Regional carbon emission prediction method and related equipment

Abstract

The invention provides a regional carbon emission prediction method and related equipment. The method comprises the following steps: acquiring index data of a preset index parameter about carbon emission prediction in a target area; performing carbon emission prediction based on a carbon emission prediction model and the index data to obtain an initial carbon emission of the target area; wherein the carbon emission prediction model is constructed based on the preset index parameters; and correcting the initial carbon emission based on a correction model and the correction data to obtain a predicted carbon emission.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, and in particular to a method for predicting regional carbon emissions and related equipment. Background Art

[0002] Traditional carbon peak prediction technology often only focuses on energy and carbon emissions, ignoring the large differences between different regions, resulting in inaccurate and low-efficiency predictions of carbon emissions. Summary of the invention

[0003] The present disclosure proposes a regional carbon emissions prediction method and related equipment to solve the technical problems of inaccurate carbon emissions prediction and low efficiency to a certain extent.

[0004] In a first aspect, the present disclosure provides a method for predicting carbon emissions by region, comprising:

[0005] Obtaining indicator data of preset indicator parameters for carbon emission forecasting in the target area;

[0006] Carrying out carbon emission prediction based on the carbon emission prediction model and the index data to obtain the initial carbon emission of the target area; wherein the carbon emission prediction model is constructed based on the preset index parameters;

[0007] The initial carbon emissions are corrected based on the correction model and the correction data to obtain predicted carbon emissions.

[0008] In some embodiments, the carbon emissions prediction model includes:

[0009] f(x)=C1(x)+C2(x)+C3(x),

[0010] st.min p ≤index p ≤max p ,

[0011] i∈{rate population ,rate GDP ,ratio re ,incre_rate carbon ,incre_rate green ,ratio nof};

[0012] Wherein, f(x) is the objective function of the carbon emission prediction model, C1(x) is the direct carbon emission of energy activities, C2(x) is the carbon emission of industrial processes, and C3(x) is the transferred carbon emission of energy activities;

[0013] Among them, C1(x) = g1(x) + g2(x), g1(x) is the carbon emissions of terminal consumption, and g2(x) is the carbon emissions of processing and conversion input and output;

[0014] is the carbon emission release of the ith sector in terminal consumption, and z is the total sectoral amount of terminal consumption;

[0015] input_output_ene j is the carbon emission of the jth sector in the input-output, and m is the total sectoral input-output;

[0016] C2(x)=∑(p i (x)×factor i ), p i (x) is the output of the lth product, factor i is the product carbon emission factor corresponding to the lth product;

[0017] C3(x)=E trans ×factor ele , E trans is the carbon emissions of regional electricity transfer, factor ele is the corresponding carbon emission factor;

[0018] index p is the pth preset indicator parameter, rate population is the natural population growth rate, rate GDP is the GDP growth rate, ratio re is the proportion of renewable energy generation, increase_rate carbon is the carbon quota growth rate, increase_rate green is the growth rate of green certificate trading volume, ratio nof is the proportion of non-fossil energy consumption; min p is the lower limit of the pth preset indicator parameter, max p is the upper limit of the pth preset indicator parameter.

[0019] In some embodiments, the constraints on the carbon quota price in the carbon emission prediction model include: min ≤P≤P max ; Wherein, P represents the carbon quota price, which is related to the supply and demand of carbon quotas, P min Indicates the price lower limit, P max Indicates the price ceiling.

[0020] In some embodiments, the carbon emission prediction model further includes: ∑D t =∑St +∑B t ; where t represents the time period, ∑D t represents the total demand for carbon quotas in time period t, ∑S t represents the total supply of carbon quotas in time period t, ∑B t represents the net balance of carbon quotas in time period t; the constraints for carbon quota supply and demand balance include: ∑S t -∑D t ≥0; where St represents the carbon quota supply in time period t, and Dt represents the carbon quota demand in time period t.

[0021] In some embodiments, the modified model comprises:

[0022]

[0023] Among them, △ t represents the correction amount in time period t, μ represents the overall mean, M t-1 represents the error correction term, α represents the error correction coefficient, Indicates GDP correction coefficient, ΔY k represents the GDP change of the kth sample in time period t, n is the total number of samples, σ k represents the population correction factor, ΔP k ′ represents the population change of the kth sample in time period t, ξ k Represents the capital investment correction factor, ΔK k represents the change in capital investment of the kth sample in time period t, λ k represents the labor input correction factor, ΔL k represents the change in labor input of the kth sample in time period t, ε t represents white noise in time period t.

[0024] In some embodiments, the method further comprises:

[0025] In response to receiving a selection of a target scenario from preset scenarios, preset indicator parameters and constraint conditions corresponding to the target scenario are determined.

[0026] In some embodiments, the method further comprises:

[0027] Determining a first weight of a candidate indicator parameter based on a hierarchical analysis method, and determining a second weight of the candidate indicator parameter based on an entropy weight method;

[0028] The preset indicator parameter is determined from the candidate indicator parameters based on the first weight and the second weight.

[0029] In a second aspect of the present disclosure, a device for predicting carbon emissions by region is provided, comprising:

[0030] An acquisition module, used to acquire index data of preset index parameters for carbon emission prediction in a target area;

[0031] A prediction module, used to perform carbon emission prediction based on a carbon emission prediction model and the index data to obtain the initial carbon emission of the target area; wherein the carbon emission prediction model is constructed based on the preset index parameters;

[0032] The correction module is used to correct the initial carbon emissions based on the correction model and correction data to obtain the predicted carbon emissions.

[0033] In some embodiments, the carbon emissions prediction model includes:

[0034] f(x)=C1(x)+C2(x)+C3(x),

[0035] st.min p ≤index p ≤max p ,

[0036] i∈{rate population ,rate GDP ,ratio re ,incre_rate carbon ,incre_rate green ,ratio nof};

[0037] Wherein, f(x) is the objective function of the carbon emission prediction model, C1(x) is the direct carbon emission of energy activities, C2(x) is the carbon emission of industrial processes, and C3(x) is the transferred carbon emission of energy activities;

[0038] Among them, C1(x) = g1(x) + g2(x), g1(x) is the carbon emissions of terminal consumption, and g2(x) is the carbon emissions of processing and conversion input and output;

[0039] the_end_ene i is the carbon emission release of the ith sector in terminal consumption, and z is the total sectoral amount of terminal consumption;

[0040] input_output_ene j is the carbon emission of the jth sector in the input-output, and m is the total sectoral input-output;

[0041] C2(x)=∑(pi (x)×factor i ), p i (x) is the output of the lth product, factor i is the product carbon emission factor corresponding to the lth product;

[0042] C3(x)=E trans ×factor ele , E trans is the carbon emissions of regional electricity transfer, factor ele is the corresponding carbon emission factor;

[0043] index p is the pth preset indicator parameter, rate population is the natural population growth rate, rate GDP is the GDP growth rate, ratio re is the proportion of renewable energy generation, increase_rate carbon is the carbon quota growth rate, increase_rate green is the growth rate of green certificate trading volume, ratio nof is the proportion of non-fossil energy consumption; min p is the lower limit of the pth preset indicator parameter, max p is the upper limit of the pth preset indicator parameter.

[0044] In some embodiments, the constraints on the carbon quota price in the carbon emission prediction model include: min ≤P≤P max ; Wherein, P represents the carbon quota price, which is related to the supply and demand of carbon quotas, P min Indicates the price lower limit, P max Indicates the price ceiling.

[0045] In some embodiments, the carbon emission prediction model further includes: ∑D t =∑S t +∑B t ; where t represents the time period, ∑D t represents the total demand for carbon quotas in time period t, ∑S t represents the total supply of carbon quotas in time period t, ∑B t represents the net balance of carbon quotas in time period t;

[0046] The constraints for carbon quota supply and demand balance include: ∑S t -∑D t ≥0; where St represents the carbon quota supply in time period t, and Dt represents the carbon quota demand in time period t.

[0047] In some embodiments, the modified model comprises:

[0048]

[0049] Among them, △ t represents the correction amount in time period t, μ represents the overall mean, M t-1 represents the error correction term, α represents the error correction coefficient, Indicates GDP correction coefficient, ΔY k represents the GDP change of the kth sample in time period t, n is the total number of samples, σ k represents the population correction factor, ΔP k ′ represents the population change of the kth sample in time period t, ξ k Represents the capital investment correction factor, ΔK k represents the change in capital investment of the kth sample in time period t, λ k represents the labor input correction factor, ΔL k represents the change in labor input of the kth sample in time period t, ε t represents white noise in time period t.

[0050] In some embodiments, the apparatus further comprises:

[0051] The scenario setting module is used to determine preset indicator parameters and constraint conditions corresponding to the target scenario in response to receiving a target scenario selected from preset scenarios.

[0052] In some embodiments, the apparatus further comprises:

[0053] A weight module, used to determine a first weight of a candidate indicator parameter based on a hierarchical analysis method, and to determine a second weight of the candidate indicator parameter based on an entropy weight method;

[0054] A parameter module is used to determine the preset indicator parameter from the candidate indicator parameters based on the first weight and the second weight.

[0055] In a third aspect of the present disclosure, an electronic device is provided, comprising one or more processors, a memory; and one or more programs, wherein the one or more programs are stored in the memory and executed by the one or more processors, and the programs include instructions for executing the method described in the first aspect.

[0056] According to a fourth aspect of the present disclosure, a non-volatile computer-readable storage medium containing a computer program is provided. When the computer program is executed by one or more processors, the processors execute the method described in the first aspect.

[0057] In a fifth aspect of the present disclosure, a computer program product is provided, comprising computer program instructions, which, when executed on a computer, enable the computer to execute the method described in the first aspect.

[0058] From the above, it can be seen that the present invention provides a regional carbon emissions prediction method and related equipment, which collects preset indicator parameter data of the target area, uses a pre-built carbon emissions prediction model to make a preliminary prediction to obtain the initial carbon emissions, and then corrects the initial prediction result based on the correction model and correction data, thereby improving the prediction accuracy of carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the present disclosure or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0060] Figure 1 Schematic diagram of a regional carbon emissions prediction framework according to an embodiment of the present disclosure.

[0061] Figure 2 The figure is a schematic diagram of the hardware structure of an exemplary electronic device according to an embodiment of the present disclosure.

[0062] Figure 3 The figure is a flow chart of a method for predicting carbon emissions by region according to an embodiment of the present disclosure.

[0063] Figure 4 This is a schematic diagram of the data flow of carbon peak prediction in an embodiment of the present disclosure.

[0064] Figure 5 It is a schematic diagram of the principle of the correction model of the embodiment of the present disclosure.

[0065] Figure 6 Schematic diagram of the carbon emission prediction model and correction model of the embodiment of the present disclosure.

[0066] Figure 7 A schematic diagram of a preset scenario of an embodiment of the present disclosure.

[0067] Figure 8 Schematic diagram of parameter settings in different scenarios of an embodiment of the present disclosure.

[0068] Fig. 9 It is a schematic diagram of a device for predicting carbon emissions by region according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0069] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0070] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0071] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0072] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0073] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0074] Figure 1 A schematic diagram of a regional carbon emissions prediction framework according to an embodiment of the present disclosure is shown. Figure 1The regional carbon emissions prediction architecture 100 may include a server 110, a terminal 120, and a network 130 providing a communication link. The server 110 and the terminal 120 may be connected via a wired or wireless network 130. The server 110 may be an independent physical server, or a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, security services, and CDN.

[0075] The terminal 120 may be implemented in hardware or software. For example, when the terminal 120 is implemented in hardware, it may be various electronic devices having a display screen and supporting page display, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers, and desktop computers, etc. When the terminal 120 device is implemented in software, it may be installed in the electronic devices listed above; it may be implemented as multiple software or software modules (such as software or software modules used to provide distributed services), or it may be implemented as a single software or software module, which is not specifically limited here.

[0076] It should be noted that the regional carbon emission prediction method provided in the embodiment of the present application can be executed by the terminal 120 or by the server 110. It should be understood that Figure 1 The number of terminals, networks and servers in the embodiment is only for illustration and is not intended to limit the number of terminals, networks and servers. Any number of terminals, networks and servers may be provided as required.

[0077] Figure 2 FIG. 2 shows a schematic diagram of the hardware structure of an exemplary electronic device 200 provided in an embodiment of the present disclosure. Figure 2 As shown, the electronic device 200 may include: a processor 202, a memory 204, a network module 206, a peripheral interface 208 and a bus 210. The processor 202, the memory 204, the network module 206 and the peripheral interface 208 are connected to each other in communication within the electronic device 200 through the bus 210.

[0078] Processor 202 may be a central processing unit (CPU), a neural network processor (NPU), a microcontroller (MCU), a programmable logic device, a digital signal processor (DSP), an application specific integrated circuit (ASIC), or one or more integrated circuits. Processor 202 may be used to perform functions related to the technology described in this disclosure. In some embodiments, processor 202 may also include multiple processors integrated into a single logical component. For example, Figure 2 As shown, processor 202 may include a plurality of processors 202a, 202b, and 202c.

[0079] The memory 204 may be configured to store data (eg, instructions, computer code, etc.). Figure 2 As shown, the data stored in the memory 204 may include program instructions (for example, program instructions for implementing the method for predicting regional carbon emissions according to an embodiment of the present disclosure) and data to be processed (for example, the memory may store configuration files of other modules, etc.). The processor 202 may also access the program instructions and data stored in the memory 204, and execute the program instructions to operate on the data to be processed. The memory 204 may include a volatile storage device or a non-volatile storage device. In some embodiments, the memory 204 may include a random access memory (RAM), a read-only memory (ROM), an optical disk, a magnetic disk, a hard disk, a solid-state drive (SSD), a flash memory, a memory stick, etc.

[0080] The network module 206 can be configured to provide communication with other external devices to the electronic device 200 via a network. The network can be any wired or wireless network capable of transmitting and receiving data. For example, the network can be a wired network, a local wireless network (e.g., Bluetooth, WiFi, near field communication (NFC) etc.), a cellular network, the Internet or a combination thereof. It is understood that the type of network is not limited to the above specific examples. In some embodiments, the network module 206 can include any number of network interface controllers (NICs), radio frequency modules, transceivers, modems, routers, gateways, adapters, cellular network chips, etc., in any combination.

[0081] The peripheral interface 208 can be configured to connect the electronic device 200 to one or more peripheral devices to achieve information input and output. For example, the peripheral devices can include input devices such as a keyboard, a mouse, a touch pad, a touch screen, a microphone, and various sensors, and output devices such as a display, a speaker, a vibrator, and an indicator light.

[0082] The bus 210 can be configured to transmit information between various components of the electronic device 200 (e.g., the processor 202, the memory 204, the network module 206, and the peripheral interface 208), such as an internal bus (e.g., a processor-memory bus), an external bus (USB port, PCI-E bus), etc.

[0083] It should be noted that, although the architecture of the electronic device 200 only shows the processor 202, the memory 204, the network module 206, the peripheral interface 208 and the bus 210, in the specific implementation process, the architecture of the electronic device 200 may also include other components necessary for normal execution. In addition, it can be understood by those skilled in the art that the architecture of the electronic device 200 may also only include the components necessary for implementing the embodiments of the present disclosure, and does not necessarily include all the components shown in the figure.

[0084] Traditional carbon peak prediction technology often only focuses on energy and carbon emissions, ignoring the impact of energy efficiency, energy structure, green certificate price, renewable energy ratio, etc. The "electricity-certificate-carbon" policies of different regions vary greatly, and the degree of participation and process flow of carbon markets in different regions also vary greatly, resulting in difficulties and challenges in the construction of regional carbon emission peak prediction models. Among the existing carbon emission prediction mechanisms, top-down models: typical representatives of CGE, STIERPAT, etc., have high requirements for data integrity, and the flexibility and scalability of the model are poor; bottom-up models: typical representatives of LEAP, MARKAL, etc., the model lacks consideration of economic factors and has limited application scenarios; hybrid models: typical representatives of MARKAL-MACRO, the implementation of the model is difficult and the subsequent optimization space is small. Machine learning models: including black box models represented by long short-term memory neural networks (LSTM) and interpretable models represented by ARDL. These two types of models have high requirements for the magnitude and integrity of data, and the input variables of the interpretable models are few, and external influencing factors cannot be constructed. Therefore, how to improve the accuracy and stability of carbon emission predictions has become a technical problem that needs to be solved urgently.

[0085] In view of this, the embodiments of the present disclosure provide a regional carbon emissions prediction method and related equipment, which collects preset indicator parameter data of the target area, uses a pre-built carbon emissions prediction model to make a preliminary prediction to obtain the initial carbon emissions, and then corrects the initial prediction result based on the correction model and correction data, thereby improving the prediction accuracy of carbon emissions.

[0086] See also Figure 3 , Figure 3 The schematic flow chart of the method for predicting carbon emissions by region according to the embodiment of the present disclosure is shown. The method for predicting carbon emissions by region according to the embodiment of the present disclosure can be deployed on a terminal or a server. Figure 3 In the method 300 for predicting carbon emissions by region, the method 300 may further include the following steps.

[0087] In step S310, index data of preset index parameters for carbon emission prediction in the target area are obtained.

[0088] Among them, the target area may refer to a specific geographical range or area where carbon emissions forecasting is required. This area may be a country, province, city or a specific geographical block. The target area may be selected based on the needs of research or policy making. For example, it is necessary to forecast the carbon emissions in a certain area in order to formulate emission reduction policies. Carbon emissions forecasting may refer to the use of mathematical models or statistical methods to estimate the carbon emissions of the target area in the future. The preset indicator parameters may refer to variables or parameters pre-set in the carbon emissions forecasting model to reflect carbon emission-related factors. The indicator data may refer to specific values ​​or data corresponding to the preset indicator parameters for carbon emissions forecasting. In order to forecast carbon emissions, the specific values ​​or data of the preset indicator parameters related to carbon emissions in the target area may be collected to establish or run a carbon emissions forecasting model to obtain carbon emissions forecast results for a period of time in the future.

[0089] In some embodiments, method 300 further includes:

[0090] Determining a first weight of a candidate indicator parameter based on a hierarchical analysis method, and determining a second weight of the candidate indicator parameter based on an entropy weight method;

[0091] The preset indicator parameter is determined from the candidate indicator parameters based on the first weight and the second weight.

[0092] Among them, candidate indicator parameters refer to a series of indicators that are initially screened out when selecting indicators and may be used to describe or evaluate a certain problem or phenomenon. The first weight refers to the weight of the candidate indicator parameters determined by the hierarchical analysis method, which reflects the subjective judgment of decision makers or experts on the importance of the indicators. The second weight refers to the weight of the candidate indicator parameters determined by the entropy weight method, which is based on the characteristics of the data itself and reflects the objective distribution of the indicator information.

[0093] The analytic hierarchy process is a multi-attribute decision analysis method that decomposes complex problems into multiple components and groups these factors according to the dominant relationship to form a hierarchical structure. The relative importance of each factor in the hierarchy is determined by pairwise comparison, and then the weight ranking of all factors is obtained. For example, the problem is decomposed into different levels, such as the target level, the criterion level, and the indicator level. Then, the indicators are compared pairwise within the criterion level to form a judgment matrix. By calculating the eigenvector or average value of the judgment matrix, the relative weight of each indicator under the criterion is obtained. Finally, the total weight of the indicator (i.e., the first weight) is calculated based on the weight of each criterion and the weight of the indicator under the criterion.

[0094] The entropy weight method is an objective weighting method that determines the weight of indicators based on information entropy. Information entropy reflects the degree of disorder of information. The smaller the information entropy, the lower the degree of disorder of information, the greater the utility value of information, and the greater the weight of the indicator. The original data can be standardized first to eliminate the influence of dimension and order of magnitude. Then, the information entropy of each indicator is calculated. The larger the information entropy, the smaller the amount of information contained in the indicator, and its weight should be smaller. Finally, the weight of each indicator (i.e., the second weight) is calculated based on the information entropy, and the size of the weight is inversely proportional to the information entropy.

[0095] The analytic hierarchy process focuses more on subjective judgment and experience, while the entropy weight law relies more on the characteristics of the data itself. Based on these two weights, the preset indicator parameters are screened from the candidate indicator parameters through certain methods (such as weighted average method). Combining subjective judgment and objective data can more comprehensively reflect the importance and information content of the indicator, thereby improving the accuracy and reliability of evaluation or prediction.

[0096] Specifically, we can determine five major categories of primary system indicators, including energy, economy, technology, population, and "electricity-certificate-carbon", and 38 secondary indicators, clarify the meaning of indicators, data sources and time frequency, and form an indicator set of influencing factors. Based on the indicator set of influencing factors, the AHP-improved entropy weight method is used for quantification. The AHP-improved entropy weight method is suitable for complex decision-making problems with multiple indicators and multiple levels. It can better reflect the complexity and uncertainty between indicators in the fields of green electricity, green certificates, and carbon markets by constructing a multi-level indicator quantification system.

[0097] Firstly, the subjective weights of the influencing factor index set are analyzed by the AHP method, and then the objective weights are calculated by the improved entropy weight method. Finally, the regional carbon peak influencing factor index set and its weights are obtained under the background of "electricity-certificate-carbon" market synergy.

[0098] The AHP-improved entropy weight method is used to quantify the influencing factor set. The subjective weight is determined by the analytic hierarchy process (AHP), and the objective weight is determined by the improved entropy weight method. The combination of subjective and objective weights can integrate the subjectivity of expert experience and the objectivity of real data. Finally, the combined weight of the indicators is obtained, which is used to quantify the influencing factors of the sub-region under the coordination of the "electricity-certificate-carbon" market. The steps to determine the weight of the indicator based on the AHP-entropy weight method are as follows:

[0099] (1) Using AHP to determine indicator weights

[0100] First, construct a judgment matrix: use the 1-9 scale method to quantitatively describe the indicators at the same level. The AHP evaluation scale is used as a pairwise comparison between the indicator factors at each level. For the indicators of the same level belonging to the same superior, the 1-9 scale pairwise comparison method is used to establish a judgment matrix. The basic division includes five items, namely, equal strength, slightly strong, quite strong, extremely strong, and absolutely strong. Four other scales are set between the five basic scales and are assigned measurement values ​​of 2, 4, 6, and 8, totaling nine scales. The meaning of each scale is shown in Table 1 below.

[0101] Evaluation scale definition illustrate 1 Equally important The contributions of both factors are equally important 3 Slightly important Experience and judgment slightly favor one factor 5 Quite important Experience and judgment strongly favor one element 7 Extremely important Actually showing a very strong preference for one element 9 Absolutely important There is enough evidence to absolutely prefer a certain factor 2,4,6,8 The middle value of adjacent scales Between two judgments

[0102] Table 1

[0103] Then perform consistency test: calculate the maximum characteristic root λmax of the judgment matrix, calculate the consistency index CI=(λmax-n) / (n-1), where n is the order of the judgment matrix. Calculate the consistency ratio CR=CI / RI. When CR<0.1, the judgment matrix is ​​considered to be subjectively consistent, otherwise the judgment matrix should be appropriately modified.

[0104] Then calculate the weight: use the eigenvalue method to solve the eigenvector corresponding to the maximum eigenroot of the judgment matrix, and after normalization, obtain the weight vector, i.e., the first weight.

[0105] (2) Steps to calculate weights using the entropy weight method

[0106] First, the data is standardized, and the range standardization method (maximum and minimum value normalization) is used to convert the data into dimensionless and comparable data. The expression is as follows:

[0107]

[0108] Among them, Z ij represents the standardized matrix, x ij Represents all possible values ​​of the indicator, minX represents the minimum value of all possible values ​​of the indicator, and maxX represents the maximum value of all possible values ​​of the indicator.

[0109] Secondly, the information entropy value of each indicator is calculated, which is expressed as follows:

[0110]

[0111] Among them, y ij It represents the proportion of the standardized value of the i-th evaluation object on the j-th indicator, and m is the number of indicators.

[0112] Determine the indicator weights again and calculate the normalized entropy value. The expression is as follows:

[0113]

[0114] Among them, e j is the entropy value of the jth factor, and m represents the number of indicators.

[0115] Then the comprehensive evaluation model is determined, and the weighted average method is used to calculate the decision factor weights obtained by AHP and the weights of each indicator obtained by the entropy weight method to obtain the weights of each indicator. The expression is as follows:

[0116]

[0117] Among them, w j Represents the normalized entropy value of the jth index.

[0118] The set of influencing factors is quantified through the AHP-improved entropy weight method. In the green electricity market, key indicators such as the proportion of renewable energy power generation and green electricity trading volume are screened out; in the green certificate market, key indicators such as green certificate price and green certificate quantity are screened out; in the carbon market, key indicators such as carbon quota benchmark price and carbon quota auction ratio are screened out to construct a "electricity-certificate-carbon" market collaborative indicator system for subsequent model construction.

[0119] In the green electricity market, the proportion of renewable energy generation is an important indicator to measure the degree of clean energy utilization. This indicator can directly affect the energy structure in the model. The proportion of renewable energy generation drives the change in the proportion of new energy generation, changes the energy consumption structure, and thus affects the carbon emission calculation. This factor helps policymakers evaluate the promotion effect of renewable energy and adjust relevant policies accordingly.

[0120] The trading volume of green electricity reflects the supply and demand relationship in the green electricity trading market. Combined with the price of green electricity, it reflects the market demand for green electricity, the degree of recognition and the market value of green electricity. The increase in the trading volume of green electricity can reflect the increase in the market demand for green electricity, and this demand growth provides a strong market driving force for the research and development of clean energy technology, prompting enterprises, scientific research institutions and universities to increase their investment in research and development in the field of clean energy technology, thereby promoting the improvement of the level of scientific and technological innovation in clean energy technology and promoting the commercial application of clean energy technology, so as to further increase the proportion of clean energy in power generation, change the energy consumption structure, and ultimately affect the carbon emission measurement.

[0121] In the green certificate market, green certificate price fluctuations will affect the clean energy production decisions of power producers. When the price of green certificates rises, it means that more power producers will turn to clean energy production, increase profits and reduce carbon emissions. The model uses the "power certificate carbon" market synergy indicator system to simulate the impact of energy market changes on carbon emissions under different green power green certificate trading volume change scenarios, providing decision support for policymakers.

[0122] Based on the carbon quota carry-over and trading situation, changes in the carbon quota auction ratio will affect the market supply and demand balance and price trends, and then reflect the market changes and emission reduction effects under different carbon quota auction ratio scenarios. The model can simulate the market response under different carbon quota benchmark prices and auction ratio scenarios, and provide policymakers with suggestions on carbon market pricing and regulation mechanisms.

[0123] In summary, factors such as the proportion of renewable energy generation, green electricity trading volume, green certificate price, green certificate quantity, carbon quota benchmark price, and carbon quota auction ratio are interrelated and influence each other, and work together to promote energy transformation and low-carbon development. The IPAC-VECM model provides scientific and comprehensive decision-making support for policymakers by simulating and analyzing the changes and impacts of the "electricity-certificate-carbon" market synergy system under different scenarios.

[0124] In step S320, carbon emissions are predicted based on the carbon emissions prediction model and the indicator data to obtain the initial carbon emissions of the target area; wherein the carbon emissions prediction model is constructed based on the preset indicator parameters.

[0125] Specifically, the carbon emission prediction model can be based on the IPAC model, and the data flow of carbon peak prediction is as follows: Figure 4 As shown, Figure 4 A schematic diagram of the data flow for carbon peak prediction according to an embodiment of the present disclosure is shown.

[0126] Figure 4 In the carbon emission prediction model, relevant indicators including carbon emission, energy consumption, energy effect, energy structure, green certificate price, and renewable energy power generation ratio are taken into account. The carbon peak prediction of each region is realized by using the optimization method of the minimum objective function.

[0127] First, establish an objective function and minimize it as the training goal of the model. The objective function focuses on energy, carbon emissions, energy efficiency, energy structure, green certificate price, renewable energy ratio, etc., and the constraints focus on carbon quota price, carbon quota supply and demand, etc.

[0128] The objective function has the form:

[0129] f(x)=C1(x)+C2(x)+C3(x)

[0130] Among them, C1(x) is the direct carbon emissions from energy activities, C2(x) is the carbon emissions from industrial processes, and C3(x) is the transferred carbon emissions from energy activities (indirect electricity).

[0131] (1) Direct carbon emissions from energy activities:

[0132] C1(x)=g1(x)+g2(x);

[0133] g1(x) is carbon emissions from terminal consumption (excluding use as raw materials), and g2(x) is carbon emissions from processing and conversion inputs (-) and outputs (+) (including carbon emissions from thermal power generation, carbon emissions from heating, carbon emissions from refining and coal-to-liquids, carbon emissions from gas production, and carbon emissions from energy recovery).

[0134] the_end_ene i is the carbon emission of the ith sector in the final consumption, and z is the total amount of the final consumption sector. i =f1(α1,α2,α3,α4,α5,α6), α1 is GDP, α2 is electricity price, α3 is the proportion of renewable energy power generation, α4 ​​is electricity substitution rate, α5 is tertiary industry GDP, and α6 is the tertiary industry employment population.

[0135] input_output_ene j is the carbon emission of the jth sector in the input-output, and m is the total amount of the input-output sector. j =f2(β1,β2,β3,β4,β5,β6), β1 is GDP, β2 is electricity price, β3 is the proportion of renewable energy power generation, β4 is electricity substitution rate, β5 is tertiary industry GDP, and β6 is the tertiary industry employment population.

[0136] (2) Carbon emissions from industrial processes:

[0137] C2(x)=∑(p i (x)×factor i ), p i (x) is the output of the lth product, factor i is the product carbon emission factor corresponding to the lth product.

[0138] p i(x) = g(x1,x2,x3,x4,x5,x6), x1 is the gross domestic product, x2 is the electricity price, x3 is the number of invention patents authorized, x4 is the market size, x5 is the proportion of the added value of the tertiary industry in the gross domestic product, and x6 is the employed population.

[0139] Product output is affected by macro factors such as GDP (macroeconomy), electricity prices (costs), the number of invention patents granted (technology), population (market size), the proportion of the tertiary industry (economic structure), employed population (labor costs), and the corresponding growth rate (expectations).

[0140] (3) Transferred carbon emissions (i.e. indirect carbon emissions from net electricity transfer):

[0141] C3(x)=E trans ×factor ele , E trans For regional power transfer, factor ele is the corresponding carbon emission factor.

[0142] Constraints can include: st.min p ≤index p ≤max p ,

[0143] p∈{rate population ,rate GDP ,ratio re ,incre_rate carbon ,incre_rate green ,ratio nof};

[0144] Among them, index i is the pth preset indicator parameter, rate population is the natural population growth rate, rate GDP is the GDP growth rate, ratio re is the proportion of renewable energy generation, increase_rate carbon is the carbon quota growth rate, increase_rate green is the growth rate of green certificate trading volume, ratio nof is the proportion of non-fossil energy consumption; min p is the lower limit of the pth preset indicator parameter, max p is the upper limit of the pth preset indicator parameter.

[0145] 2. Carbon quota price constraints

[0146] The price of carbon quotas is affected by many factors, including but not limited to the supply and demand relationship of the carbon market, policy changes, economic activity levels, etc. Therefore, some price constraints are set to ensure that market prices will not fluctuate too much and limit the fluctuation range of carbon quota prices, thereby affecting the stability and efficiency of the market.

[0147] The constraints of carbon quota prices should meet the following requirements:

[0148] P min ≤P≤P max

[0149] Where P represents the carbon quota price at any time, which is related to the supply and demand of carbon quotas. min Indicates the price lower limit, P max P represents the price ceiling. min It is used to ensure that carbon quotas have a certain value and prevent prices from being too low, which leads to emission reduction and lack of economic incentives. max It is used to avoid excessively high carbon quota prices, which would put excessive pressure on the economic burden of enterprises and may cause negative economic effects.

[0150] 3. Carbon quota supply and demand balance constraints

[0151] The balance of supply and demand of carbon quotas is an important concept in the carbon trading market. It refers to the relationship between the total amount of carbon quotas that all market participants need to purchase and the total amount of carbon quotas that they are willing to sell within a specific period of time, reflecting that the supply of upper-level carbon quotas must meet the demand for lower-level carbon quotas. In order to maintain the healthy operation of the market, it is usually hoped to achieve a state of supply and demand balance to ensure that the market can effectively guide emission reduction behaviors.

[0152] A basic condition for carbon quota supply and demand balance is that total demand should equal total supply plus any net balance adjustment, that is:

[0153] ∑D t =∑S t +∑B t

[0154] Where t represents the time period, ∑D t Represents the total demand for carbon quotas in a specific period of time, ∑S t represents the total supply of carbon quotas in a specific period of time, ∑B t Indicates the net balance of carbon allowances over a specific period of time.

[0155] If B = 0, that is, there is no additional quota adjustment, the supply and demand balance condition is simplified to:

[0156] ∑D t =∑S t

[0157] The supply and demand of carbon quotas satisfy the constraint that the overall carbon quota supply must be greater than or equal to the overall carbon quota demand.

[0158] The form of carbon quota supply and demand balance constraint is:

[0159] ∑S t -∑D t ≥0

[0160] Where S represents the carbon quota supply, D represents the carbon quota demand, and t represents the time period.

[0161] In step S330, the initial carbon emissions are corrected based on the correction model and the correction data to obtain predicted carbon emissions.

[0162] Among them, the correction model can be a VECM model, which is an error correction and sensitivity analysis model. In order to reduce the errors in various parameters and variables in the model, other influencing factors such as GDP, population, capital input, and labor input can be used as correction variables to establish a vector error correction model (VECM) to analyze the causal relationship between variables to correct errors. The data corresponding to the correction variable is the correction data. Figure 5 As shown, Figure 5 A schematic diagram of the principle of the correction model according to an embodiment of the present disclosure is shown.

[0163] Specifically, the vector error correction model (VECM) form may include:

[0164]

[0165] Among them, △ t represents the correction amount in time period t, μ represents the overall mean, M t-1 represents the error correction term, α represents the error correction coefficient, Indicates GDP correction coefficient, ΔY k represents the GDP change of the kth sample in time period t, n is the total number of samples, σ k represents the population correction factor, ΔP k ′ represents the population change of the kth sample in time period t, ξ k Represents the capital investment correction factor, ΔK k represents the change in capital investment of the kth sample in time period t, λ k represents the labor input correction factor, ΔL k represents the change in labor input of the kth sample in time period t, ε t represents white noise in time period t.

[0166] See also Figure 6 , Figure 6 A schematic diagram of a carbon emission prediction model and a correction model according to an embodiment of the present disclosure is shown. Figure 6 In the paper, the carbon emission prediction model and correction model combines the IPAC model and the VECM model. It is a time series analysis model that takes into account the supply and demand of the "electricity-certificate-carbon" market, macroeconomics, policy changes, the proportion of renewable energy and population data. Among them, the IPAC model is based on minimizing the carbon emission cost, setting the target optimization function, and considering the mutual influence and relationship between multiple time series variables. It can capture multiple patterns and trends in the time series, so that the model can more comprehensively reflect the complexity of the "electricity-certificate-carbon" regional carbon emission system; the error correction mechanism in the VECM model helps to eliminate errors and noise in time series data, conduct sensitivity analysis and error correction on the model's prediction results, and improve the accuracy and stability of the prediction.

[0167] Based on the results of the analysis of the influencing factors of the regional carbon emission system of "electricity-certificate-carbon", data on the supply and demand relationship of the carbon market, policy changes, economic activity levels, the proportion of renewable energy, population and GDP were obtained. The IPAC-VECM model was used to comprehensively consider the mutual influence and relationship between multiple time series variables to perform time series forecasts, and the VECM model was used for error correction to improve the accuracy and stability of the forecast.

[0168] In some embodiments, method 300 further includes:

[0169] In response to receiving a selection of a target scenario from preset scenarios, preset indicator parameters and constraint conditions corresponding to the target scenario are determined.

[0170] Specifically, three scenarios, namely, the baseline scenario, the low-carbon policy-driven scenario, and the policy-technology dual-driven scenario, can be set as regional carbon peak prediction scenarios. At the same time, the parameter values ​​of the indicators under different scenarios can be set, and different indicator ranges can be set for the parameters. Figure 7 As shown, Figure 7 A schematic diagram of a preset scenario according to an embodiment of the present disclosure is shown. Figure 7 In the scenario parameters, six indicators, including natural population growth rate, GDP growth rate, renewable energy power generation ratio, green certificate trading growth rate, carbon quota growth rate, and non-fossil energy consumption ratio, are selected as parameters for scenario division. Based on the values ​​of the indicators, the scenarios are divided into baseline scenarios, low-carbon policy-oriented scenarios, and policy-technology dual-driven scenarios. The parameter settings under different scenarios are as follows: Figure 8 As shown, Figure 8 A schematic diagram showing parameter settings in different scenarios according to an embodiment of the present disclosure.

[0171] Among them, the baseline scenario refers to a scenario based on the existing policy system, without changing the original situation or adding new constraints; the low-carbon policy-oriented scenario refers to a scenario based on existing plans and foreseeable energy-saving and carbon-reduction policy measures; the policy-technology dual-driven scenario refers to a scenario in which energy-saving and carbon-reduction technologies are added on the basis of the policy scenario. This scenario has a higher carbon reduction force, can suppress the growth of energy consumption and begin to decline significantly in the preset time period, and lay a better foundation for achieving carbon peak. The optimized regional carbon emission peak prediction model is used to carry out regional carbon emission peak prediction under different scenarios, and the prediction results are verified. Considering the economic characteristics of each region and how to balance carbon emission reduction and economic growth in the process of carbon peak, the carbon peak prediction values ​​of each sub-region under different scenarios are given.

[0172] It can be seen that the present disclosure adopts a bottom-up model analysis method, takes the minimization of overall carbon emissions as the optimization goal, constructs an objective function, and uses a linear programming-based minimization optimization method to train and solve. Among them, the data indicators involved include energy activity indicators, economic development indicators, population growth indicators, green certificate carbon market indicators, and scientific and technological innovation indicators. On the basis of the improved IPAC model, constraints such as regional carbon quota prices and carbon quota supply and demand are introduced to achieve regional carbon peak forecast analysis. On the basis of the IPAC carbon peak forecast results, an error correction and sensitivity analysis model based on the vector error correction model (VECM) is introduced to reduce the errors in each parameter and variable in the model. At the same time, GDP, population and other influencing factors are used as correction variables to establish VECM, and the causal relationship between variables is analyzed to correct errors. Different carbon emission scenarios are set according to influencing factors such as historical carbon emission trends and industry policies in each region, so as to support carbon peak forecasts under different scenarios in different regions.

[0173] In view of the fact that the existing carbon peak prediction model only considers traditional factors such as economy, population, energy, technology, etc., and does not consider the synergy of the "electricity-certificate-carbon" market, the present invention proposes a carbon emission peak prediction method for the "electricity-certificate-carbon" market synergy background. By introducing the "electricity-certificate-carbon" related data and the influencing factor set screened by the entropy weight method, as well as the quantitative data of "electricity-certificate-carbon" in different scenarios, the IPAC and VECM models are combined, and the mutual influence and relationship between multiple time series variables are considered at the same time. It can capture multiple patterns and trends in the time series, so that the model can more comprehensively reflect the complexity of the "electricity-certificate-carbon" regional carbon emission system. At the same time, since the error correction mechanism in the VECM model helps to eliminate errors and noise in the time series data, the VECM module is added on the basis of the constructed IPAC model to improve the accuracy and stability of the model prediction.

[0174] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0175] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0176] Based on the same technical concept, corresponding to any of the above-mentioned embodiments and methods, the present disclosure also provides a regional carbon emissions prediction device, see Fig. 9 , the regional carbon emissions prediction device comprises:

[0177] An acquisition module, used to acquire index data of preset index parameters for carbon emission prediction in a target area;

[0178] A prediction module, used to perform carbon emission prediction based on a carbon emission prediction model and the index data to obtain the initial carbon emission of the target area; wherein the carbon emission prediction model is constructed based on the preset index parameters;

[0179] The correction module is used to correct the initial carbon emissions based on the correction model and correction data to obtain the predicted carbon emissions.

[0180] In some embodiments, the carbon emissions prediction model includes:

[0181] f(x)=C1(x)+C2(x)+C3(x),

[0182] st.min p ≤index p ≤max p ,

[0183] i∈{rate population ,rate GDP ,ratio re ,incre_rate carbon ,incre_rate green ,rationof};

[0184] Wherein, f(x) is the objective function of the carbon emission prediction model, C1(x) is the direct carbon emission of energy activities, C2(x) is the carbon emission of industrial processes, and C3(x) is the transferred carbon emission of energy activities;

[0185] Among them, C1(x) = g1(x) + g2(x), g1(x) is the carbon emissions of terminal consumption, and g2(x) is the carbon emissions of processing and conversion input and output;

[0186] the_end_ene i is the carbon emission release of the ith sector in terminal consumption, and z is the total sectoral amount of terminal consumption;

[0187] input_output_ene j is the carbon emission of the jth sector in the input-output, and m is the total sectoral input-output;

[0188] C2(x)=∑(p i (x)×factor i ), p i (x) is the output of the lth product, factor i is the product carbon emission factor corresponding to the lth product;

[0189] C3(x)=E trans ×factor ele , E trans is the carbon emissions of regional electricity transfer, factor ele is the corresponding carbon emission factor;

[0190] index p is the pth preset indicator parameter, rate population is the natural population growth rate, rate GDP is the GDP growth rate, ratio re is the proportion of renewable energy generation, increase_rate carbon is the carbon quota growth rate, increase_rate green is the growth rate of green certificate trading volume, ratio nof is the proportion of non-fossil energy consumption; min p is the lower limit of the pth preset indicator parameter, max p is the upper limit of the pth preset indicator parameter.

[0191] In some embodiments, the constraints on the carbon quota price in the carbon emission prediction model include:min ≤P≤P max ; Wherein, P represents the carbon quota price, which is related to the supply and demand of carbon quotas, P min Indicates the price lower limit, P max Indicates the price ceiling.

[0192] In some embodiments, the carbon emission prediction model further includes: ∑D t =∑S t +∑B t ; where t represents the time period, ∑D t represents the total demand for carbon quotas in time period t, ∑S t represents the total supply of carbon quotas in time period t, ∑B t represents the net balance of carbon quotas in time period t;

[0193] The constraints for carbon quota supply and demand balance include: ∑S t -∑D t ≥0; where St represents the carbon quota supply in time period t, and Dt represents the carbon quota demand in time period t.

[0194] In some embodiments, the modified model comprises:

[0195]

[0196] Among them, △ t represents the correction amount in time period t, μ represents the overall mean, M t-1 represents the error correction term, α represents the error correction coefficient, Indicates GDP correction coefficient, ΔY k represents the GDP change of the kth sample in time period t, n is the total number of samples, σ k represents the population correction factor, ΔP k ′ represents the population change of the kth sample in time period t, ξ k Represents the capital investment correction factor, ΔK k represents the change in capital investment of the kth sample in time period t, λ k represents the labor input correction factor, ΔL k represents the change in labor input of the kth sample in time period t, ε t represents white noise in time period t.

[0197] In some embodiments, the apparatus further comprises:

[0198] The scenario setting module is used to determine preset indicator parameters and constraint conditions corresponding to the target scenario in response to receiving a target scenario selected from preset scenarios.

[0199] In some embodiments, the apparatus further comprises:

[0200] A weight module, used to determine a first weight of a candidate indicator parameter based on a hierarchical analysis method, and to determine a second weight of the candidate indicator parameter based on an entropy weight method;

[0201] A parameter module is used to determine the preset indicator parameter from the candidate indicator parameters based on the first weight and the second weight.

[0202] For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the present disclosure, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0203] The device of the above embodiment is used to implement the corresponding regional carbon emission prediction method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0204] Based on the same technical concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the regional carbon emissions prediction method as described in any of the above embodiments.

[0205] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0206] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the regional carbon emissions prediction method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0207] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples. Based on the concept of the present disclosure, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of the embodiments of the present disclosure as described above, which are not provided in detail for the sake of simplicity.

[0208] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present disclosure difficult to understand, the known power / ground connections to the integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present disclosure difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure will be implemented (that is, these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present disclosure, it is apparent to those skilled in the art that the embodiments of the present disclosure can be implemented without these specific details or with changes in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0209] Although the present disclosure has been described in conjunction with specific embodiments of the present disclosure, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0210] The embodiments of the present disclosure are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method for predicting carbon emissions by region, comprising: Obtaining indicator data of preset indicator parameters for carbon emission forecasting in the target area; Carrying out carbon emission prediction based on the carbon emission prediction model and the index data to obtain the initial carbon emission of the target area; wherein the carbon emission prediction model is constructed based on the preset index parameters; The initial carbon emissions are corrected based on the correction model and the correction data to obtain predicted carbon emissions.

2. The method according to claim 1, wherein: The carbon emission prediction model includes: f(x)=C1(x)+C2(x)+C3(x), st.min p ≤index p ≤max p , p∈(rate population ,rate GDP ,ratio re ,incre_rate carbon ,incre_rate green ,ratio noi }; Wherein, f(x) is the objective function of the carbon emission prediction model, C1(x) is the direct carbon emission of energy activities, C2(x) is the carbon emission of industrial processes, and C3(x) is the transferred carbon emission of energy activities; Among them, C1(x)=g1(x)+g2(x), g1(x) is the carbon emissions of terminal consumption, and g2(x) is the carbon emissions of processing and conversion input and output; the_end_ene i is the carbon emission release of the ith sector in terminal consumption, and z is the total sectoral amount of terminal consumption; input_output_ene j is the carbon emission of the jth sector in the input-output, and m is the total sectoral input-output; C2(x)=∑(p i (x)×factor i ), pi(x) is the output of the th product, factor i is the product carbon emission factor corresponding to the lth product; C3(x)=E trans ×factor ele , E trans is the carbon emissions of regional electricity transfer, factor ele is the corresponding carbon emission factor; index p is the pth preset indicator parameter, rate population is the natural population growth rate, rate GDP is the GDP growth rate, ratio re is the proportion of renewable energy generation, increase_rate carbon is the carbon quota growth rate, increase_rate green is the growth rate of green certificate trading volume, ratio nof is the proportion of non-fossil energy consumption; min p is the lower limit of the pth preset indicator parameter, max p is the upper limit of the pth preset indicator parameter.

3. The method according to claim 2, wherein: The constraints of the carbon quota price in the carbon emission prediction model include: min ≤P≤P max ; Wherein, P represents the carbon quota price, which is related to the supply and demand of carbon quotas. min Indicates the price lower limit, P max Indicates the price ceiling.

4. The method according to claim 3, wherein: The carbon emission prediction model also includes: ∑D t =∑S t +∑B t ; Where t represents the time period, ∑D t represents the total demand for carbon quotas in time period t, ∑S t represents the total supply of carbon quotas in time period t, ∑B t represents the net balance of carbon quotas in time period t; The constraints for carbon quota supply and demand balance include: ∑S t -∑D t ≥0; Among them, St represents the carbon quota supply in time period t, and Dt represents the carbon quota demand in time period t.

5. The method according to claim 2, wherein: The modified model includes: Among them, Δ t represents the correction amount in time period t, μ represents the overall mean, M t-1 represents the error correction term, α represents the error correction coefficient, Indicates GDP correction coefficient, ΔY k represents the GDP change of the kth sample in time period t, n is the total number of samples, σ k represents the population correction factor, ΔP k ′ represents the population change of the kth sample in time period t, ξ k Represents the capital investment correction factor, ΔK k represents the change in capital investment of the kth sample in time period t, λ k represents the labor input correction factor, ΔL k represents the change in labor input of the kth sample in time period t, ε t represents white noise in time period t.

6. The method according to claim 2, further comprising: In response to receiving a selection of a target scenario from preset scenarios, preset indicator parameters and constraint conditions corresponding to the target scenario are determined.

7. The method according to claim 1, further comprising: Determining a first weight of a candidate indicator parameter based on a hierarchical analysis method, and determining a second weight of the candidate indicator parameter based on an entropy weight method; The preset indicator parameter is determined from the candidate indicator parameters based on the first weight and the second weight.

8. A device for predicting carbon emissions by region, comprising: An acquisition module, used to acquire index data of preset index parameters for carbon emission prediction in a target area; A prediction module, used to perform carbon emission prediction based on a carbon emission prediction model and the index data to obtain the initial carbon emission of the target area; wherein the carbon emission prediction model is constructed based on the preset index parameters; The correction module is used to correct the initial carbon emissions based on the correction model and correction data to obtain the predicted carbon emissions.

9. The device according to claim 8, wherein: The carbon emission prediction model includes: f(x)=C1(x)+C2(x)+C3(x), st.min p ≤index p ≤max p , p∈{rate population ,rate GDP ,ratio re ,incre_rate carbon ,incre_rate green ,ratio nof }; Wherein, f(x) is the objective function of the carbon emission prediction model, C1(x) is the direct carbon emission of energy activities, C2(x) is the carbon emission of industrial processes, and C3(x) is the transferred carbon emission of energy activities; Among them, C1(x)=g1(x)+g2(x), g1(x) is the carbon emissions of terminal consumption, and g2(x) is the carbon emissions of processing and conversion input and output; the_end_ene i is the carbon emission release of the ith sector in terminal consumption, and z is the total sectoral amount of terminal consumption; input_output_ene j is the carbon emission of the jth sector in the input-output, and m is the total sectoral input-output; C2(x)=∑(p i (x)×factor i ), p i (x) is the output of the lth product, factor i is the product carbon emission factor corresponding to the lth product; C3(x)=E trans ×factor ele , E trans is the carbon emissions of regional electricity transfer, factor ele is the corresponding carbon emission factor; index p is the pth preset indicator parameter, rate population is the natural population growth rate, rate GDP is the GDP growth rate, ratio re is the proportion of renewable energy generation, increase_rate carbon is the carbon quota growth rate, increase_rate green is the growth rate of green certificate trading volume, ratio nof is the proportion of non-fossil energy consumption; min p is the lower limit of the pth preset indicator parameter, max p is the upper limit of the pth preset indicator parameter.

10. The device according to claim 9, wherein: The constraints of the carbon quota price in the carbon emission prediction model include: min ≤P≤P max ; Wherein, P represents the carbon quota price, which is related to the supply and demand of carbon quotas. min Indicates the price lower limit, P max Indicates the price ceiling.

11. The device according to claim 10, wherein: The carbon emission prediction model also includes: ∑D t =∑S t +∑B t ; Where t represents the time period, ∑D t represents the total demand for carbon quotas in time period t, ∑S t represents the total supply of carbon quotas in time period t, ∑B t represents the net balance of carbon quotas in time period t; The constraints for carbon quota supply and demand balance include: ∑S t -∑D t ≥0; Among them, St represents the carbon quota supply in time period t, and Dt represents the carbon quota demand in time period t.

12. The device according to claim 9, wherein: The modified model includes: Among them, Δ t represents the correction amount in time period t, μ represents the overall mean, M t-1 represents the error correction term, α represents the error correction coefficient, Indicates GDP correction coefficient, ΔY k represents the GDP change of the kth sample in time period t, n is the total number of samples, σ k represents the population correction factor, ΔP k ′ represents the population change of the kth sample in time period t, ξ k Represents the capital investment correction factor, ΔK k represents the change in capital investment of the kth sample in time period t, λ k represents the labor input correction factor, ΔL k represents the change in labor input of the kth sample in time period t, ε t represents white noise in time period t.

13. The apparatus according to claim 9, further comprising: The scenario setting module is used to determine preset indicator parameters and constraint conditions corresponding to the target scenario in response to receiving a target scenario selected from preset scenarios.

14. The apparatus according to claim 8, further comprising: A weight module, used to determine a first weight of a candidate indicator parameter based on a hierarchical analysis method, and to determine a second weight of the candidate indicator parameter based on an entropy weight method; A parameter module is used to determine the preset indicator parameter from the candidate indicator parameters based on the first weight and the second weight.

15. An electronic device comprising 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 program. 16 . A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method according to claim 1 .

Images