of the first carbon emission impact indicator of each current carbon emission impact indicator in the next time period of the current time period, X gray (s) is the indicator value corresponding to each of the current carbon emission impact indicators, and α and β are parameters determined according to the grayscale prediction algorithm.

[0136] Furthermore, one implementation of the above S302 is:

[0137] The fourth formula corresponding to the support vector machine algorithm, which can also be called the carbon emission influencing factor analysis model, analyzes and predicts each of the current carbon emission influencing indicators to obtain a second carbon emission influencing indicator prediction value of each of the current carbon emission influencing indicators in the next time period of the current time period, wherein the fourth formula is:

[0138]

[0139] Among them, X SVM represents the predicted value of the second carbon emission impact indicator of each current carbon emission impact indicator in the next time period of the current time period, τ i is the Lagrange multiplier, which indicates the contribution of the ith carbon emission impact index (current carbon emission impact index) to the carbon emission impact factor analysis model. The quadratic programming algorithm is used to solve the dual problem and obtain the optimal Lagrange multiplier τ i ;h i is the true value of the ith carbon emission impact indicator (i.e., the indicator value of the current carbon emission impact indicator); K(α i ,α) is a kernel function used to calculate the nonlinear mapping in the original feature space. The kernel function used in the method of this embodiment is a radial basis function kernel; σ is a bias term; m is the number of current carbon emissions influencing indicators.

[0140] It should be noted that the calculation process of the carbon emission influencing factor analysis model based on the support vector machine algorithm is as follows:

[0141] 1) Establish the basic formula of the carbon emission influencing factor analysis model based on the support vector machine algorithm, as shown in the fifth formula:

[0142] f(h)=<ω,h>+σ (5)

[0143] Among them, ω is the weight vector, h is the input feature vector, and σ is the bias term.

[0144] 2) In order to improve the numerical prediction accuracy of carbon emission influencing factors, the prediction error is limited, a threshold ∈ is set, and only data exceeding the threshold is punished to control the tolerance of the model to errors. Among them, the objective function is expressed by the L2 norm of the weight vector, C is the regularization parameter, and g i and f(h i ) are the true value and predicted value of the i-th training sample, respectively. Each training sample represents the index value of the carbon emissions impact index in a time period. Specifically, as shown in the sixth and seventh formulas:

[0145] L ∈ (g,f(h))=max(0,|gf(h)|-∈) (6)

[0146]

[0147] 3) Using the Lagrange multiplier method, the original problem is transformed into a dual problem, and the relevant constraints are integrated into the objective function, as shown in the eighth formula.

[0148]

[0149] Among them, τ i is the Lagrange multiplier

[0150] By deducing the relevant parameters in the eighth formula above, the carbon emission influencing factor analysis model of this embodiment is finally obtained:

[0151] Furthermore, one implementation of the above S303 is:

[0152] The first carbon emission impact index prediction value and the second carbon emission impact index prediction value are fused through the ninth formula to obtain the target carbon emission impact index prediction value, wherein the ninth formula is:

[0153]

[0154] Among them, Xmix is the predicted value of the target carbon emission impact indicator, and δ is the mixing parameter. represents the predicted value of the first carbon emission impact indicator, X SVM Represents the predicted value of the second carbon emission impact indicator.

[0155] In this scheme, the calculated index value of the current carbon emissions impact index is brought into the carbon emissions impact factor analysis model to obtain the carbon emissions and carbon reduction assessment of the power system in future years, that is, the predicted value of the target carbon emissions impact index for the next time period of the current time period.

[0156] Step S40: Analyze and process the predicted values ​​of the target carbon emission impact indicators to obtain the predicted electricity carbon emission of the target area in the next time period. Figure 2 The calculations shown in Figure 1 project the carbon reduction potential of the power system in future years.

[0157] Optionally, an implementation of the above S40 is:

[0158] Through the pre-trained regional power system carbon emission reduction potential assessment model, the predicted values ​​of each target carbon emission impact index are analyzed and processed to obtain the predicted power carbon emission of the target area in the next time period. The regional power system carbon emission reduction potential assessment model is a model obtained by training a neural network based on historical carbon emission data. The historical carbon emission data includes historical power carbon emissions and historical carbon emission impact indicators. Figure 2 The dynamic change trend of the factors affecting electricity carbon emissions is calculated based on the hybrid deep learning method as shown in the figure.

[0159] In this step, the predicted value of the target carbon emissions impact index for the next time period of the current time period calculated in the above step is substituted into the power system carbon emission reduction potential assessment model to obtain the power system carbon emissions (predicted power carbon emissions) and carbon emission reduction assessment in future years (the next time period of the current time period).

[0160] Among them, the power system carbon emission reduction potential assessment model is a function established based on a neural network to describe the relationship between "carbon emission impact index" (x) and "power carbon emissions" (y), that is, by inputting a set of x, a y can be obtained.

[0161] After obtaining the predicted value of the target carbon emission impact index for the next time period of the current time period, the predicted value of the target carbon emission impact index for the next time period of the current time period can be used as all the input parameters x required by the power system carbon emission reduction potential assessment model. As an example, the x value of a certain year is input into the trained power system carbon emission reduction potential assessment model to obtain the y value of that year. Users can perform carbon emission reduction assessment based on the obtained y value.

[0162] Based on the in-depth analysis of historical carbon emission data using the Convolutional Neural Networks (CNN) technology, this paper explores the relationship between carbon emission reduction influencing factors and carbon emissions, and establishes a carbon emission reduction potential assessment model for the power system that takes into account multiple factors and error correction. The convolutional neural network algorithm is a data-driven neural network algorithm that performs well in dealing with multivariate time series regression problems. It can capture the degree of influence and evolution pattern of different factors on power carbon emissions through the identification and analysis of historical carbon emission data. The core technical parts of the power system carbon emission reduction potential assessment model include convolution operations, pooling operations, fully connected layer calculations, loss function settings, etc.

[0163] Therefore, in the present application, the construction process of the above-mentioned power system carbon emission reduction potential assessment model (corresponding to Figure 2 The relationship between the quantitative assessment influencing factors and the carbon emissions of electricity is shown in the figure, and the electricity carbon emission reduction potential assessment model considering multiple factors and error correction is established) is:

[0164] In the convolution operation of the power system carbon reduction potential assessment model, each neuron performs a weighted summation on a local area of ​​the input data and then passes it through a nonlinear activation function. For a given input I and a convolution kernel K, the convolution operation is shown in the tenth formula.

[0165] (I*K)(i,j)=∑ m ∑ n I(m,n)·K(im,jn) (10)

[0166] Among them, I(m,n) represents the input carbon emission influencing factor, that is, the value of the predicted value of the target carbon emission influencing index of the next time period of the current time period at position (m,n), K(im,jn) is the weight of the convolution kernel at position (im,jn), and (I*K)(i,j) is the value of the feature map after convolution at position (i,j).

[0167] The pooling operation of the power system carbon emission reduction potential assessment model is mainly used to reduce the spatial dimension of the feature graph, reduce the number of parameters and the amount of calculation, and improve the stability of the model through the pooling operation. The pooling operation is shown in the eleventh formula.

[0168] P(i,j)=max m,n∈pooling window I(i·s+m,j·s+n) (11)

[0169] Among them, P(i,j) is the value of the feature map at position (i,j) after pooling, I is the input feature map, s is the step size, and m,n represent the index within the pooling window.

[0170] The convolution and pooling operation results are mapped and calculated and output through the fully connected layer of the power system carbon emission reduction potential assessment model. Each neuron in the fully connected layer is connected to all neurons in the previous layer. The calculation result of the fully connected layer can be expressed as the twelfth formula:

[0171] Y(i)=∑ j W(i,j)·I(j)+b(i) (12)

[0172] Among them, I(j) is the input of the previous layer, W(i,j) is the weight, b(i) is the bias term, and Y(i) is the output value of the neuron in the i-th layer.

[0173] In order to better monitor the data overfitting phenomenon in the training process of the power carbon emission reduction potential assessment model, the method of this embodiment defines a loss function based on mean square error to optimize the model weights and biases. The loss function is shown in the thirteenth and fourteenth formulas:

[0174]

[0175] W t+1 =W t -μ (14)

[0176] Among them, y i is the true value of carbon emissions, that is, the electricity carbon emissions of the ith sample corresponding to a certain area in the historical carbon emissions data in a time period t. is the predicted value of carbon emissions, that is, the predicted value of carbon emissions of electricity corresponding to the i-th sample in this time period, N is the number of samples, and W t is the current weight, μ is the result of the learning rate * the gradient of the loss function with respect to the weight, W t+1 is the next weight.

[0177] The obtained fully connected layer result h is weighted to obtain the predicted value of regional electricity carbon emissions in the future year (the next time period t+1 of a time period t) By subtracting the carbon emissions in the previous year, the carbon emission reduction potential of the region can be obtained. o is the weight vector of the output layer, b o is the bias term, Y Carbon is the carbon emission reduction potential of electricity in the region, and Y′ is the historical carbon emissions in the previous year, as shown in the following formulas 15 and 16:

[0178]

[0179] Furthermore, this embodiment introduces a carbon emission scenario analysis strategy into the regional power system carbon emission reduction potential assessment model. Construct different future scenarios, such as high carbon emission scenarios, low carbon emission scenarios, technology innovation leading scenarios, etc., set corresponding model parameters for each scenario, such as energy consumption efficiency, clean energy growth rate, application degree of carbon capture technology, etc., use the regional power carbon emission reduction potential assessment model, combined with the deduced values ​​of carbon emission influencing factors, simulate and predict each scenario, and obtain the carbon emissions and emission reduction potential under different scenarios. By adjusting the key influencing factors of the input under different assumptions, predicting and comparing possible carbon emission paths in the future, it helps decision makers understand the potential impacts of implementing different emission reduction measures and technological advances, so as to formulate policies more targetedly. It will also help to more comprehensively identify potential risks and opportunities and improve the adaptability and resilience of the power system.

[0180] Through the scheme of the present invention, the factors affecting the changes in regional electricity carbon emissions, such as the construction of new energy power generation facilities and green electricity trading, are deeply analyzed, a relationship map of factors affecting electricity carbon emissions based on system dynamics is established, and a key influencing indicator system including dimensions such as power energy structure, green electricity trading volume, social electricity consumption intensity, and power supply and demand relationship is formed. The hybrid deep learning algorithm is used to quantify the influencing factors with small sample data characteristics, and a power carbon emission reduction potential assessment model considering multiple factors and error correction is designed. The dynamic change trend of power carbon emissions is analyzed and deduced, a more reliable assessment of the power system carbon emission reduction potential is carried out, and power carbon emission reduction countermeasures are provided to help build a cleaner and more efficient power system.

[0181] Based on Figure 1 Based on the same principle as the method shown in , the embodiment of the present invention also provides a regional electricity carbon emission reduction potential assessment device 20 considering green electricity trading contracts, such as Figure 4 As shown in , the regional electricity carbon emission reduction potential assessment device 20 considering green electricity trading contracts may include an acquisition module 210, an impact index determination module 220, an impact index value prediction module 230 and an electricity carbon emission prediction module 240, wherein:

[0182] The acquisition module 210 is used to acquire the current electricity carbon emissions of the target area in the current time period;

[0183] The impact index determination module 220 is used to determine a plurality of current carbon emission impact indicators corresponding to the current electricity carbon emission according to the current electricity carbon emission and a pre-established system dynamics model, wherein the system dynamics model is established based on different electricity carbon emissions corresponding to different regions in the process of electricity production and consumption and a plurality of carbon emission impact indicators corresponding to each of the electricity carbon emissions, wherein the plurality of carbon emission impact indicators include an impact indicator corresponding to green electricity trading;

[0184] The impact index value prediction module 230 is used to analyze and predict each of the current carbon emission impact indicators to obtain a target carbon emission impact index prediction value of each of the current carbon emission impact indicators in the next time period of the current time period;

[0185] The power carbon emission prediction module 240 is used to analyze and process the predicted values ​​of the target carbon emission impact indicators to obtain the predicted power carbon emission of the target area in the next time period.

[0186] Optionally, the system dynamics model is obtained by training based on the following model training module, wherein the model training module is used to:

[0187] Acquire historical data within multiple historical time periods, each of the historical time periods including multiple historical carbon emission related data and historical electricity carbon emissions, and for each of the historical time periods, the multiple historical carbon emission related data within the historical time period include carbon emission related data corresponding to different regions during the electricity production and consumption process of the historical time period, and the historical electricity carbon emissions within the historical time period include electricity carbon emissions corresponding to different regions during the electricity production and consumption process of the historical time period;

[0188] For each of the historical time periods, determining the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions within the historical time period;

[0189] For each of the historical time periods, according to the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions, determine the target historical carbon emission related data corresponding to the historical time period from the plurality of historical carbon emission related data;

[0190] The system dynamics model is established according to the target historical carbon emission related data and the historical electricity carbon emissions corresponding to each of the historical time periods.

[0191] Optionally, the multiple historical carbon emission related data include total social electricity consumption, thermal power generation, wind power generation, solar power generation, standard coal consumption for power generation, line loss electricity and residents' living electricity intensity.

[0192] Optionally, when establishing the system dynamics model according to the target historical carbon emission related data and the historical electricity carbon emissions corresponding to each of the historical time periods, the model training module is specifically used to:

[0193] For each of the historical time periods, extracting the historical carbon emission impact indicators of different regions within the historical time period according to the target historical carbon emission related data;

[0194] For each of the historical time periods, determining the impact relationship between the historical electricity carbon emissions and the historical carbon emissions impact index of each of the regions within the historical time period;

[0195] For each of the historical time periods, the initial model is trained according to the historical carbon emissions impact index of each of the regions within the historical time period, the historical electricity carbon emissions, and the historical electricity carbon emissions corresponding to each of the regions within the historical time period and the impact relationship between the historical carbon emissions impact index, to obtain the predicted electricity carbon emissions for the next historical time period of the historical time period;

[0196] For each of the historical time periods, determine the loss value corresponding to the historical time period according to the predicted electricity carbon emissions in the next historical time period of the historical time period and the historical electricity carbon emissions in the next historical time period of the historical time period;

[0197] According to the loss values ​​corresponding to each of the historical time periods, the training of the initial model is completed to obtain the system dynamics model.

[0198] Optionally, multiple historical carbon emission impact indicators for each of the regions include power energy structure, green electricity trading volume, power supply and demand relationship, transmission and distribution losses, industrial production conditions, social electricity intensity, green technology innovation level and green electricity policy.

[0199] Optionally, when the impact index value prediction module 230 analyzes and predicts each of the current carbon emission impact indicators to obtain a predicted value of the target carbon emission impact indicator of each of the current carbon emission impact indicators in the next time period of the current time period, it is specifically used to:

[0200] Analyze and predict each of the current carbon emission impact indicators using a grayscale prediction algorithm to obtain a first carbon emission impact indicator prediction value for each of the current carbon emission impact indicators in the next time period of the current time period;

[0201] Analyze and predict each of the current carbon emission impact indicators using a support vector machine algorithm to obtain a second carbon emission impact indicator prediction value for each of the current carbon emission impact indicators in the next time period of the current time period;

[0202] The first carbon emission impact index prediction value and the second carbon emission impact index prediction value are fused to obtain the target carbon emission impact index prediction value.

[0203] Optionally, when the power carbon emission prediction module 240 analyzes and processes the predicted values ​​of the target carbon emission impact indicators to obtain the predicted power carbon emission of the target area in the next time period, it is specifically used to:

[0204] By using a pre-trained regional power system carbon emission reduction potential assessment model, the predicted values ​​of each target carbon emission impact indicator are analyzed and processed to obtain the predicted electricity carbon emissions of the target area in the next time period. The regional power system carbon emission reduction potential assessment model is a model obtained by training a neural network based on historical carbon emission data, and the historical carbon emission data includes historical electricity carbon emissions and historical carbon emission impact indicators.

[0205] The regional electricity carbon emission reduction potential assessment device considering green electricity trading contracts in the embodiment of the present invention can execute the regional electricity carbon emission reduction potential assessment method considering green electricity trading contracts provided in the embodiment of the present invention, and the implementation principle is similar. The actions performed by each module and unit in the regional electricity carbon emission reduction potential assessment device considering green electricity trading contracts in each embodiment of the present invention correspond to the steps in the regional electricity carbon emission reduction potential assessment method considering green electricity trading contracts in each embodiment of the present invention. For the detailed functional description of each module of the regional electricity carbon emission reduction potential assessment device considering green electricity trading contracts, please refer to the description of the corresponding regional electricity carbon emission reduction potential assessment method considering green electricity trading contracts shown in the previous text, which will not be repeated here.

[0206] Among them, the above-mentioned regional electricity carbon emission reduction potential assessment device considering green electricity trading contracts can be a computer program (including program code) running in a computer device. For example, the regional electricity carbon emission reduction potential assessment device considering green electricity trading contracts is an application software; the device can be used to execute the corresponding steps in the method provided in the embodiment of the present invention.

[0207] In some embodiments, the regional electricity carbon emission reduction potential assessment device considering green electricity trading contracts provided in an embodiment of the present invention can be implemented in a combination of software and hardware. As an example, the regional electricity carbon emission reduction potential assessment device considering green electricity trading contracts provided in an embodiment of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the regional electricity carbon emission reduction potential assessment method considering green electricity trading contracts provided in an embodiment of the present invention. For example, the processor in the form of a hardware decoding processor can use one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs) or other electronic components.

[0208] In other embodiments, the regional electricity carbon emission reduction potential assessment device considering green electricity trading contracts provided by the embodiments of the present invention can be implemented in a software manner. Figure 4 A regional electricity carbon emission reduction potential assessment device considering green electricity trading contracts stored in a memory is shown, which can be software in the form of programs and plug-ins, and includes a series of modules, including an acquisition module 210, an impact indicator determination module 220, an impact indicator value prediction module 230 and an electricity carbon emission prediction module 240, which are used to implement the regional electricity carbon emission reduction potential assessment method considering green electricity trading contracts provided in an embodiment of the present invention.

[0209] The modules involved in the embodiments of the present invention may be implemented by software or hardware, wherein the name of a module does not limit the module itself in some cases.

[0210] Based on the same principle as the method shown in the embodiments of the present invention, an electronic device is also provided in the embodiments of the present invention, which may include but is not limited to: a processor and a memory; the memory is used to store a computer program; the processor is used to execute the method shown in any embodiment of the present invention by calling the computer program.

[0211] In an alternative embodiment, an electronic device is provided, such as Figure 5 As shown, Figure 5The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0212] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0213] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0214] The memory 4003 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0215] The memory 4003 is used to store the application code (computer program) for executing the solution of the present invention, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the application code stored in the memory 4003 to implement the content shown in the above method embodiment.

[0216] The electronic device may also be a terminal device. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0217] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents of the aforementioned method embodiment.

[0218] According to another aspect of the present invention, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the implementation modes of the above-mentioned various embodiments.

[0219] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0220] It should be understood that the flow charts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the module, the program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0221] The computer-readable storage medium provided by the embodiment of the present invention may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0222] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0223] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the disclosure scope involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) by each other.

Claims

1. A method for evaluating the potential for carbon emission reduction in regional electricity considering green electricity trading contracts, characterized in that: The following steps are involved: Obtain the current electricity carbon emissions of the target area in the current time period; According to the current electricity carbon emissions and a pre-established system dynamics model, a plurality of current carbon emissions impact indicators corresponding to the current electricity carbon emissions are determined, wherein the system dynamics model is established based on different electricity carbon emissions corresponding to different regions in the process of electricity production and consumption and a plurality of carbon emissions impact indicators corresponding to each of the electricity carbon emissions, wherein the plurality of carbon emissions impact indicators include an impact indicator corresponding to green electricity trading; Analyze and predict each of the current carbon emission impact indicators to obtain a predicted value of a target carbon emission impact indicator for each of the current carbon emission impact indicators in the next time period of the current time period; The predicted values ​​of the influencing indicators of each target carbon emission are analyzed and processed to obtain the predicted electricity carbon emission of the target area in the next time period.

2. The method according to claim 1, characterized in that The system dynamics model is established based on the following approach: Acquire historical data within multiple historical time periods, each of the historical time periods including multiple historical carbon emission related data and historical electricity carbon emissions, and for each of the historical time periods, the multiple historical carbon emission related data within the historical time period include carbon emission related data corresponding to different regions during the electricity production and consumption process of the historical time period, and the historical electricity carbon emissions within the historical time period include electricity carbon emissions corresponding to different regions during the electricity production and consumption process of the historical time period; For each of the historical time periods, determining the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions within the historical time period; For each of the historical time periods, according to the correlation between each of the historical carbon emission related data and the historical electricity carbon emissions, determine the target historical carbon emission related data corresponding to the historical time period from the plurality of historical carbon emission related data; The system dynamics model is established according to the target historical carbon emission related data and the historical electricity carbon emissions corresponding to each of the historical time periods.

3. The method according to claim 2, characterized in that The multiple historical carbon emission related data include the total electricity consumption of the whole society, thermal power generation, wind power generation, solar power generation, standard coal consumption for power generation, line loss and residents' daily electricity consumption intensity.

4. The method according to claim 2, characterized in that: The establishing of the system dynamics model according to the target historical carbon emission related data and the historical electricity carbon emission corresponding to each of the historical time periods includes: For each of the historical time periods, extracting the historical carbon emission impact indicators of different regions within the historical time period according to the target historical carbon emission related data; For each of the historical time periods, determine the degree of influence of each historical carbon emissions impact indicator of each of the regions on the historical electricity carbon emissions within the historical time period; For each of the historical time periods, the initial model is trained according to the historical carbon emission impact indicators of each of the regions within the historical time period, the historical electricity carbon emissions, and the degree of influence of each historical carbon emission impact indicator corresponding to each of the regions within the historical time period on the historical electricity carbon emissions, to obtain the predicted electricity carbon emissions for the next historical time period of the historical time period; For each of the historical time periods, determine the loss value corresponding to the historical time period according to the predicted electricity carbon emissions in the next historical time period of the historical time period and the historical electricity carbon emissions in the next historical time period of the historical time period; According to the loss values ​​corresponding to each of the historical time periods, the training of the initial model is completed to obtain the system dynamics model.

5. The method according to claim 3, characterized in that: Multiple historical carbon emission impact indicators for each of the regions include power energy structure, green electricity trading volume, power supply and demand relationship, transmission and distribution losses, industrial production conditions, social electricity intensity, green technology innovation level and green electricity policy.

6. The method according to any one of claims 1 to 5, characterized in that The analyzing and predicting processing of each current carbon emission impact indicator to obtain a predicted value of a target carbon emission impact indicator for each current carbon emission impact indicator in the next time period of the current time period includes: Analyze and predict each of the current carbon emission impact indicators using a grayscale prediction algorithm to obtain a first carbon emission impact indicator prediction value for each of the current carbon emission impact indicators in the next time period of the current time period; Analyze and predict each of the current carbon emission impact indicators using a support vector machine algorithm to obtain a second carbon emission impact indicator prediction value for each of the current carbon emission impact indicators in the next time period of the current time period; The first carbon emission impact index prediction value and the second carbon emission impact index prediction value are fused to obtain the target carbon emission impact index prediction value.

7. The method according to any one of claims 1 to 5, characterized in that The analyzing and processing of the predicted values ​​of the target carbon emission impact indicators to obtain the predicted electricity carbon emission of the target area in the next time period includes: By using a pre-trained regional power system carbon emission reduction potential assessment model, the predicted values ​​of each target carbon emission impact indicator are analyzed and processed to obtain the predicted electricity carbon emissions of the target area in the next time period. The regional power system carbon emission reduction potential assessment model is a model obtained by training a neural network based on historical carbon emission data, and the historical carbon emission data includes historical electricity carbon emissions and historical carbon emission impact indicators.

8. A device for evaluating the potential for carbon emission reduction in regional electricity considering green electricity trading contracts, characterized in that: include: An acquisition module, used to acquire the current electricity carbon emissions of the target area in the current time period; An impact index determination module is used to determine a plurality of current carbon emission impact indicators corresponding to the current electricity carbon emission according to the current electricity carbon emission and a pre-established system dynamics model, wherein the system dynamics model is established based on different electricity carbon emissions corresponding to different regions in the process of electricity production and consumption and a plurality of carbon emission impact indicators corresponding to each of the electricity carbon emissions, wherein the plurality of carbon emission impact indicators include an impact indicator corresponding to green electricity trading; An impact index value prediction module is used to analyze and predict each of the current carbon emission impact indicators to obtain a target carbon emission impact index prediction value of each of the current carbon emission impact indicators in the next time period of the current time period; The power carbon emission prediction module is used to analyze and process the predicted values ​​of the influencing indicators of each target carbon emission to obtain the predicted power carbon emission of the target area in the next time period.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images