Carbon emission prediction method, device, equipment and medium

Abstract

The invention discloses a carbon emission prediction method and device, equipment and a medium. The method comprises the following steps: constructing a carbon emission vector according to current carbon emission data and historical carbon emission data of a target enterprise; inputting the carbon emission vector into a pre-trained Times Net model to obtain an intermediate parameter; and inputting the intermediate parameters into a pre-trained time convolution model to obtain carbon emission prediction data of the target enterprise at the target time. According to the technical scheme, by combining the TimesNet model and the time convolution model, the problem of bidirectional dependence of a time sequence is effectively solved, meanwhile, the depth and the breadth of the model are greatly improved, and the precision of predicting carbon emission in a complex oil and gas field enterprise production scene is improved.

Description

Technical Field

[0001] The present application relates to the technical field of carbon asset management, and in particular to a method, device, equipment and medium for predicting carbon emissions. Background Art

[0002] The emission of greenhouse gases such as carbon dioxide has led to global warming, which has become a challenging problem facing mankind. The emission of greenhouse gases mainly comes from the rapid development of human industrialization, especially the extensive use of fossil fuels. In this context, in order to improve the intelligent management level of enterprises and promote energy conservation and consumption reduction of enterprises, it is necessary to predict carbon emissions based on current economic operation statistics and energy consumption, so as to accurately evaluate whether the emission reduction targets at each stage can be achieved and achieve smoother emission reduction measures.

[0003] At present, the main methods for carbon emission prediction include physical methods, statistical methods and artificial intelligence methods. Among them, artificial intelligence methods are the hotspot of research, and the widely used artificial intelligence models mainly include back propagation neural networks, support vector machines, long short-term memory networks, etc. However, the carbon emission process of oil and gas field enterprises is relatively complex. Therefore, in the carbon emission prediction scenario of oil and gas field enterprises, the prediction effect of high-dimensional complex data changes is poor.

[0004] Therefore, how to provide a technical solution that can accurately predict carbon emissions is a technical problem that needs to be urgently solved by those skilled in the art. Summary of the invention

[0005] The present application provides a carbon emission prediction method, device, equipment and medium. By combining the TimesNet model and the time convolution model, the problem of bidirectional dependency of time series is effectively solved. At the same time, the depth and breadth of the model are greatly improved, thereby improving the accuracy of carbon emission prediction in complex oil and gas field enterprise production scenarios.

[0006] According to one aspect of the present application, a method for predicting carbon emissions is provided, the method comprising:

[0007] Construct a carbon emission vector based on the current carbon emission data and historical carbon emission data of the target enterprise;

[0008] Inputting the carbon emission vector into a pre-trained TimesNet model to obtain intermediate parameters;

[0009] The intermediate parameters are input into a pre-trained time convolution model to obtain the carbon emission forecast data of the target enterprise at the target time.

[0010] According to another aspect of the present application, a carbon emission prediction device is provided, the device comprising:

[0011] A carbon emission vector construction module is used to construct a carbon emission vector based on the current carbon emission data and historical carbon emission data of the target enterprise;

[0012] An intermediate parameter acquisition module, used for inputting the carbon emission vector into a pre-trained TimesNet model to obtain intermediate parameters;

[0013] The carbon emission prediction module is used to input the intermediate parameters into a pre-trained time convolution model to obtain the carbon emission prediction data of the target enterprise at the target time.

[0014] The technical solution provided by this application constructs a carbon emission vector based on the current carbon emission data and historical carbon emission data of the target enterprise; inputs the carbon emission vector into a pre-trained TimesNet model to obtain intermediate parameters; and inputs the intermediate parameters into a pre-trained time convolution model to obtain the target enterprise's carbon emission forecast data at the target time. This technical solution effectively solves the problem of bidirectional dependency of time series by combining the TimesNet model with the time convolution model, and at the same time greatly improves the depth and breadth of the model, thereby improving the accuracy of carbon emission prediction in complex oil and gas field enterprise production scenarios.

[0015] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A flowchart of a method for predicting carbon emissions provided in Example 1 of the present application;

[0018] Figure 2 A flowchart of a TimesNet model training process provided in Example 1 of the present application;

[0019] Figure 3 A schematic diagram of the structure of a carbon emission prediction device provided in Example 3 of the present application;

[0020] Figure 4 It is a structural schematic diagram of a device for implementing a carbon emission prediction method in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0022] It should be noted that the terms "first", "second", "original", "standard", "training", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] Embodiment 1

[0024] Figure 1 This is a flow chart of a carbon emission prediction method provided in the first embodiment of the present application. This embodiment is applicable to the case of predicting carbon emissions. The method can be executed by a carbon emission prediction device. The carbon emission prediction device can be implemented in the form of hardware and / or software. The carbon emission prediction device can be configured in a device with data processing capabilities. Figure 1 As shown, the method includes:

[0025] S110. Construct a carbon emission vector based on the current carbon emission data and historical carbon emission data of the target enterprise.

[0026] Among them, carbon emission data can be the greenhouse gas emissions generated by the target enterprise during production and other operational activities. Specifically, the default emission factor and fuel calorific value can be used as input to model the emission factor, and the emission factor corresponding to each gas can be calculated; further, in accordance with the carbon inventory requirements of relevant standards, based on activity data, emission factors, and global warming potential, the carbon emission data can be calculated based on the carbon emission topology model.

[0027] Among them, the current carbon emission data and historical carbon emission data can be determined according to the collection frequency of carbon emission data. If the collection frequency is daily, the current carbon emission data is the carbon emission data of the current day, and the historical carbon emission data is the carbon emission data of the historical preset days; if the collection frequency is weekly, the current carbon emission data is the carbon emission data of the current week, and the historical carbon emission data is the carbon emission data of the historical preset weeks.

[0028] In this solution, the carbon emission vector may be in the form of a vector in which current carbon emission data and historical carbon emission data are arranged in time series.

[0029] It should be noted that the historical carbon emission data may be the carbon emission data actually collected during the historical period, or may be the data obtained by preprocessing the carbon emission data actually collected during the historical period.

[0030] S120, inputting the carbon emission vector into a pre-trained TimesNet model to obtain intermediate parameters.

[0031] Among them, the TimesNet model can convert a one-dimensional time series into a set of two-dimensional tensors based on multiple cycles. Specifically, TimesBlock can be used as a universal backbone for time series analysis and connected through residual connections.

[0032] Among them, the intermediate parameter can be a characteristic parameter of the carbon emission vector, which can be used to represent the changing trend of the carbon emission data of the target enterprise.

[0033] S130: Input the intermediate parameters into a pre-trained time convolution model to obtain carbon emission prediction data of the target enterprise at the target time.

[0034] Among them, the temporal convolutional network (TCN) is a method based on the convolutional neural network structure, which can calculate the data in all time steps in parallel, and has a strong ability to model long-term dependencies and fewer parameters. Specifically, by inputting the intermediate parameters into the temporal convolutional model, the carbon emission forecast data of the target enterprise at the target time can be obtained.

[0035] It should be noted that the time series data of carbon emission data of oil and gas field enterprises are often the superposition of different periodic processes, such as daily changes in the short term and weekly or monthly changes in the long term. The superposition and interference of these data of different periods have brought great challenges to time series analysis. The TimesNet model can analyze time series changes from a multi-period perspective and transform the original multi-period one-dimensional time series into a two-dimensional space to achieve modeling of changes between and within cycles, which is more effective than the model that directly extracts information from the one-dimensional time series.

[0036] The embodiment of the present invention provides a carbon emission prediction method, which constructs a carbon emission vector based on the current carbon emission data and historical carbon emission data of the target enterprise; inputs the carbon emission vector into a pre-trained TimesNet model to obtain intermediate parameters; and inputs the intermediate parameters into a pre-trained time convolution model to obtain the carbon emission prediction data of the target enterprise at the target time. This technical solution effectively solves the problem of bidirectional dependency of time series by combining the TimesNet model with the time convolution model, and at the same time greatly improves the depth and breadth of the model, thereby improving the accuracy of carbon emission prediction in complex oil and gas field enterprise production scenarios.

[0037] Embodiment 2

[0038] Figure 2 This is a flowchart of a TimesNet model training process provided in Example 2 of this application. This example is optimized based on the above example. Figure 2 As shown, the method of this embodiment specifically includes the following steps:

[0039] S210: Collect carbon emission data of the target enterprise at at least two time points, and use the collected carbon emission data and the collection time points as original sample data.

[0040] Specifically, the historical carbon emission data of oil and gas field enterprises can be collected in time series with a collection frequency of days. The collected time series data sets are marked as {X_i,i=1,2,…,n}, where n is the number of collected data sets and X_i is the carbon emissions of the enterprise on the i-th day.

[0041] It should be noted that in order to ensure the training accuracy of the model, the number of sample data collected is at least 100.

[0042] S220: Perform data preprocessing on the original sample data to obtain standard sample data.

[0043] Among them, data preprocessing is used to improve the quality of sample data and make the sample data more suitable for analysis and model training. Common data preprocessing methods include data cleaning, data conversion, data integration, data reduction, etc. For example, duplicate data, abnormal data, and missing data in sample data can be processed to clean the sample data.

[0044] Optionally, the original sample data is preprocessed to obtain standard sample data, including: determining abnormal data or missing data in the original sample data; deleting the abnormal data and replacing the missing data to obtain intermediate sample data; normalizing the intermediate sample data to obtain standard sample data.

[0045] Specifically, the data set {X_i} is preprocessed, including removing abnormal data and filling missing values. The abnormal data includes but is not limited to negative numbers and zero. The missing value filling method includes but is not limited to: replacing with the average value of adjacent data.

[0046] Optionally, the intermediate parameters are input into a pre-trained time convolution model to obtain the carbon emission prediction data of the target enterprise at the target time, including: inputting the intermediate parameters into a pre-trained time convolution model to obtain the standard carbon emission prediction data of the target enterprise at the target time; and performing denormalization processing on the carbon emission prediction data to obtain the carbon emission prediction data.

[0047] Since normalization is used in the preprocessing of the data set in the above steps, the data obtained by the prediction of the TimesNet model and the time convolution model is the standard carbon emission prediction data. Therefore, it is necessary to perform denormalization on the carbon emission prediction data to obtain the carbon emission prediction data.

[0048] S230: Input the standard sample data into a first model, train the first model, and obtain a TimesNet model.

[0049] Optionally, the standard sample data is input into a first model, and the first model is trained to obtain a TimesNet model, including: based on a preset sliding window, the standard sample data is intercepted to obtain at least two sub-standard sample data; according to each of the sub-standard sample data, the first model is trained to obtain a TimesNet model.

[0050] The preset sliding window may be determined according to the collection period. Specifically, based on the size of the preset sliding window, the standard sample data is intercepted in time series to obtain sub-standard sample data.

[0051] Exemplarily, if the preset sliding window dimension is 5 and the size is 1, then the phase space reconstruction of the data set {X_i} can obtain {X_i, i=1, 2, ..., 116}, whose input is expressed as x_t=[X_t, X_(t+1), X_(t+2), X_(t+m-1)], where t=1, 2, ..., 116, and for the tth data set, the corresponding output is Y_t=x_(t+m).

[0052] Optionally, the training termination condition of the first model is reaching a preset number of training times. For example, the number of iterations of the model can be set to 500 times, and when the model reaches the training number, the model is marked.

[0053] Optionally, after inputting the standard sample data into the first model, training the first model, and obtaining the TimesNet model, the method further includes: obtaining intermediate training parameters; accordingly, the training process of the temporal convolution model includes: inputting the intermediate training parameters into the second model, training the second model, and obtaining the temporal convolution model.

[0054] The embodiment of the present invention provides a training process of a TimesNet model and a training process of a temporal convolution model, by collecting carbon emission data of a target enterprise at at least two time nodes, and using the collected carbon emission data and the collection time nodes as original sample data; performing data preprocessing on the original sample data to obtain standard sample data; inputting the standard sample data into a first model, training the first model to obtain a TimesNet model; and on this basis, training the temporal convolution model. This technical solution, by combining the TimesNet model with the temporal convolution model, effectively solves the problem of bidirectional dependency of time series, and at the same time greatly improves the depth and breadth of the model, thereby improving the accuracy of carbon emission prediction in complex oil and gas field enterprise production scenarios.

[0055] Embodiment 3

[0056] Figure 3 This is a schematic diagram of the structure of a carbon emission prediction device provided in Example 3 of the present application. Figure 3 As shown, the device comprises:

[0057] A carbon emission vector construction module 310 is used to construct a carbon emission vector according to the current carbon emission data and historical carbon emission data of the target enterprise;

[0058] An intermediate parameter acquisition module 320, used to input the carbon emission vector into a pre-trained TimesNet model to obtain intermediate parameters;

[0059] The carbon emission prediction module 330 is used to input the intermediate parameters into a pre-trained time convolution model to obtain the carbon emission prediction data of the target enterprise at the target time.

[0060] The embodiment of the present invention provides a carbon emission prediction device, which constructs a carbon emission vector based on the current carbon emission data and historical carbon emission data of the target enterprise; inputs the carbon emission vector into a pre-trained TimesNet model to obtain intermediate parameters; and inputs the intermediate parameters into a pre-trained time convolution model to obtain the carbon emission prediction data of the target enterprise at the target time. This technical solution effectively solves the problem of bidirectional dependency of time series by combining the TimesNet model and the time convolution model, and at the same time greatly improves the depth and breadth of the model, thereby improving the accuracy of carbon emission prediction in complex oil and gas field enterprise production scenarios.

[0061] Furthermore, the training process of the TimesNet model includes:

[0062] Collect carbon emission data of the target enterprise at at least two time points, and use the collected carbon emission data and the collection time points as original sample data;

[0063] Performing data preprocessing on the original sample data to obtain standard sample data;

[0064] The standard sample data is input into the first model, and the first model is trained to obtain a TimesNet model.

[0065] Further, the original sample data is preprocessed to obtain standard sample data, including:

[0066] Determining abnormal data or missing data in the original sample data;

[0067] Deleting the abnormal data and replacing the missing data to obtain intermediate sample data;

[0068] The intermediate sample data is normalized to obtain standard sample data.

[0069] Furthermore, the intermediate parameters are input into a pre-trained time convolution model to obtain the carbon emission forecast data of the target enterprise at the target time, including:

[0070] Inputting the intermediate parameters into a pre-trained time convolution model to obtain standard carbon emission forecast data of the target enterprise at the target time;

[0071] The standard carbon emission prediction data is subjected to denormalization processing to obtain carbon emission prediction data.

[0072] Furthermore, the standard sample data is input into the first model, and the first model is trained to obtain a TimesNet model, including:

[0073] Based on a preset sliding window, the standard sample data is intercepted to obtain at least two sub-standard sample data;

[0074] The first model is trained according to each of the sub-standard sample data to obtain a TimesNet model.

[0075] Furthermore, the training termination condition of the first model is reaching a preset number of training times.

[0076] Furthermore, after inputting the standard sample data into the first model and training the first model to obtain the TimesNet model, the method further includes:

[0077] Get intermediate training parameters;

[0078] Accordingly, the training process of the temporal convolutional model includes:

[0079] The intermediate training parameters are input into the second model, and the second model is trained to obtain a temporal convolution model.

[0080] A carbon emission prediction device provided in an embodiment of the present application can execute a carbon emission prediction method provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method.

[0081] Embodiment 4

[0082] Figure 4 A schematic diagram of a device 10 that can be used to implement an embodiment of the present application is shown. The device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0083] like Figure 4As shown, the device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0084] A number of components in the device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0085] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for predicting carbon emissions.

[0086] In some embodiments, the method for predicting carbon emissions may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for predicting carbon emissions described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for predicting carbon emissions in any other appropriate manner (e.g., by means of firmware).

[0087] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0088] The computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor, the functions / operations specified in the flow charts and / or block diagrams are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0089] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0090] To provide interaction with a user, the systems and techniques described herein can be implemented on a device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0091] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0092] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0093] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0094] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for predicting carbon emissions, characterized in that: The method comprises: Construct a carbon emission vector based on the current carbon emission data and historical carbon emission data of the target enterprise; Inputting the carbon emission vector into a pre-trained TimesNet model to obtain intermediate parameters; The intermediate parameters are input into a pre-trained time convolution model to obtain the carbon emission forecast data of the target enterprise at the target time.

2. The method according to claim 1, characterized in that The training process of the TimesNet model includes: Collect carbon emission data of the target enterprise at at least two time points, and use the collected carbon emission data and the collection time points as original sample data; Performing data preprocessing on the original sample data to obtain standard sample data; The standard sample data is input into the first model, and the first model is trained to obtain a TimesNet model.

3. The method according to claim 2, characterized in that The original sample data is preprocessed to obtain standard sample data, including: Determining abnormal data or missing data in the original sample data; Deleting the abnormal data and replacing the missing data to obtain intermediate sample data; The intermediate sample data is normalized to obtain standard sample data.

4. The method according to claim 3, characterized in that The intermediate parameters are input into the pre-trained time convolution model to obtain the carbon emission forecast data of the target enterprise at the target time, including: Inputting the intermediate parameters into a pre-trained time convolution model to obtain standard carbon emission forecast data of the target enterprise at the target time; The standard carbon emission prediction data is subjected to denormalization processing to obtain carbon emission prediction data.

5. The method according to claim 2, characterized in that: Inputting the standard sample data into the first model, training the first model, and obtaining a TimesNet model, including: Based on a preset sliding window, the standard sample data is intercepted to obtain at least two sub-standard sample data; The first model is trained according to each of the sub-standard sample data to obtain a TimesNet model.

6. The method according to claim 5, characterized in that The training termination condition of the first model is reaching a preset number of training times.

7. The method according to claim 2, characterized in that: After inputting the standard sample data into the first model and training the first model to obtain the TimesNet model, the method further includes: Get intermediate training parameters; Accordingly, the training process of the temporal convolutional model includes: The intermediate training parameters are input into the second model, and the second model is trained to obtain a temporal convolution model.

8. A carbon emission prediction device, characterized in that: The device comprises: A carbon emission vector construction module is used to construct a carbon emission vector based on the current carbon emission data and historical carbon emission data of the target enterprise; An intermediate parameter acquisition module, used for inputting the carbon emission vector into a pre-trained TimesNet model to obtain intermediate parameters; The carbon emission prediction module is used to input the intermediate parameters into a pre-trained time convolution model to obtain the carbon emission prediction data of the target enterprise at the target time.

9. An electronic device, characterized in that: The device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the carbon emission prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the carbon emission prediction method according to any one of claims 1 to 7 when executed.

Images