Method and device for formulating carbon emission targets based on carbon emission inventories

Abstract

This application relates to the field of carbon emission target planning and discloses a method for formulating carbon emission targets based on a carbon emission inventory. This method includes: using an activity level prediction model to determine the predicted activity level data of carbon emissions over time based on historical activity level data; and using an emission factor prediction model to determine the predicted emission factor data of carbon emissions over time based on historical emission factor data; using an activity level fluctuation prediction model to determine activity level adjustment data based on activity level fluctuation event information and predicted target activity level data; using an emission factor fluctuation prediction model to determine emission factor adjustment data based on emission factor fluctuation event information and predicted target emission factor data; and determining the carbon emission target over time for the target time period based on the activity level adjustment data and the emission factor adjustment data. This application can scientifically formulate the carbon emission targets of enterprises and helps to scientifically optimize and control carbon emissions.

Description

Technical Field

[0001] This application relates to the technical field of carbon emission target planning. More specifically, it relates to a method and device for formulating carbon emission targets based on a carbon emission inventory. Background Art

[0002] A carbon emission inventory is used to statistically calculate the greenhouse gas emissions of an organization, enterprise, project, product or region, and is used to systematically collect, record and report the direct and indirect greenhouse gas emissions within a set time period. The carbon emission inventory details the emissions of carbon dioxide (CO2) and other greenhouse gases (such as methane CH4, nitrous oxide N2O, etc.) generated by various activities. The carbon emission inventory is an important tool for assessing and managing greenhouse gas emissions. The main contents of the carbon emission inventory include direct emission statistics, indirect emission statistics and other indirect emission statistics. Direct emission statistics include the emissions from carbon emission sources directly owned or controlled by an enterprise. For example, the emissions directly generated by an enterprise's coal-fired boiler, the fuel used by company vehicles, etc. Indirect emission statistics include the emissions generated by the energy purchased by an enterprise. For example, the emissions generated by the electricity purchased from the power grid. Other indirect emissions include emissions caused by an enterprise's activities but occurring outside the enterprise. For example, the emissions of suppliers, the emissions during the use stage of products, the emissions in waste treatment, etc.

[0003] A carbon emission target is a specific emission reduction target set by an enterprise, organization or government to address climate change and reduce greenhouse gas emissions. Formulating a carbon emission target requires clarifying the amount of carbon emissions to be reduced within a certain period of time or reaching a certain carbon emission peak. Patent CN116090908B (Application No.: CN202310340159.7) provides a method for monitoring and verifying the carbon emissions of a nearly zero-carbon port. The intelligent monitoring module collects the port carbon data within a preset time period and uploads it to the intelligent calculation module; the intelligent calculation module calculates the carbon emissions of the port through an emission calculation method based on the received carbon data; the carbon emission verification module verifies the carbon emission data calculated by the intelligent calculation module according to the port carbon emission inventory; the carbon emission prediction module predicts the carbon emissions in the next time period based on the data obtained from the calculation and verification. The method in Patent CN116090908B can predict the carbon emissions of a nearly zero-carbon port, but cannot scientifically formulate the carbon emission target for an enterprise. Summary of the Invention

[0004] The purpose of this application is to provide a method and device for formulating carbon emission targets based on a carbon emission inventory, which solves the technical problem of being unable to scientifically formulate the carbon emission target for an enterprise, and achieves the technical effects of scientifically formulating the carbon emission target for an enterprise and scientifically optimizing and controlling the carbon emissions.

[0005] A carbon emission target setting method based on a carbon emission inventory provided by an embodiment of the present application. The method includes: obtaining historical data of activity levels and historical data of emission factors of carbon emissions over time, and filling in the missing values of the historical data of activity levels and the historical data of emission factors; obtaining information on target activity level fluctuation events and target emission factor fluctuation events over time in a target time period; where one historical data of an activity level corresponds to one historical data of an emission factor; determining, through an activity level prediction model, predicted activity level data of carbon emissions over time based on the historical data of activity levels; and determining, through an emission factor prediction model, predicted emission factor data of carbon emissions over time based on the historical data of emission factors; determining activity level adjustment data through an activity level fluctuation prediction model based on the information on activity level fluctuation events and the predicted target activity level data; determining emission factor adjustment data through an emission factor fluctuation prediction model based on the information on emission factor fluctuation events and the predicted target emission factor data; and determining a carbon emission target over time in the target time period based on the activity level adjustment data and the emission factor adjustment data.

[0006] In a possible implementation manner, obtaining historical data of activity levels and historical data of emission factors of carbon emissions over time includes: determining multiple activity level data on multiple consecutive time periods in the historical data that do not include information on activity level fluctuation events as the historical data of activity levels; determining multiple emission factor data on multiple consecutive time periods in the historical data that do not include information on emission factor fluctuation events as the historical data of emission factors; where the time periods of the multiple historical data of activity levels and the multiple historical data of emission factors correspond respectively.

[0007] In another possible implementation manner, the method further includes: determining activity level data on a consecutive time period in the historical data that includes information on historical activity level fluctuation events as activity level training data; determining emission factor data on a consecutive time period in the historical data that includes information on historical emission factor fluctuation events as emission factor training data; and obtaining historical data of activity levels and historical data of emission factors before and during the same time period and with the same duration as the activity level training data; where the information on historical activity level fluctuation events includes the type of activity level fluctuation event, the amplitude of the fluctuation impact and the duration of the fluctuation impact of the historical data of activity levels over time, and the information on historical emission factor fluctuation events includes the type of emission factor fluctuation event, the amplitude of the fluctuation impact and the duration of the fluctuation impact of the historical data of emission factors over time; training an activity level fluctuation prediction model based on the historical data of activity levels, the activity level training data and the information on historical activity level fluctuation events; and training an emission factor fluctuation prediction model based on the historical data of emission factors, the emission factor training data and the information on historical emission factor fluctuation events.

[0008] In another possible implementation, obtaining the historical data of the activity level and the historical data of the emission factor of carbon emissions over time further includes: among multiple activity level data, determining a first quantity of activity level data whose corresponding time period length is greater than a preset time period length and the time interval between the time period corresponding to the activity level data and the current time is less than a preset time interval as the historical data of the activity level.

[0009] In another possible implementation, obtaining the historical data of the activity level and the historical data of the emission factor of carbon emissions over time further includes: among multiple activity level data, when the quantity of activity level data whose time interval between the time period corresponding to the activity level data and the current time is less than a preset time interval is less than the first quantity, determining the first activity level data on the first continuous time period including the information of the first historical activity level fluctuation event in the historical data, and the time period length corresponding to the first activity level data is greater than a preset time period length, and the fluctuation influence duration of the activity level data corresponding to the information of the first historical activity level fluctuation event over time is less than a preset fluctuation influence duration; through the activity level prediction model, completing the activity level data corresponding to the fluctuation influence duration in the first activity level data as the historical data of the activity level.

[0010] In another possible implementation, the method further includes: obtaining a carbon emission constraint target and a target time period corresponding to the carbon emission constraint target, and when the carbon emission target at the end of the target time period is greater than the carbon emission constraint target, randomly inserting one or more design activity level fluctuation event information and design emission factor fluctuation event information; through the activity level fluctuation prediction model, determining the activity level design data according to the design activity level fluctuation event information and the target activity level prediction data; through the emission factor fluctuation prediction model, determining the emission factor design data according to the design emission factor fluctuation event information and the target emission factor prediction data; determining the carbon emission design target of the target time period over time according to the activity level design data and the emission factor design data; when the carbon emission design target at the end of the target time period is less than or equal to the carbon emission constraint target, outputting one or more design activity level fluctuation event information and design emission factor fluctuation event information.

[0011] An embodiment of the present application further provides a carbon emission target formulation device based on a carbon emission inventory. The carbon emission target formulation device based on a carbon emission inventory includes units for executing the method described above.

[0012] An embodiment of the present application further provides a carbon emission target formulation device based on a carbon emission inventory, including 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 described above is implemented.

[0013] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method described above is implemented.

[0014] The embodiment of the present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the method described above are implemented.

[0015] The beneficial effects of the embodiment of the present application compared with the prior art are as follows:

[0016] The embodiment of the present application provides a method for formulating a carbon emission target based on a carbon emission inventory. The method includes: obtaining historical data of activity levels and historical data of emission factors of carbon emissions in time series, and complementing the missing values of the historical data of activity levels and historical data of emission factors; obtaining information on target activity level fluctuation events and target emission factor fluctuation events in the target time period in time series; determining predicted activity level data of carbon emissions in time series through an activity level prediction model based on the historical data of activity levels; and determining predicted emission factor data of carbon emissions in time series through an emission factor prediction model based on the historical data of emission factors; determining activity level adjustment data through an activity level fluctuation prediction model based on the information on activity level fluctuation events and the predicted target activity level data; determining emission factor adjustment data through an emission factor fluctuation prediction model based on the information on emission factor fluctuation events and the predicted target emission factor data; and determining the carbon emission target in the target time period in time series based on the activity level adjustment data and the emission factor adjustment data. By combining the information on activity level fluctuation events and emission factor fluctuation events, the embodiment of the present application predicts and corrects the carbon emissions, and can scientifically combine the activity level fluctuation events and emission factor fluctuation events to formulate the carbon emission target, thereby improving the scientificity and rationality of formulating the carbon emission target. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0018] Figure 1 It is a schematic flowchart of a method for formulating a carbon emission target based on a carbon emission inventory provided by the embodiment of the present application;

[0019] Figure 2 It is a schematic diagram of a carbon emission target formulation process provided by the embodiment of the present application;

[0020] Figure 3 A schematic flowchart for training an activity level fluctuation prediction model and a training emission factor fluctuation prediction model provided by an embodiment of this application;

[0021] Figure 4 A schematic logical structure diagram of a carbon emission target setting device based on a carbon emission inventory provided by an embodiment of this application;

[0022] Figure 5 A schematic physical structure diagram of a carbon emission target setting device based on a carbon emission inventory provided by an embodiment of this application. Detailed implementation manners

[0023] It should be understood that when used in the description of this application specification and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0024] It should also be understood that the term "and / or" used in the description of this application specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0025] As used in the description of this application specification and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining" or "in response to detecting" according to the context. Similarly, the phrase "if it is determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once it is determined", "in response to determining", "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]" according to the context.

[0026] In addition, in the description of this application specification and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "comprising", "including", "having" and their variants mean "including but not limited to", unless otherwise specifically emphasized.

[0028] In existing methods for predicting carbon emissions, it is not possible to scientifically formulate carbon emission targets for enterprises.

[0029] For the above reasons, the embodiments of this application provide a method for formulating carbon emission targets based on a carbon emission inventory. This method includes: obtaining historical data on activity levels and historical data on emission factors of carbon emissions over time, and filling in the missing values of the historical data on activity levels and historical data on emission factors; obtaining information on target activity level fluctuation events and target emission factor fluctuation events over time for the target time period; through an activity level prediction model, determining predicted activity level data of carbon emissions over time based on the historical data on activity levels; and through an emission factor prediction model, determining predicted emission factor data of carbon emissions over time based on the historical data on emission factors; through an activity level fluctuation prediction model, determining activity level adjustment data based on the information on activity level fluctuation events and the predicted target activity level data; through an emission factor fluctuation prediction model, determining emission factor adjustment data based on the information on emission factor fluctuation events and the predicted target emission factor data; and determining the carbon emission target over time for the target time period based on the activity level adjustment data and the emission factor adjustment data. The embodiments of this application predict and correct carbon emissions by combining information on activity level fluctuation events and emission factor fluctuation events, and can scientifically combine activity level fluctuation events and emission factor fluctuation events to formulate carbon emission targets, improving the scientificity and rationality of formulating carbon emission targets.

[0030] In some scenarios, a method for formulating carbon emission targets based on a carbon emission inventory according to the embodiments of this application can be applied to formulating carbon emission targets for enterprises. Especially for manufacturing enterprises such as cement and electricity, it can combine activity level fluctuation events and emission factor fluctuation events to formulate carbon emission targets, and can reasonably estimate the carbon emission fluctuations caused by production fluctuations and technological improvements, improving the scientificity and rationality of formulating carbon emission targets.

[0031] The following specifically describes a method for formulating carbon emission targets provided by an embodiment of the present application in combination with specific examples.

[0032] Figure 1 It is a schematic flowchart of a method for formulating carbon emission targets provided by an embodiment of the present application. As Figure 1 shown, this method includes S110 to S130, and the following specifically describes S110 to S130.

[0033] S110. Obtain the historical data of the activity level and the historical data of the emission factor of carbon emissions in time series, and complete the missing values of the historical data of the activity level and the historical data of the emission factor. Obtain the information of the target activity level fluctuation events and the target emission factor fluctuation events of the target time period in time series. Among them, one historical data of the activity level corresponds to one historical data of the emission factor.

[0034] Figure 2 It is a schematic diagram of a carbon emission target formulation process provided by an embodiment of the present application. As Figure 1 and Figure 2 shown, in order to scientifically formulate carbon emission targets, the historical data of the activity level and the historical data of the emission factor of carbon emissions in time series can be obtained first. The historical data of the activity level represents the information of the production activity level such as the product output in the production activities of the enterprise, and the historical data of the emission factor represents the carbon emission calculation factor corresponding to the product production output in the production activities of the enterprise.

[0035] Exemplarily, the historical data of the activity level and the historical data of the emission factor of carbon emissions in time series can be obtained through the carbon emission inventory of the enterprise.

[0036] When calculating the carbon emissions, the carbon emissions corresponding to the first product can be obtained by multiplying the historical data of the activity level corresponding to the first product and the historical data of the emission factor corresponding to the first product.

[0037] After obtaining the historical data of the activity level and the historical data of the emission factor, the missing values of the historical data of the activity level and the historical data of the emission factor can be completed by methods such as curve fitting completion and deep learning completion, so as to improve the accuracy when predicting carbon emissions through the historical data of the activity level and the historical data of the emission factor in the future.

[0038] When determining carbon emission targets, during production activities, the activity level of an enterprise may change due to changes in order volume, or the carbon emission factor may change due to factors such as technological improvements. Therefore, it is possible to obtain information on target activity level fluctuation events and target emission factor fluctuation events in the time series for the target time period. The target time period is the time period for which carbon emission targets need to be set. The information on target activity level fluctuation events represents the change information of the activity level caused by changes in order volume, and the information on target emission factor fluctuation events represents the change information of the carbon emission factor caused by factors such as technological improvements.

[0039] Exemplarily, when obtaining historical activity level data, one historical activity level data corresponds to one historical emission factor data, thereby ensuring the simultaneity of the activity level and the emission factor.

[0040] Exemplarily, the historical activity level data can all be activity level data in the time series, and the historical emission factor data can be emission factor data in the time series.

[0041] S120. Through the activity level prediction model, based on the historical activity level data, determine the predicted activity level data of carbon emissions in the time series. And through the emission factor prediction model, based on the historical emission factor data, determine the predicted emission factor data of carbon emissions in the time series.

[0042] As Figure 1 and Figure 2 shown, when formulating carbon emission targets, it is possible to first determine the predicted activity level data for the target time period without the influence of information on target activity level fluctuation events, so that the activity level can conform to the actual daily production status of the enterprise. Furthermore, through the activity level prediction model, based on the historical activity level data, determine the predicted activity level data of carbon emissions in the time series. The predicted activity level data reflects the enterprise activity level data without the influence of information on target activity level fluctuation events.

[0043] Exemplarily, the activity level prediction model can be a time series prediction model based on LSTM.

[0044] Exemplarily, the activity level prediction model can be trained through historical activity level data in the time series.

[0045] Exemplarily, target activity level fluctuation events can include production-related events (such as planned equipment maintenance and repair events, equipment failure events, production capacity expansion or reduction events), supply chain events (such as raw material supply interruption events, transportation delay events), market-related events (such as demand fluctuation events, competitor behavior events), and policy and regulation change events (such as environmental protection regulation change events, tax policy change events), etc.

[0046] Similarly, it is also possible to first determine the emission factor prediction data for the target time period without the influence of target emission factor fluctuation event information, so that the emission factor can conform to the actual daily production status of the enterprise. Furthermore, through the emission factor prediction model, based on the historical emission factor data, the emission factor prediction data can be determined, and the emission factor prediction data reflects the emission factor level data without the influence of target emission factor fluctuation event information.

[0047] Exemplarily, the emission factor prediction model can be a time series prediction model based on LSTM.

[0048] Exemplarily, the emission factor prediction model can be trained through the historical emission factor data in time series.

[0049] Exemplarily, the target emission factor fluctuation event can include technology upgrade events, equipment efficiency change events, energy type change events, and equipment accident events, etc.

[0050] Exemplarily, the activity level prediction data is the enterprise activity level data in time series, and the emission factor prediction data is the enterprise emission factor data in time series.

[0051] S130. Through the activity level fluctuation prediction model, based on the activity level fluctuation event information and the target activity level prediction data, determine the activity level adjustment data. Through the emission factor fluctuation prediction model, based on the emission factor fluctuation event information and the target emission factor prediction data, determine the emission factor adjustment data. Based on the activity level adjustment data and the emission factor adjustment data, determine the carbon emission target for the target time period in time series.

[0052] After obtaining the activity level prediction data that reflects the situation without the influence of target activity level fluctuation event information, in order to combine the sudden fluctuation of the enterprise's activity level, through the activity level fluctuation prediction model, based on the activity level fluctuation event information and the target activity level prediction data, determine the activity level adjustment data, and the activity level adjustment data reflects the activity level data information of the enterprise's production activities under the influence of the activity level fluctuation event.

[0053] Exemplarily, the activity level fluctuation prediction model can be a time series prediction model based on LSTM.

[0054] Similarly, after obtaining the emission factor prediction data for the target time period without the influence of target emission factor fluctuation event information, through the emission factor fluctuation prediction model, based on the emission factor fluctuation event information and the target emission factor prediction data, determine the emission factor adjustment data, and the emission factor adjustment data reflects the emission factor data information of the emission factor in the enterprise's production activities under the influence of the target emission factor fluctuation event.

[0055] Exemplarily, the activity level adjustment data is the activity level data in time series, and the emission factor adjustment data is the emission factor data in time series.

[0056] Exemplarily, the emission factor fluctuation prediction model can be a time series prediction model based on LSTM.

[0057] Such as Figure 1 and Figure 2 As shown, after obtaining the activity level adjustment data and the emission factor adjustment data, the activity level adjustment data and the emission factor adjustment data at each time point can be multiplied according to the activity level adjustment data and the emission factor adjustment data to obtain the carbon emission target in time series for the target time period. The carbon emission target represents the carbon emission target in the enterprise production activities affected by the activity level fluctuation and the emission factor fluctuation.

[0058] The beneficial effect brought by the above implementation method is that it can combine the activity level data information of the enterprise production activities affected by the activity level fluctuation event and the emission factor data information of the emission factors in the enterprise production activities affected by the standard emission factor fluctuation event, obtain the carbon emission target in the enterprise production activities affected by the activity level fluctuation and the emission factor fluctuation, and realize the reasonable prediction and formulation of the carbon emission target in the enterprise production activities.

[0059] In some implementation methods, in the above S110, obtaining the activity level historical data and the emission factor historical data of the carbon emission in time series includes: determining multiple activity level data on multiple consecutive time periods in the historical data that do not include the activity level fluctuation event information as the activity level historical data. Determining multiple emission factor data on multiple consecutive time periods in the historical data that do not include the emission factor fluctuation event information as the emission factor historical data; wherein, the time periods of the multiple activity level historical data and the multiple emission factor historical data correspond respectively.

[0060] When determining the activity level prediction data of the carbon emission in time series through the activity level prediction model, in order to ensure that the activity level historical data is not affected by the activity level fluctuation event, multiple activity level data on multiple consecutive time periods in the historical data that do not include the activity level fluctuation event information can be determined as the activity level historical data.

[0061] Exemplarily, the multiple consecutive time periods of the activity level historical data are all consecutive time periods, which can avoid the impact of carbon emissions caused by production interruption.

[0062] When determining the emission factor prediction data of carbon emissions over time through an emission factor prediction model, in order to ensure that historical emission factor data is not affected by emission factor fluctuation events, multiple emission factor data on multiple consecutive time periods in the historical data that do not include information on emission factor fluctuation events can be determined as the historical emission factor data.

[0063] Exemplarily, multiple consecutive time periods of the historical emission factor data are all consecutive time periods, which can avoid the impact of carbon emissions caused by production interruptions.

[0064] When determining multiple historical activity level data and multiple historical emission factor data, it is also necessary to ensure that the time periods of the multiple historical activity level data and the multiple historical emission factor data correspond respectively, so as to ensure that the prediction of carbon emissions conforms to the actual production of the enterprise.

[0065] Exemplarily, the first time period in which the first historical activity level data is located corresponds to the first time period in which the first historical emission factor data is located.

[0066] The beneficial effects brought by the above implementation method are that by determining multiple activity level data on multiple consecutive time periods in the historical data that do not include information on activity level fluctuation events, and determining multiple emission factor data on multiple consecutive time periods in the historical data that do not include information on emission factor fluctuation events, it can be ensured that the prediction of carbon emissions conforms to the actual production of the enterprise.

[0067] The beneficial effects brought by the above implementation method also lie in that by ensuring that the time periods of multiple historical activity level data and multiple historical emission factor data correspond respectively, it can be ensured that the prediction and target setting of carbon emissions conform to the actual production of the enterprise.

[0068] In some implementation methods, the above method further includes S210 to S220, which will be specifically described below.

[0069] S210: Determine the activity level data on the consecutive time periods in the historical data that include information on historical activity level fluctuation events as the activity level training data. Determine the emission factor data on the consecutive time periods in the historical data that include information on historical emission factor fluctuation events as the emission factor training data. And obtain the historical activity level data and historical emission factor data before and during the same period and with the same duration as the activity level training data. Among them, the historical activity level fluctuation event information includes the type of activity level fluctuation event, the fluctuation impact amplitude and fluctuation impact duration of the historical activity level data over time, and the historical emission factor fluctuation event information includes the type of emission factor fluctuation event, the fluctuation impact amplitude and fluctuation impact duration of the historical emission factor data over time.

[0070] Figure 3 A flowchart showing the process of training an activity level fluctuation prediction model and an emission factor fluctuation prediction model provided by an embodiment of the present application. As Figure 3 shown, when training the activity level fluctuation prediction model, it is possible to determine the activity level data on a continuous time period in historical data that includes historical activity level fluctuation event information. The activity level data on a continuous time period that includes historical activity level fluctuation event information represents the activity level data affected by historical activity level fluctuation events. Taking the activity level data affected by historical activity level fluctuation events as activity level training data can predict the activity level data affected by subsequent activity level fluctuation events.

[0071] As Figure 3 shown, when training the emission factor fluctuation prediction model, it is possible to determine the emission factor data on a continuous time period in historical data that includes historical emission factor fluctuation event information. The emission factor data on a continuous time period that includes historical emission factor fluctuation event information represents the emission factor data affected by historical emission factor fluctuation events. Taking the emission factor data affected by historical emission factor fluctuation events as emission factor training data can predict the emission factor data affected by subsequent emission factor fluctuation events.

[0072] When training the activity level fluctuation prediction model or the emission factor fluctuation prediction model, in order to accurately simulate the situation affected by subsequent activity level fluctuation events or emission factor fluctuation events, it is possible to obtain the activity level historical data and emission factor historical data that are before and contemporaneous with the activity level training data and have the same duration, and train the activity level fluctuation prediction model or the emission factor fluctuation prediction model based on the activity level historical data and emission factor historical data that are before and contemporaneous with the activity level training data and have the same duration, so as to accurately evaluate the impact data of activity level fluctuation events or emission factor fluctuation events.

[0073] Exemplarily, the duration corresponding to the activity level training data can be the activity level data within 12 hours on the 5th of the current month, and the activity level historical data and emission factor historical data that are contemporaneous with the activity level training data and have the same duration can be the activity level data and emission historical data within 12 hours on the 5th of the previous month.

[0074] Exemplarily, the historical activity level fluctuation event information may include the activity level fluctuation event type, the fluctuation impact amplitude and the fluctuation impact duration of the activity level historical data in time series. The activity level fluctuation event type characterizes the specific type of the event that affects the activity level. The fluctuation impact amplitude and the fluctuation impact duration of the activity level historical data in time series characterize the amplitude information and the duration information of the impact of the historical activity level fluctuation event on the activity level.

[0075] Exemplarily, the historical emission factor fluctuation event information may include the emission factor fluctuation event type, the fluctuation impact amplitude and the fluctuation impact duration of the emission factor historical data in time series. The emission factor fluctuation event type characterizes the specific type of the event that affects the emission factor. The fluctuation impact amplitude and the fluctuation impact duration of the emission factor historical data in time series characterize the amplitude information and the duration information of the impact of the historical emission factor fluctuation event on the emission factor.

[0076] S220. Train an activity level fluctuation prediction model according to the activity level historical data, the activity level training data and the historical activity level fluctuation event information. Train an emission factor fluctuation prediction model according to the emission factor historical data, the emission factor training data and the historical emission factor fluctuation event information.

[0077] After obtaining the above-mentioned activity level historical data, activity level training data and historical activity level fluctuation event information, an activity level fluctuation prediction model can be trained according to the activity level historical data, the activity level training data and the historical activity level fluctuation event information. The activity level fluctuation prediction model can predict the activity level data after an activity level fluctuation event occurs according to the activity level data and the activity level fluctuation event information.

[0078] After obtaining the above-mentioned emission factor historical data, emission factor training data and historical emission factor fluctuation event information, an emission factor fluctuation prediction model can be trained according to the emission factor historical data, the emission factor training data and the historical emission factor fluctuation event information. The emission factor fluctuation prediction model can predict the emission factor data after an emission factor fluctuation event occurs according to the emission factor data and the emission factor fluctuation event information.

[0079] The beneficial effects brought by the above implementation manner are that the trained activity level fluctuation prediction model can predict the activity level data after an activity level fluctuation event occurs according to the activity level data and the activity level fluctuation event information; the trained emission factor fluctuation prediction model can predict the emission factor data after an emission factor fluctuation event occurs according to the emission factor data and the emission factor fluctuation event information.

[0080] The beneficial effects brought by the above implementation method also lie in that it can train an activity level fluctuation prediction model or an emission factor fluctuation prediction model based on the activity level historical data and emission factor historical data that are before and during the activity level training data and have the same duration, so as to accurately evaluate the impact data of the activity level fluctuation event or the emission factor fluctuation event.

[0081] In some implementation methods, in the above S110, obtaining the activity level historical data and emission factor historical data of the carbon emissions in time series further includes: among multiple activity level data, determining the first quantity of activity level data whose corresponding time period length is greater than the preset time period length and the time interval between the corresponding time period of the activity level data and the current time is less than the preset time interval as the activity level historical data.

[0082] When determining the activity level historical data, among multiple activity level data, it can be determined that the corresponding time period length of the activity level data is greater than the preset time period length. By making the corresponding time period length of the activity level data greater than the preset time period length, it can ensure that the activity level data is predicted within a certain time length range, avoiding accidental errors caused by too short time periods during the collection of activity level data.

[0083] When determining the activity level historical data, it can be determined that the first quantity of activity level data whose corresponding time period and the current time have a time interval less than the preset time interval as the activity level historical data, so as to ensure that the recent activity level data can be used for prediction and ensure that the predicted value of the activity level data is more in line with the actual production of the enterprise.

[0084] Exemplarily, the preset time interval can be 2 to 5 times the preset time period length.

[0085] Exemplarily, when the preset time period length is 10 days, the preset time interval can be 20 days to 50 days.

[0086] Exemplarily, the first quantity can be 3 to 5.

[0087] Exemplarily, the time interval between the corresponding time period of the activity level data and the current time can be the time interval between the midpoint moment of the corresponding time period of the activity level data and the current time, and the current time is the starting moment of the target time period.

[0088] The beneficial effects brought by the above implementation method lie in that the activity level data is predicted within a certain time length range, avoiding accidental errors caused by too short time periods during the collection of activity level data.

[0089] The beneficial effects brought by the above implementation method also lie in that using recent activity level data for prediction can ensure that the predicted values of the activity level data are more in line with the actual production of the enterprise.

[0090] The beneficial effects brought by the above implementation method also lie in that the preset time interval is 2 to 5 times the length of the preset time period, which can flexibly adjust the length of the preset time interval according to the length of the time period when collecting the activity level data. When using recent activity level data for prediction, it ensures that the first quantity of activity level data can be collected, facilitating the flexible collection of activity level data.

[0091] In some implementation methods, in the above S110, obtaining the historical activity level data and emission factor historical data of carbon emissions in time series further includes S310 to S320. The following specifically describes S310 to S320.

[0092] S310. Among multiple activity level data, when the number of activity level data whose time interval between the corresponding time period and the current time is less than the preset time interval is less than the first quantity, determine the first activity level data on the first continuous time period including the first historical activity level fluctuation event information in the historical data, and the time period length corresponding to the first activity level data is greater than the preset time period length, and the fluctuation influence duration of the activity level data corresponding to the first historical activity level fluctuation event information in time series is less than the preset fluctuation influence duration.

[0093] Among multiple activity level data, when the number of activity level data whose time interval between the corresponding time period and the current time is less than the preset time interval is less than the first quantity, at this time, the first quantity of recent activity level data that meets the conditions cannot be obtained.

[0094] In order to obtain activity level data that conforms to the actual production of the enterprise, the activity level data on the continuous time period including historical activity level fluctuation event information can be used to approximately replace the activity level data on the continuous time period that does not include historical activity level fluctuation event information, so as to ensure that the historical activity level data conforms to the actual production of the enterprise.

[0095] During approximate replacement, the first activity level data on the first continuous time period including the first historical activity level fluctuation event information in the historical data can be determined, and the first activity level data is the activity level data affected by the first historical activity level fluctuation event.

[0096] When determining the first activity level data, it is necessary to ensure that the time period length corresponding to the first activity level data is greater than the preset time period length, so as to be able to predict the activity level data within a certain time length range and avoid accidental errors caused by too short time periods when collecting activity level data.

[0097] Meanwhile, it is necessary to ensure that the activity level data corresponding to the first historical activity level fluctuation event information has a fluctuation influence duration in time series that is less than a preset fluctuation influence duration, so as to avoid the influence duration of the first historical activity level fluctuation event being too long and causing the activity level data to deviate from the actual production situation of the enterprise over a long time span.

[0098] Exemplarily, the preset fluctuation influence duration can be 1 / 10 to 1 / 5 of the preset time period length.

[0099] S320. Through the activity level prediction model, complete the activity level data corresponding to the fluctuation influence duration in the first activity level data as the activity level historical data.

[0100] After obtaining the first activity level data, through the activity level prediction model, the activity level data corresponding to the fluctuation influence duration in the first activity level data can be completed as the activity level historical data.

[0101] When completing the activity level data corresponding to the fluctuation influence duration in the first activity level data, by reusing the activity level prediction model, the activity level data affected by the historical activity level fluctuation event can be completed.

[0102] The beneficial effects brought by the above implementation method are as follows: The activity level data in the continuous time period including the historical activity level fluctuation event information is used to approximately replace the activity level data in the continuous time period not including the historical activity level fluctuation event information, and the activity level data corresponding to the fluctuation influence duration is simulated and replaced to ensure that the historical activity level data conforms to the actual production of the enterprise.

[0103] The beneficial effects brought by the above implementation method also lie in that the fluctuation influence duration of the activity level data corresponding to the first historical activity level fluctuation event information in time series is less than the preset fluctuation influence duration, which can avoid the activity level data deviating from the actual production situation of the enterprise over a long time span.

[0104] The beneficial effects brought by the above implementation method also lie in that by reusing the activity level prediction model, the activity level data affected by the historical activity level fluctuation event can be completed, which can ensure that the activity level data conforms to the actual production of the enterprise.

[0105] In some implementation methods, the above method further includes S410 to S420, which are specifically described below.

[0106] S410. Obtain the carbon emission constraint target and the target time period corresponding to the carbon emission constraint target. When the carbon emission target at the end of the target time period is greater than the carbon emission constraint target, randomly insert one or more design activity level fluctuation event information and design emission factor fluctuation event information.

[0107] When formulating the carbon emission target, it is often necessary to consider the carbon emission constraint target, which is the carbon emission target that meets various constraint conditions. Among them, the various constraint conditions of the carbon emission constraint target can be constraint conditions such as the policy requirements and enterprise goals of the carbon emission target.

[0108] After obtaining the carbon emission target in the time series of the target time period, the carbon emission constraint target and the target time period corresponding to the carbon emission constraint target can be determined. The carbon emission constraint target is multiple carbon emission constraint targets in the time series of the target time period. Furthermore, the carbon emission target and the carbon emission constraint target can be compared and judged to determine whether the carbon emission target meets the carbon emission constraint target.

[0109] During the comparison, when the carbon emission target at the end of the target time period is greater than the carbon emission constraint target, it means that the carbon emission target at the end of the target time period does not meet the predetermined carbon emission constraint target. At this time, the adjustment measures of the carbon emission target can be simulated so that the carbon emission target at the end of the target time period does not meet the predetermined carbon emission constraint target.

[0110] When simulating the adjustment measures of the carbon emission target, one or more design activity level fluctuation event information and design emission factor fluctuation event information can be randomly inserted. The one or more design activity level fluctuation event information and design emission factor fluctuation event information are used to simulate activity level fluctuation events or emission factor fluctuation events.

[0111] S420. Through the activity level fluctuation prediction model, determine the activity level design data according to the design activity level fluctuation event information and the target activity level prediction data. Through the emission factor fluctuation prediction model, determine the emission factor design data according to the design emission factor fluctuation event information and the target emission factor prediction data. Determine the carbon emission design target in the time series of the target time period according to the activity level design data and the emission factor design data. When the carbon emission design target at the end of the target time period is less than or equal to the carbon emission constraint target, output one or more design activity level fluctuation event information and design emission factor fluctuation event information.

[0112] After randomly inserting one or more design activity level fluctuation event information, the activity level design data can be determined through the activity level fluctuation prediction model according to the design activity level fluctuation event information and the target activity level prediction data. The activity level design data is the activity level data corresponding to the simulated activity level fluctuation event.

[0113] After randomly inserting information on one or more design emission factor fluctuation events, the emission factor design data can be determined through an emission factor fluctuation prediction model based on the information on design emission factor fluctuation events and target emission factor prediction data. The emission factor design data is the emission factor data corresponding to the simulated emission factor fluctuation events.

[0114] After obtaining the activity level design data and the emission factor design data, the carbon emission design target for the target time period in terms of time series can be determined based on the activity level design data and the emission factor design data. The carbon emission design target is the carbon emission target after inserting information on one or more design activity level fluctuation events and information on design emission factor fluctuation events.

[0115] Exemplarily, the carbon emission design target can be obtained by multiplying the activity level design data and the emission factor design data.

[0116] After obtaining the carbon emission design target, when the carbon emission design target at the end of the target time period is less than or equal to the carbon emission constraint target, it indicates that the carbon emission target after inserting information on one or more design activity level fluctuation events and information on design emission factor fluctuation events meets the requirements of the carbon emission design target. At this time, information on one or more design activity level fluctuation events and information on design emission factor fluctuation events can be output. The information on one or more design activity level fluctuation events and information on design emission factor fluctuation events can guide the enterprise's measures to adjust carbon emissions in production activities, so that the carbon emissions meet the carbon emission constraint target.

[0117] The beneficial effects brought by the above implementation method are that it can guide and adjust carbon emissions in the enterprise's production activities, so that the carbon emissions meet the carbon emission constraint target.

[0118] The beneficial effects brought by the above implementation method also lie in that information on one or more design activity level fluctuation events and information on design emission factor fluctuation events can specifically guide the enterprise's measures to adjust carbon emissions in production activities.

[0119] The embodiment of the present application also provides a carbon emission target formulation device based on a carbon emission inventory. This carbon emission target formulation device based on a carbon emission inventory includes units for executing the method described above.

[0120] Figure 5 It is a schematic logical structure diagram of a carbon emission target formulation device based on a carbon emission inventory provided by an embodiment of the present application, as Figure 5As shown, the device 1 of this embodiment includes a processing unit 11, a storage unit 12, and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to transmit and receive data. The processing unit 11, the storage unit 12, and the transceiver unit 13 cooperate with each other to implement the above-mentioned method. The beneficial effects brought by the embodiments of this application have been described in the above method and will not be elaborated here.

[0121] The embodiments of this application also provide a carbon emission target setting device based on a carbon emission inventory, including 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 above-mentioned method is implemented.

[0122] Figure 5 FIG. is a schematic physical structure diagram of a carbon emission target setting device based on a carbon emission inventory provided by an embodiment of this application. As Figure 5 shown, the device 2 of this embodiment includes: at least one processor 20 ( Figure 5 only one processor 20 is shown in the figure), a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20. When the processor 20 executes the computer program 22, the steps in any of the above method embodiments are implemented. The beneficial effects brought by the embodiments of this application have been described in the above method and will not be elaborated here.

[0123] It should be noted that the information interaction, execution process, etc. between the above devices / units, due to the same concept as the method embodiments of this application, for their specific functions and the technical effects brought, please refer to the method embodiment part for details and will not be elaborated here.

[0124] Those skilled in the art can clearly understand that for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiments and will not be elaborated here.

[0125] The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0126] The embodiments of the present application provide a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal is enabled to execute the steps in the above-mentioned method embodiments.

[0127] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned method embodiments of the present application, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0128] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by the combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0130] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0131] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for setting carbon emission targets based on a carbon emission inventory, characterized in that: The method comprises: Obtain the historical activity level data and emission factor data of carbon emissions in time series, and fill in the missing values of the historical activity level data and emission factor data; obtain the target activity level fluctuation event information and target emission factor fluctuation event information in time series for the target time period; where one historical activity level data corresponds to one historical emission factor data; Using the activity level forecast model, based on the historical activity level data, the activity level forecast data of carbon emissions in time series is determined; and using the emission factor forecast model, based on the historical emission factor data, the emission factor forecast data of carbon emissions in time series is determined; Through the activity level fluctuation prediction model, activity level adjustment data is determined based on activity level fluctuation event information and target activity level prediction data; through the emission factor fluctuation prediction model, emission factor adjustment data is determined based on emission factor fluctuation event information and target emission factor prediction data; based on the activity level adjustment data and emission factor adjustment data, the carbon emission target for the target time period is determined in time series; The method further comprises: Obtain the carbon emission constraint target and the target time period corresponding to the carbon emission constraint target. When the carbon emission target at the end of the target time period is greater than the carbon emission constraint target, randomly insert one or more design activity level fluctuation event information and design emission factor fluctuation event information. Through the activity level fluctuation prediction model, the activity level design data is determined according to the design activity level fluctuation event information and the target activity level prediction data; through the emission factor fluctuation prediction model, the emission factor design data is determined according to the design emission factor fluctuation event information and the target emission factor prediction data; based on the activity level design data and the emission factor design data, the carbon emission design target in the target time period is determined in time series; when the carbon emission design target at the end of the target time period is less than or equal to the carbon emission constraint target, one or more design activity level fluctuation event information and design emission factor fluctuation event information are output.

2. The method according to claim 1, wherein Obtain historical activity level data and emission factor data over time for carbon emissions, including: Determine multiple activity level data over multiple consecutive time periods that do not include information on activity level fluctuation events in the historical data as activity level historical data; determine multiple emission factor data over multiple consecutive time periods that do not include information on emission factor fluctuation events in the historical data as emission factor historical data; wherein the time periods of the multiple activity level historical data and the multiple emission factor historical data correspond to each other.

3. The method according to claim 2, wherein The method further comprises: Determine activity level data over a continuous time period including historical activity level fluctuation event information in the historical data as activity level training data; determine emission factor data over a continuous time period including historical emission factor fluctuation event information in the historical data as emission factor training data; and obtain historical activity level data and emission factor historical data that are concurrent with and of the same duration as the activity level training data and before the activity level training data; wherein the historical activity level fluctuation event information includes the activity level fluctuation event type, the fluctuation impact amplitude and fluctuation impact duration of the historical activity level data in the time series, and the historical emission factor fluctuation event information includes the emission factor fluctuation event type, the fluctuation impact amplitude and fluctuation impact duration of the historical emission factor data in the time series; The activity level fluctuation prediction model is trained based on the historical activity level data, activity level training data and historical activity level fluctuation event information; the emission factor fluctuation prediction model is trained based on the historical emission factor data, emission factor training data and historical emission factor fluctuation event information.

4. The method according to claim 3, wherein Obtain historical activity level data and emission factor data over time for carbon emissions, including: Among multiple activity level data, determine a first number of activity level data whose corresponding time period length is greater than a preset time period length and whose time interval between the time period corresponding to the activity level data and the current time is less than a preset time interval as activity level history data.

5. The method according to claim 4, wherein Obtain historical activity level data and emission factor data over time for carbon emissions, including: When the time interval between the time period corresponding to the activity level data and the current time is less than a preset time interval and the number of activity level data is less than a first number, determining first activity level data for a first continuous time period including first historical activity level fluctuation event information in the historical data, and the time period length corresponding to the first activity level data is greater than the preset time period length, and the fluctuation impact duration of the activity level data corresponding to the first historical activity level fluctuation event information in time series is less than the preset fluctuation impact duration; The activity level prediction model is used to complete the activity level data corresponding to the fluctuation impact duration in the first activity level data as the activity level historical data.

6. A carbon emission target setting device based on a carbon emission inventory, characterized in that: Comprising means for performing the method according to any one of claims 1 to 5.

7. A device for setting a carbon emission target based on a carbon emission inventory, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images