Carbon emission monitoring method, device and equipment and storage medium
By obtaining electricity load data in real time and using convolutional neural networks and category attention mechanisms, the carbon emissions of industrial users are calculated, which solves the problem of inaccurate user-side carbon emission monitoring in traditional methods, real-time and high-precision carbon Emission monitoring.
Patent Information
- Application Number
- CN202411150578.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-11-15
AI Technical Summary
Traditional carbon emission estimation lacks user-side methods, especially industrial users’ carbon emission monitoring is not accurate enough, making it difficult to support emission reduction efforts.
By obtaining the user's electricity load data in real time, using convolutional neural networks for feature extraction and category attention mechanism calculation, combined with activation function mapping, the working status and carbon emissions of the core carbon emission equipment are accurately calculated.
Real-time monitoring and accurate estimation of user carbon emissions is realized, and the accuracy of carbon emission monitoring is improved, and it is more real-time and accurate than traditional methods.
Smart Images

Figure CN118964946A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of carbon emission monitoring, and in particular to a carbon emission monitoring method, device, equipment and storage medium. Background Art
[0002] With the increasing human activities, the concentration of carbon dioxide and other greenhouse gases in the atmosphere continues to rise, leading to a continuous rise in global temperatures, triggering a series of serious consequences such as extreme weather, rising sea levels, and ecosystem destruction. The estimation of carbon emissions is the basis for achieving environmental goals such as mitigating climate change and sustainable development of society. It can effectively promote the transformation of a low-carbon economy and improve economic efficiency. Studying the estimation of carbon emissions has great practical significance for reducing carbon emissions. Traditional carbon emission estimation is carried out from the power generation side and the power grid side, and lacks estimation methods on the user side. On the user side, industrial users' carbon emissions account for a large share and are the focus of attention among carbon emission users. Therefore, accurately estimating the carbon emissions of industrial users plays an important role in supporting emission reduction efforts. Summary of the invention
[0003] The present application provides a carbon emission monitoring method, device, equipment and storage medium for improving the accuracy of carbon emission monitoring.
[0004] In view of this, the first aspect of the present application provides a carbon emission monitoring method, comprising:
[0005] Obtain users' electricity load data in real time, and obtain the carbon emission intensity of core carbon emission equipment under different working conditions;
[0006] Extracting features from the power load data using a convolutional neural network to obtain a feature graph;
[0007] Calculating a category attention score of the feature map based on a category attention mechanism, and performing weighted summation on the feature map using the category attention score to obtain a category feature vector;
[0008] Mapping the category feature vector through an activation function to obtain the working status of the user's core carbon emission equipment;
[0009] The user's carbon emissions are calculated based on the working status of the core carbon emission equipment and the corresponding carbon emission intensity.
[0010] Optionally, the calculation formula for the category attention score of the feature map is:
[0011]
[0012] In the formula, is the category attention score of the j-th position of feature map z about category i, iϵ[1,2,…,c], c is the number of categories; m i is the network parameter; T is the transposition operation; z k is the value of the kth position of the feature map; l is the size of the feature map.
[0013] Optionally, the mapping formula of the category feature vector is:
[0014]
[0015] In the formula, a c is the category feature vector of the cth category; is the mapping result.
[0016] Optionally, the calculation formula for the user's carbon emissions is:
[0017]
[0018] Where, CE is carbon emissions; EF is i,j is the carbon emission intensity of the core carbon emission equipment in working state i in time interval j; T is the evaluation period, b is the time interval; m is the number of core carbon emission equipment in working state i.
[0019] A second aspect of the present application provides a carbon emission monitoring device, comprising:
[0020] An acquisition unit is used to acquire the user's electricity load data in real time and to acquire the carbon emission intensity of the core carbon emission equipment under different working conditions;
[0021] A feature extraction unit, used to extract features from the power load data through a convolutional neural network to obtain a feature graph;
[0022] A first calculation unit, configured to calculate a category attention score of the feature map based on a category attention mechanism, and perform weighted summation of the feature map by the category attention score to obtain a category feature vector;
[0023] A mapping unit, used for mapping the category feature vector through an activation function to obtain the working status of the user's core carbon emission equipment;
[0024] The second calculation unit is used to calculate the carbon emissions of the user according to the working status of the core carbon emission equipment and the corresponding carbon emission intensity.
[0025] Optionally, the calculation formula for the category attention score of the feature map is:
[0026]
[0027] In the formula, is the category attention score of the j-th position of feature map z about category i, iϵ[1,2,…,c], c is the number of categories; m i is the network parameter; T is the transposition operation; z k is the value of the kth position of the feature map; l is the size of the feature map.
[0028] Optionally, the mapping formula of the category feature vector is:
[0029]
[0030] In the formula, a c is the category feature vector of the cth category; is the mapping result.
[0031] Optionally, the calculation formula for the user's carbon emissions is:
[0032]
[0033] Where, CE is carbon emissions; EF is i,j is the carbon emission intensity of the core carbon emission equipment in working state i in time interval j; T is the evaluation period, b is the time interval; m is the number of core carbon emission equipment in working state i.
[0034] A third aspect of the present application provides an electronic device, the device comprising a processor and a memory;
[0035] The memory is used to store program code and transmit the program code to the processor;
[0036] The processor is used to execute any one of the carbon emission monitoring methods described in the first aspect according to the instructions in the program code.
[0037] A fourth aspect of the present application provides a computer-readable storage medium, which is used to store program code. When the program code is executed by a processor, it implements the carbon emission monitoring method described in any one of the first aspects.
[0038] It can be seen from the above technical solutions that this application has the following advantages:
[0039] The present application provides a carbon emission monitoring method, including: obtaining the user's electricity load data in real time, and obtaining the carbon emission intensity of core carbon emission equipment under different working conditions; extracting features of the electricity load data through a convolutional neural network to obtain a feature map; calculating the category attention score of the feature map based on the category attention mechanism, and performing weighted summation of the feature map through the category attention score to obtain a category feature vector; mapping the category feature vector through an activation function to obtain the working status of the user's core carbon emission equipment; and calculating the user's carbon emissions based on the working status of the core carbon emission equipment and the corresponding carbon emission intensity.
[0040] This application combines the user's electricity load data with the equipment's carbon emission intensity to achieve user carbon emission monitoring. Compared with the traditional full life cycle method and macro method, it can achieve real-time carbon emission monitoring. This application uses a convolutional neural network to predict the working status of the user's core carbon emission equipment, and combines the category attention mechanism for feature extraction to enhance feature representation, which can achieve more accurate identification of the working status of the core carbon emission equipment, thereby improving the accuracy of carbon emission monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art 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 paying creative work.
[0042] Figure 1 A schematic diagram of a process of a carbon emission monitoring method provided in an embodiment of the present application;
[0043] Figure 2 A schematic diagram of the structure of a convolutional neural network provided in an embodiment of the present application;
[0044] Figure 3 A structural schematic diagram of a carbon emission monitoring device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0045] 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 are within the scope of protection of this application.
[0046] For easier understanding, please refer to Figure 1, the present application embodiment provides a carbon emission monitoring method, comprising:
[0047] Step 110: Obtain the user's electricity load data in real time, and obtain the carbon emission intensity of the core carbon emission equipment under different working conditions.
[0048] The user's electricity load data can be obtained in real time through the electricity meter to obtain the electricity load sequence X, and the user's core carbon emission equipment can be counted at the same time. Taking the glass factory as an example, the core equipment of the glass factory includes electric melting furnaces and electric quenching furnaces. The hourly carbon emissions caused by the electric melting furnace and the electric quenching furnace under different working conditions can be calculated respectively, and the carbon emission intensity of the core carbon emission equipment under different working conditions can be obtained.
[0049] Step 120: extract features from the power load data using a convolutional neural network to obtain a feature graph.
[0050] The convolutional neural network is used to extract the features of the collected power load sequence and obtain a feature map with a length of l and a number of channels d. Figure 2 , the convolutional neural network in this application includes 8 convolutional layers. Taking the first convolutional layer as an example, "7conv,32, / 2" means that the one-dimensional convolution kernel length used by the convolutional layer is 7, the number of feature channels output is 32, and the maximum pooling of 2 times is performed after the convolutional layer. Since the input sequence X is long, the first layer of the neural network uses a longer convolution kernel, which can reduce the number of calculations. After maximum pooling, the feature size is reduced, so subsequent layers can use smaller convolution kernels. From the perspective of receptive field, the receptive field provided by three convolutional layers with a convolution kernel length of 3 is the same as that of a convolutional layer with a convolution kernel length of 7, but can provide more nonlinearity.
[0051] Step 130: Calculate the category attention score of the feature map based on the category attention mechanism, perform weighted summation on the feature map using the category attention score to obtain a category feature vector.
[0052] Based on the category attention mechanism, the attention score of each state label on the feature map is calculated, which contains multiple binary classifiers, and finally the state result corresponding to the device is obtained. The calculation formula of the category attention score of the feature map is:
[0053]
[0054] In the formula, is the category attention score of the j-th position of feature map z about category i, iϵ[1,2,…,c], c is the number of categories; m i is the network parameter, obtained by training the network with training data; T is the transposition operation; z k is the value of the kth position of the feature map; l is the size of the feature map.
[0055] Then, the category attention score As the weight, the feature map is weighted and summed to calculate the category feature vector of the i-th category:
[0056]
[0057] In the formula, a i is the category feature vector of the i-th category.
[0058] Step 140: Map the category feature vector through an activation function to obtain the working status of the user's core carbon emission equipment.
[0059] The category feature vector is mapped through the activation function to obtain the probability of each working state of the user's core carbon emission equipment, and finally the working state with the maximum probability is output as the working state of the user's core carbon emission equipment.
[0060] The mapping formula of the category feature vector is:
[0061]
[0062] In the formula, a c is the category feature vector of the cth category; is the probability of the cth category (i.e., the working status category); sigmoid( ) is the activation function, which limits the output range to between 0 and 1:
[0063]
[0064] The working state corresponding to the category with the maximum probability is finally output as the working state of the user's core carbon emission equipment.
[0065] Step 150: Calculate the user's carbon emissions based on the working status of the core carbon emission equipment and the corresponding carbon emission intensity.
[0066] For a user with m core carbon emission devices in different states, the carbon emission in a given evaluation period T is divided into b estimation time intervals. The carbon emission intensity of each core carbon emission device in each working state can be used for estimation. The formula is as follows:
[0067]
[0068] Where, CE is carbon emissions; EF is i,j It is the carbon emission intensity of the core carbon emission equipment in working state i in time interval j.
[0069] This application abandons the traditional statistical method of calculating carbon emissions and instead considers the real-time monitoring and measurement of carbon emissions; it locates the user's carbon emissions to a specific device, identifies the device's operating status, and combines the device's carbon emission intensity to accurately estimate the user's carbon emissions.
[0070] This application combines the user's electricity load data with the equipment's carbon emission intensity to achieve user carbon emission monitoring. Compared with the traditional full life cycle method and macro method, it can achieve real-time carbon emission monitoring. This application uses a convolutional neural network to predict the working status of the user's core carbon emission equipment, and combines the category attention mechanism for feature extraction to enhance feature representation, which can achieve more accurate identification of the working status of the core carbon emission equipment, thereby improving the accuracy of carbon emission monitoring.
[0071] The above is an embodiment of a carbon emission monitoring method provided by the present application, and the following is an embodiment of a carbon emission monitoring device provided by the present application.
[0072] Please refer to Figure 3 , a carbon emission monitoring device provided in an embodiment of the present application includes:
[0073] An acquisition unit is used to acquire the user's electricity load data in real time and to acquire the carbon emission intensity of the core carbon emission equipment under different working conditions;
[0074] A feature extraction unit, used for extracting features from the power load data through a convolutional neural network to obtain a feature graph;
[0075] A first calculation unit is used to calculate a category attention score of the feature map based on a category attention mechanism, and perform weighted summation of the feature map through the category attention score to obtain a category feature vector;
[0076] A mapping unit, used for mapping the category feature vector through an activation function to obtain the working status of the user's core carbon emission equipment;
[0077] The second calculation unit is used to calculate the carbon emissions of the user according to the working status of the core carbon emission equipment and the corresponding carbon emission intensity.
[0078] As a further improvement, the calculation formula of the category attention score of the feature map is:
[0079]
[0080] In the formula, is the category attention score of the j-th position of feature map z about category i, iϵ[1,2,…,c], c is the number of categories; m i is the network parameter; T is the transposition operation; z kis the value of the kth position of the feature map; l is the size of the feature map.
[0081] As a further improvement, the mapping formula of the category feature vector is:
[0082]
[0083] In the formula, a c is the category feature vector of the cth category; is the mapping result.
[0084] As a further improvement, the user's carbon emissions are calculated as follows:
[0085]
[0086] Where, CE is carbon emissions; EF is i,j is the carbon emission intensity of the core carbon emission equipment in working state i in time interval j; T is the evaluation period, b is the time interval; m is the number of core carbon emission equipment in working state i.
[0087] This application combines the user's electricity load data with the equipment's carbon emission intensity to achieve user carbon emission monitoring. Compared with the traditional full life cycle method and macro method, it can achieve real-time carbon emission monitoring. This application uses a convolutional neural network to predict the working status of the user's core carbon emission equipment, and combines the category attention mechanism for feature extraction to enhance feature representation, which can achieve more accurate identification of the working status of the core carbon emission equipment, thereby improving the accuracy of carbon emission monitoring.
[0088] The embodiment of the present application also provides an electronic device, the device comprising a processor and a memory;
[0089] The memory is used to store the program code and transmit the program code to the processor;
[0090] The processor is used to execute the carbon emission monitoring method in the aforementioned method embodiment according to the instructions in the program code.
[0091] An embodiment of the present application also provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code, and when the program code is executed by a processor, the carbon emission monitoring method in the aforementioned method embodiment is implemented.
[0092] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0093] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes 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.
[0094] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0095] In the several 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 only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0096] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0097] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0098] 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, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions for executing all or part of the steps of the method described in each embodiment of the present application through a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.
[0099] As described above, 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A carbon emission monitoring method, characterized in that: include: Obtain users' electricity load data in real time, and obtain the carbon emission intensity of core carbon emission equipment under different working conditions; Extracting features from the power load data using a convolutional neural network to obtain a feature graph; Calculating a category attention score of the feature map based on a category attention mechanism, and performing weighted summation on the feature map using the category attention score to obtain a category feature vector; Mapping the category feature vector through an activation function to obtain the working status of the user's core carbon emission equipment; The user's carbon emissions are calculated based on the working status of the core carbon emission equipment and the corresponding carbon emission intensity.
2. The carbon emission monitoring method according to claim 1, characterized in that: The calculation formula for the category attention score of the feature map is: In the formula, is the category attention score of the j-th position of the feature map z about category i, iϵ[1,2,…,c], c is the number of categories; m i is the network parameter; T is the transposition operation; z k is the value of the kth position of the feature map; l is the size of the feature map.
3. The carbon emission monitoring method according to claim 2, characterized in that: The mapping formula of the category feature vector is: In the formula, a c is the category feature vector of the cth category; is the mapping result.
4. The carbon emission monitoring method according to claim 1, characterized in that: The calculation formula for the user's carbon emissions is: Where, CE is carbon emissions; EF is i,j is the carbon emission intensity of the core carbon emission equipment in working state i in time interval j; T is the evaluation period, b is the time interval; m is the number of core carbon emission equipment in working state i.
5. A carbon emission monitoring device, characterized in that: include: An acquisition unit is used to acquire the user's electricity load data in real time and to acquire the carbon emission intensity of the core carbon emission equipment under different working conditions; A feature extraction unit, used to extract features from the power load data through a convolutional neural network to obtain a feature graph; A first calculation unit, configured to calculate a category attention score of the feature map based on a category attention mechanism, and perform weighted summation of the feature map by the category attention score to obtain a category feature vector; A mapping unit, used for mapping the category feature vector through an activation function to obtain the working status of the user's core carbon emission equipment; The second calculation unit is used to calculate the carbon emissions of the user according to the working status of the core carbon emission equipment and the corresponding carbon emission intensity.
6. The carbon emission monitoring device according to claim 5, characterized in that: The calculation formula for the category attention score of the feature map is: In the formula, is the category attention score of the j-th position of the feature map z about category i, iϵ[1,2,…,c], c is the number of categories; m i is the network parameter; T is the transposition operation; z k is the value of the kth position of the feature map; l is the size of the feature map.
7. The carbon emission monitoring device according to claim 6, characterized in that: The mapping formula of the category feature vector is: In the formula, a c is the category feature vector of the cth category; is the mapping result.
8. The carbon emission monitoring device according to claim 5, characterized in that: The calculation formula for the user's carbon emissions is: Where, CE is carbon emissions; EF is i,j is the carbon emission intensity of the core carbon emission equipment in working state i in time interval j; T is the evaluation period, b is the time interval; m is the number of core carbon emission equipment in working state i.
9. An electronic device, characterized in that: The device comprises a processor and a memory; The memory is used to store program codes and transmit the program codes to the processor; The processor is used to execute the carbon emission monitoring method according to any one of claims 1 to 4 according to the instructions in the program code.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and when the program code is executed by a processor, the carbon emission monitoring method according to any one of claims 1 to 4 is implemented.
Citation Information
Patent Citations
New energy grid-connected system output prediction method considering privacy protection
CN117411078A
Industrial user carbon emission estimation method and device based on ResNeSt
CN117574229A
Lightweight intrusion detection system based on residual attention mechanism
CN117852028A
Model training method, equipment operation state identification method and carbon emission real-time monitoring method
CN118520354A
Automatic air recirculation systems for vehicles
US20210374412A1
