Carbon emission monitoring method, device, equipment, medium and computer program product

Abstract

The application relates to a carbon emission monitoring method, device, equipment, medium and computer program product. The method comprises the following steps: obtaining target power load data of an electric device in a target object in a preset time range, and obtaining a target device state recognition model, wherein the target device state recognition model is obtained according to target historical power load data and target device state information corresponding to the target historical power load data; inputting the target power load data into the target device state recognition model to obtain a target device state corresponding to the target power load data, and determining a target carbon emission intensity of the target electric device according to the target device state; and determining a total carbon emission amount of the target object in the preset time range according to the target carbon emission intensity. The method can ensure the accuracy and reliability of the total carbon emission amount obtained when the running state of the device changes, thereby improving the monitoring effect of the total carbon emission amount of the enterprise.

Description

Technical Field

[0001] This application relates to the field of energy monitoring technology, and in particular to a carbon emission monitoring method, apparatus, equipment, medium, and computer program product. Background Technology

[0002] With global warming and the intensifying greenhouse effect, it is necessary to strictly control the total carbon emissions of enterprises and other entities to strengthen environmental protection. A company's total carbon emissions represent all carbon emissions generated by its production activities within a certain period and are also an important indicator for measuring a company's environmental performance.

[0003] Traditional methods for calculating a company's total carbon emissions first obtain the target company's historical electricity load data for the past month, as well as the carbon emission factors of various electrical equipment used by the company. Then, based on the historical electricity load data and the carbon emission factors of the electrical equipment, the target company's total carbon emissions for the past month are determined. The carbon emission factor represents the amount of carbon emissions generated per unit of electricity consumed by the electrical equipment.

[0004] However, traditional technologies do not take into account the operating status of different equipment when calculating carbon emissions, resulting in low accuracy and reliability of existing technologies in calculating carbon emissions, and thus poor monitoring of the total carbon emissions of enterprises. Summary of the Invention

[0005] Therefore, it is necessary to provide a carbon emission monitoring method, device, equipment, medium, and computer program product that can improve the effectiveness of total carbon emission monitoring in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a method for monitoring carbon emissions. The method includes:

[0007] Obtain target power load data of electrical equipment in the target object within a preset time range, and obtain target equipment status recognition model. The target status recognition model is trained based on the target historical power load data and the target equipment status information corresponding to the target historical power load data.

[0008] Input the target power load data into the target equipment status identification model to obtain the target equipment status corresponding to the target power load data, and determine the target carbon emission intensity of the target power-consuming equipment based on the target equipment status;

[0009] Based on the target carbon emission intensity, determine the total carbon emissions of the target object within a preset time range.

[0010] In one embodiment, determining the target carbon emission intensity of the target electrical equipment based on the target equipment status includes:

[0011] Based on the target equipment status, the target carbon emission intensity corresponding to the target equipment status is determined in a preset mapping table between equipment status and equipment carbon emission intensity.

[0012] In one embodiment, the method further includes:

[0013] Obtain historical power load data of electrical equipment within a historical time range;

[0014] The system checks for missing data in historical power load data. If missing data is found, it fills in the missing data to obtain updated historical power load data.

[0015] Obtain the target device status recognition model, including:

[0016] A target equipment status recognition model is trained based on the updated historical power load data and the target equipment status information corresponding to the target historical power load data.

[0017] In one embodiment, missing data is filled in to obtain updated historical power load data, including:

[0018] The historical time range is divided into several consecutive time periods. Missing data is supplemented based on the historical power load data in each time period to obtain updated historical power load data.

[0019] In one embodiment, missing data is supplemented based on historical power load data for each time period to obtain updated historical power load data, including:

[0020] Determine the target time period where the missing data is located, and determine the historical power load data of the two time periods adjacent to the target time period and their corresponding preset weights;

[0021] Missing data is supplemented based on historical power load data from two time periods adjacent to the target time period and their corresponding preset weights.

[0022] In one embodiment, determining the total carbon emissions of a target object within a preset time range based on the target carbon emission intensity includes:

[0023] The direct carbon emissions of the target entity are determined based on the target carbon emission intensity.

[0024] The indirect carbon emissions of the target object are determined based on the marginal carbon emission factor of the target object within a preset time range;

[0025] The total carbon emissions of the target entity within a preset time frame are determined based on direct and indirect carbon emissions.

[0026] Secondly, this application also provides a carbon emission monitoring device. The device includes:

[0027] The data acquisition module is used to acquire target power load data and target equipment status recognition model of electrical equipment in the target object within a preset time range. The target status recognition model is trained based on the target historical power load data and the target equipment status information corresponding to the target historical power load data.

[0028] The carbon emission intensity determination module is used to input the target power load data into the target equipment status identification model, obtain the target equipment status corresponding to the target power load data, and determine the target carbon emission intensity of the target power-consuming equipment based on the target equipment status.

[0029] The carbon emission calculation module is used to determine the total carbon emissions of a target object within a preset time range based on the target carbon emission intensity.

[0030] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0031] Obtain target power load data of electrical equipment in the target object within a preset time range, and obtain target equipment status recognition model. The target status recognition model is trained based on the target historical power load data and the target equipment status information corresponding to the target historical power load data.

[0032] Input the target power load data into the target equipment status identification model to obtain the target equipment status corresponding to the target power load data, and determine the target carbon emission intensity of the target power-consuming equipment based on the target equipment status;

[0033] Based on the target carbon emission intensity, determine the total carbon emissions of the target object within a preset time range.

[0034] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0035] Obtain target power load data of electrical equipment in the target object within a preset time range, and obtain target equipment status recognition model. The target status recognition model is trained based on the target historical power load data and the target equipment status information corresponding to the target historical power load data.

[0036] Input the target power load data into the target equipment status identification model to obtain the target equipment status corresponding to the target power load data, and determine the target carbon emission intensity of the target power-consuming equipment based on the target equipment status;

[0037] Based on the target carbon emission intensity, determine the total carbon emissions of the target object within a preset time range.

[0038] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0039] Obtain target power load data of electrical equipment in the target object within a preset time range, and obtain target equipment status recognition model. The target status recognition model is trained based on the target historical power load data and the target equipment status information corresponding to the target historical power load data.

[0040] Input the target power load data into the target equipment status identification model to obtain the target equipment status corresponding to the target power load data, and determine the target carbon emission intensity of the target power-consuming equipment based on the target equipment status;

[0041] Based on the target carbon emission intensity, determine the total carbon emissions of the target object within a preset time range.

[0042] The aforementioned carbon emission monitoring methods, devices, equipment, media, and computer programs acquire target power load data of electrical equipment within a preset time range and obtain a target equipment status identification model. This model is trained based on historical target power load data and the corresponding target equipment status information. The target power load data is input into the target equipment status identification model to obtain the target equipment status corresponding to the power load data. The target carbon emission intensity of the target electrical equipment is then determined based on the target equipment status. Finally, the total carbon emissions of the target object within the preset time range are determined based on the target carbon emission intensity. This application employs the above method, first determining the target equipment status based on the target power load data and the target equipment status identification model, and then determining the target carbon emission intensity based on the target equipment status. This ensures the accuracy and reliability of the target carbon emission intensity obtained when the equipment's operating status changes, thereby ensuring the accuracy and reliability of the total carbon emissions obtained based on the target carbon emission intensity, and ultimately improving the monitoring effect of the enterprise's total carbon emissions. Attached Figure Description

[0043] Figure 1 This is a diagram illustrating the application environment of a carbon emission monitoring method in one embodiment.

[0044] Figure 2 This is a flowchart of a carbon emission monitoring method in one embodiment;

[0045] Figure 3 This is a flowchart illustrating how missing data is supplemented to obtain updated historical power load data in one embodiment.

[0046] Figure 4 This is a flowchart of a method for filling in missing data in one embodiment;

[0047] Figure 5 This is a flowchart for determining the total carbon emissions of a target object within a preset time range, as described in one embodiment.

[0048] Figure 6 This is a structural block diagram of a carbon emission monitoring device in one embodiment;

[0049] Figure 7 This is an internal structural diagram of a computer device in one embodiment;

[0050] Figure 8 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0052] The carbon emission monitoring method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on the cloud or other network servers. Terminal 102 is an electrical device within a target object such as an enterprise or factory; in this embodiment, terminal 102 can be, but is not limited to, various processing equipment, monitoring equipment, smart air conditioners, etc. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0053] In one embodiment, such as Figure 2 As shown, this method is applied to Figure 1 Taking a terminal as an example, it can be understood that this method can also be applied to a server, and to a system that includes both a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0054] Step 202: Obtain target power load data of electrical equipment in the target object within a preset time range, and obtain target equipment status recognition model. The target status recognition model is trained based on the target historical power load data and the target equipment status information corresponding to the target historical power load data.

[0055] The preset time range is the pre-defined period during which the total carbon emissions data of the target object are monitored. For example, the preset time range could be from the current moment to 30 days ago, or from the current moment to 7 days ago. The target object is the object whose total carbon emissions data is being measured; the target object can be an enterprise, factory, etc. The target state recognition model is used to identify the operating state of electrical equipment within the target object. Since different operating states of the same electrical equipment correspond to different power load data, and different power load data correspond to different carbon emission intensities (carbon emission intensity representing the amount of carbon dioxide emitted per unit of power load), to obtain highly accurate total carbon emissions data, the model needs to be trained based on the target's historical power load data and the corresponding target equipment state information to obtain the target state recognition model for each electrical device. Power load data is the total amount of electrical energy consumed by electrical equipment within a certain time period, usually expressed as electricity consumption per unit time (e.g., kilowatt-hours or megawatt-hours). Target historical power load data is the power load data measured for the target equipment within a historical time period. Target equipment state information is the operating state information of the target equipment, including status information such as currently running or waiting to run. For example, when the power load data of the air conditioning equipment is 1kW / h, the corresponding operating status of the air conditioning equipment is that it is running and in cooling mode; when the power load data of the air conditioning equipment is 0.5kW / h, the corresponding operating status of the air conditioning equipment is that it is running and in dehumidification mode.

[0056] For example, when acquiring the total carbon emissions data of a steel plant within the last 30 days, the system first acquires the target equipment status identification models corresponding to the electrical equipment within the steel plant. These include, for instance, equipment status identification models for electric arc furnaces used for smelting and melting scrap steel and iron, power conversion equipment used to convert high-voltage electrical energy in the power system into low-voltage controllable electrical energy, handling equipment used to transport or transfer steel, raw materials, and finished products, and air conditioning equipment used to control the indoor temperature of the workshop. These equipment status identification models can be continuously iterated and updated based on real-time monitored power load data and the corresponding equipment operating status information, thereby improving the accuracy and effectiveness of the equipment status identification models.

[0057] The target equipment status recognition model can be trained based on a combined algorithm of convolutional neural networks and bidirectional long short-term memory (LSTM). The convolutional neural network algorithm is used to process temporally related sequential data, corresponding to the historical power load data in this application. This algorithm extracts spatial and temporal features from the historical power load data using convolutional and pooling layers. The bidirectional LSTM algorithm adds a reversed LSTM layer to the traditional LSTM network, enabling it to learn and remember information from both past and future contexts simultaneously, thereby better capturing long-term dependencies in the historical power load data. Specifically, for each electrical device, a unique identification model is constructed. Using historical power load data within a historical time range as input, three one-dimensional convolutional neural network layers are used to extract salient features from the original historical power load data and corresponding device operating status information, such as power frequency, voltage level, and power consumption variation. A recognition model based on bidirectional long short-term memory algorithm is used to extract forward and backward information from the salient feature set output by the one-dimensional convolutional neural network. Three bidirectional long short-term memory layers are used to learn the deep relationship between historical power load data and device operating status information. Finally, each identification model will output the identification result corresponding to different devices. That is, the target device status identification model will output the target operating status information of the target electrical device based on the input real-time power load data.

[0058] Step 204: Input the target power load data into the target equipment status identification model to obtain the target equipment status corresponding to the target power load data, and determine the target carbon emission intensity of the target power-consuming equipment based on the target equipment status.

[0059] The target power load data refers to the power consumption data of the target electrical equipment at the current moment. The target carbon emission intensity is used to represent the amount of carbon dioxide emitted by the target electrical equipment when consuming a unit of power load under the target equipment condition.

[0060] For example, taking a carbon emission monitoring cycle of 5 minutes within a preset time range as an example, the target power load data is the power consumption of the target electrical equipment within 5 minutes. After obtaining the power load data of an air conditioner within a certain 5-minute period within the preset time range, the power load data of the air conditioner is input into the corresponding equipment status recognition model for processing to obtain the equipment status corresponding to the power load data of the air conditioner. For example, if the target power load data input into the corresponding equipment status recognition model of the air conditioner is 1 kW·h, after processing by the equipment status recognition model, the obtained equipment status is cooling status. Then, the carbon emission intensity of the air conditioner at this time is determined according to the cooling status of the air conditioner. For example, when the air conditioner is in cooling status, the corresponding carbon emission intensity is 0.2 kg / kW·h.

[0061] Step 206: Determine the total carbon emissions of the target object within a preset time range based on the target carbon emission intensity.

[0062] For example, when calculating the total carbon emissions of a target electrical device over the past 30 days, the monitoring period can be divided into several continuous monitoring periods, with each period lasting 5 minutes. Target power load data for each monitoring period can be acquired, and this data can be input into the target device status identification model to obtain the corresponding target device status. The target carbon emission intensity can then be determined based on the target device status, allowing the carbon emission amount for each monitoring period to be determined accordingly. The carbon emission amounts for each monitoring period can then be summed to obtain the total carbon emissions of the target device over the past 30 days. Finally, the total carbon emissions of all target devices can be summed to obtain the total carbon emissions of the target object over the past 30 days.

[0063] In the above-mentioned carbon emission monitoring method, the target equipment status is first determined based on the target power load data and the target equipment status identification model. Then, the target carbon emission intensity is determined based on the target equipment status. This ensures the accuracy and reliability of the target carbon emission intensity obtained when the operating status of the equipment changes, thereby ensuring the accuracy and reliability of the total carbon emissions obtained based on the target carbon emission intensity. This, in turn, improves the monitoring effect of the total carbon emissions of enterprises.

[0064] In one embodiment, determining the target carbon emission intensity of a target electrical device based on the target device status includes: determining the target carbon emission intensity corresponding to the target device status in a preset mapping table between device status and device carbon emission intensity.

[0065] The preset mapping table between equipment status and equipment carbon emission intensity is based on historical experience. As mentioned above, the carbon emission intensity of electrical equipment is different when the equipment is in different operating states. In order to ensure the accuracy of the carbon emission calculation results of the target electrical equipment, it is necessary to look up the target carbon emission intensity corresponding to the target equipment status in the mapping table corresponding to the target equipment status.

[0066] For example, when the device status corresponding to the air conditioner is cooling, the target carbon emission intensity corresponding to the cooling status is determined to be 0.2 kg / kW·h in the preset mapping table of device status and device carbon emission intensity of the air conditioner.

[0067] In this embodiment, a preset mapping table between equipment status and equipment carbon emission intensity helps to determine the target carbon emission intensity based on the target equipment status, thereby ensuring the accuracy of the carbon emission calculation results of the target electrical equipment.

[0068] In one embodiment, such as Figure 3 As shown, the method also includes:

[0069] Step 302: Obtain historical power load data of electrical equipment within the historical time range.

[0070] Among them, the historical time range is the past time range relative to the current moment, and the historical power load data is the power consumption data generated within the past time range.

[0071] For example, obtain historical power load data for the target object's electrical equipment from the previous two years. By acquiring and analyzing historical power load data, patterns can be identified. These patterns can then be used to perform outlier detection, replacement, and missing data completion, thereby improving the accuracy of the obtained power load data.

[0072] Step 304: Check if there is any missing data in the historical power load data. If there is any missing data in the historical power load data, fill in the missing data to obtain the updated historical power load data.

[0073] One issue is that when the data acquisition equipment malfunctions, the power load data of the electrical equipment may be lost. In order to ensure the training effect of the target equipment status recognition model, the missing data needs to be supplemented.

[0074] For example, when there is missing data in the historical power load data of the target object, the missing data is filled in based on the remaining historical power load data within the historical time range to obtain updated historical power load data.

[0075] Step 306: Train the target equipment status recognition model based on the updated historical power load data and the target equipment status information corresponding to the target historical power load data.

[0076] For example, after filling in the missing data, the updated historical power load data is obtained. Then, the updated historical power load data and the target equipment status information corresponding to the target historical power load data are input into the model corresponding to the target electrical equipment for training, so as to obtain the target equipment status recognition model.

[0077] In this embodiment, missing data is filled in before model training to ensure that the model can use the complete dataset during training, thereby ensuring the effectiveness of the target device status recognition model.

[0078] In one embodiment, filling in missing data to obtain updated historical power load data includes: dividing the historical time range into several consecutive time periods, filling in missing data based on the historical power load data in each time period, and obtaining updated historical power load data.

[0079] For example, based on the foregoing, taking a 5-minute monitoring cycle as an example, the historical time range is divided into several consecutive monitoring cycles, that is, the historical time range is divided into several consecutive time periods, each with a length of 5 minutes. Since historical power load data has a certain continuity or trend, the correlation between data can be obtained by analyzing historical power load data, so that after supplementing missing data based on historical power load data, more accurate updated historical power load data can be obtained.

[0080] In this embodiment, supplementing missing data based on historical power load data helps to obtain more accurate updated historical power load data, thereby ensuring the training effect of the subsequent target equipment status recognition model.

[0081] In one embodiment, such as Figure 4 As shown, missing data is supplemented based on historical power load data for each time period to obtain updated historical power load data, including:

[0082] Step 402: Determine the target time period in which the missing data is located, and determine the historical power load data of the two time periods adjacent to the target time period and their corresponding preset weights.

[0083] The target time period is the time period containing the missing data, representing the missing historical power load data for that historical time period. The two adjacent time periods are the preceding and following historical time periods, respectively. Preset weights are used to characterize the importance of the historical power load data in the two time periods adjacent to the target time period. Since historical power load data tends to be continuous or exhibit certain trends, using the historical power load data from the two time periods adjacent to the target time period as a reference further improves the accuracy of the updated historical power load data.

[0084] For example, if the target time period in which the missing data is located is the 23rd time period, then the historical power load data corresponding to the 22nd and 24th time periods and their corresponding preset weights are obtained respectively. For example, the weight of the historical power load data in the previous historical time period in the target time period is preset to be 50%, and the weight of the historical power load data in the next historical time period in the target time period is also preset to be 50%.

[0085] Step 404: Fill in the missing data based on the historical power load data of the two time periods adjacent to the target time period and their corresponding preset weights.

[0086] For example, as can be seen from the foregoing, when supplementing missing data, the historical power load data of the previous historical time period located in the target time period is multiplied by 50% to obtain a first value, and the historical power load data of the next historical time period located in the target time period is multiplied by 50% to obtain a second value. The first value and the second value are added together to obtain the value corresponding to the missing data, thereby realizing the supplementation of missing data.

[0087] In this embodiment, missing data is supplemented based on the historical power load data of two time periods adjacent to the target time period and their corresponding preset weights, which helps to ensure the accuracy of the updated historical power load data.

[0088] In one embodiment, such as Figure 5 As shown, based on the target carbon emission intensity, the total carbon emissions of the target object within a preset time range are determined, including:

[0089] Step 502: Determine the direct carbon emissions of the target object based on the target carbon emission intensity.

[0090] Direct carbon emissions are the carbon emissions directly generated by the target entity during its production activities.

[0091] For example, the direct carbon emissions of the target object can be calculated using the following formula:

[0092]

[0093] Where, α x d represents the direct carbon emissions of the target object within a preset time range x; d represents the total number of electrical devices within the target object. For electrical equipment i in state S i How many kilograms of carbon dioxide will be emitted for every kilowatt-hour of electricity consumed?

[0094] Specifically, taking a monitoring cycle of 5 minutes and a preset time range of 30 days as an example, the target historical power load data corresponding to each monitoring cycle within the preset time range is input into the corresponding target equipment status identification model to obtain the target equipment status corresponding to the target historical power load data. Then, the target carbon emission intensity is determined according to the target equipment status. The target carbon emission intensity is then multiplied by the monitoring cycle to obtain the direct carbon emissions of the target electrical equipment within the monitoring cycle. Finally, the direct carbon emissions of all electrical equipment within 30 days are added together to obtain the direct carbon emissions of the target object within these 30 days.

[0095] Step 504: Determine the indirect carbon emissions of the target object based on the marginal carbon emission factor of the target object within a preset time range.

[0096] The marginal carbon emission factor refers to the additional carbon emissions resulting from each additional unit of electricity load. It can be used to assess the carbon emission effects of different electrical devices. The marginal carbon emission factor is determined based on the power source type and energy mix corresponding to the target object's topological location in the power grid. Since different regions or nodes in the power grid may have different power source structures and energy mixes, the marginal carbon emission factor varies. The power supply sources in the target object's region may include renewable energy (such as wind, solar, and hydropower), fossil fuels (such as coal, natural gas, and oil), and nuclear energy. When the power supply source corresponding to the grid node connected to the target object is renewable energy, the marginal carbon emission factor corresponding to the target object is smaller; when the power supply source corresponding to the grid node connected to the target object is fossil fuels, the marginal carbon emission factor corresponding to the target object is larger.

[0097] For example, the indirect carbon emissions of the target object can be calculated using the following formula:

[0098] β x =MEF x *E x ;

[0099] Where, β x The indirect carbon emissions of the target object within a preset time range x; MEF x E is the marginal carbon emission factor. x This refers to the electricity consumption of the target object within a preset time range.

[0100] Specifically, when calculating the indirect carbon emissions of the target object in the past 30 days, the target marginal carbon emission factor corresponding to the grid node connected to the target object is first obtained, and then the target electricity consumption of the target object in the past 30 days is obtained. The target electricity consumption is multiplied by the target marginal carbon emission factor to obtain the indirect carbon emissions of the target object in the past 30 days.

[0101] Step 506: Determine the total carbon emissions of the target object within a preset time range based on direct and indirect carbon emissions.

[0102] For example, the total carbon emissions of the target object within a preset time range are calculated using the following formula:

[0103]

[0104] Among them, Total x α represents the total carbon emissions of the target object within a preset time range x; x β represents the direct carbon emissions of the target object within a preset time range x; x The indirect carbon emissions of the target object within a preset time range x.

[0105] For example, the total carbon emissions of the target object in the past 30 days can be obtained by adding up the direct and indirect carbon emissions of the target object in the past 30 days.

[0106] In this embodiment, the total carbon emissions of the target object within a preset time range are obtained based on the direct and indirect carbon emissions of the target object within the preset time range, thereby further improving the monitoring effect of the total carbon emissions of the target object.

[0107] In one embodiment, after obtaining the historical power load data of electrical equipment within a historical time range, the method further includes: normalizing the target historical power load data based on the maximum and minimum values ​​of the target historical power load data within the historical time range.

[0108] The maximum value of the target historical power load data is the maximum value among all power load data of the target electrical equipment within the historical time range, and the minimum value is the minimum value among all power load data of the target electrical equipment within the historical time range. The purpose of normalization is to scale all target historical power load data to between 0 and 1, thereby improving the training efficiency of the target equipment status recognition model.

[0109] For example, the target historical electricity load data is normalized according to the following formula:

[0110]

[0111] Where, x new It is the new data value after normalization of the target historical power load data; min(x) is the minimum value of the target historical power load data within the historical time range, and max(x) is the maximum value of the target historical power load data within the historical time range.

[0112] In this embodiment, by normalizing the target power load data to between 0 and 1, the computational complexity is reduced, thereby accelerating the training process of the target equipment status recognition model.

[0113] Furthermore, after normalizing the target historical power load data, convolutional neural networks (CNNs) can effectively learn key features from the original data due to their parameter sharing and sparse connections. Therefore, a one-dimensional CNN algorithm is used to process the normalized target historical power load data. The key structure of the one-dimensional CNN is the convolutional layer, which includes filters that perform convolution operations on the input features and generate corresponding feature maps. The convolution operation is represented as:

[0114]

[0115] Where m represents the feature map output from the original data, e represents the input features of the convolutional layer, k represents the convolutional kernel of the convolutional layer, and b represents the bias. φ represents the convolution operator, and φ represents the activation function, typically a rectified linear unit. The feature map m output from the one-dimensional convolutional neural network will be used in the next step to extract forward and backward information.

[0116] For the bidirectional Long Short-Term Memory (LSTM) algorithm, a LSM network is recursively composed of multiple identical memory units. Each memory block in the LSM network has three gates: an input gate, a forget gate, and an output gate. The following equation represents which information is input into the memory block:

[0117] i t =σ(W xi ·x t +W hi ·h t-1 +W ci ·c t-1 +b i );

[0118] Among them, i t The input gate's output value is represented by σ; σ represents the activation function, used to map the result of the linear transformation to values ​​between 0 and 1; W xi Used to input about x t The weight matrix W hi h is used as input for the output of the previous time step. t-1 The weight matrix W ci Used to input information about cell state c t-1 The weight matrix; b i It is the bias vector.

[0119] The following equations indicate what information the forget gate control will record:

[0120] f t =σ(W xf ·x t +W hf ·h t-1 +W cf ·c t-1 +b f );

[0121] Among them, f t This represents the output value of the forget gate, which is used to control the previous state c. t-1 The degree of forgetting; W xf Used to input about x t The weight matrix W hf h is used as input for the output of the previous time step.t-1 The weight matrix W cf Used to input information about cell state c t-1 The weight matrix; b f It is the bias vector.

[0122] The following equations indicate which information the output gate controls will be output to the next cell state:

[0123] c t =f t ·c t-1 +i t ·tanh(W xc ·x t +W hc ·h t-1 +b c );

[0124] Among them, c t Represents the current cell state; i t It is the output value of the input gate, used to control the current input x. t The degree of influence; tanh is used to represent the hyperbolic tangent function, used to map the result of a linear transformation to values ​​in the range [-1, 1]; W xc Used to input about x t The weight matrix W hc h is used as input for the output of the previous time step. t-1 The weight matrix; b c It is the bias vector.

[0125] o t =σ(W xo ·x t +W ho ·h t-1 +W co ·c t +b o );

[0126] Among them, o t This represents the output value of the output gate, used to control the current cell state c. t For the output h t-1 Degree of impact; W xo Used to input about x t The weight matrix W ho h is used as input for the output of the previous time step. t-1 The weight matrix W co Used to input the current unit state c t-1 The weight matrix; b o It is the bias vector; the i mentioned above t f t c tand o t These are all transient results at each stage of the training process.

[0127] It is worth noting that Long Short-Term Memory (LSTM) only uses contextual information forward and not backward, while Bidirectional LSM utilizes bidirectional contextual information by recording both forward and backward information. Therefore, it is necessary to hide the forward sequence. and backward hidden sequence Defined as recording forward and backward information, its definition is given by the following two equations:

[0128]

[0129]

[0130] in, It can be o t A set of.

[0131] After training with the bidirectional long short-term memory algorithm, the model's output is:

[0132]

[0133] Finally, the output results are integrated to obtain the state vector of the target electrical equipment, which is used to represent the operating state S of the target electrical equipment within the corresponding time period.

[0134] Furthermore, to avoid overfitting during the training process of the target device state recognition model, dropout technology is used to reduce overfitting. In this embodiment, the dropout rate (the proportion of neurons that are turned off) is set to 0.2. This means that in each training iteration, 20% of the connections between and within the hidden layers will be randomly disconnected. At the same time, combined with the adaptive motion estimation algorithm, the above-mentioned relevant parameters are adjusted by optimizing the loss function so that the prediction results of the final target device state recognition model are more accurate.

[0135] This embodiment uses the above method to first determine the target equipment status based on the target power load data and the target equipment status identification model, and then determine the target carbon emission intensity based on the target equipment status. This ensures the accuracy and reliability of the target carbon emission intensity obtained when the equipment's operating status changes, thereby ensuring the accuracy and reliability of the total carbon emissions obtained based on the target carbon emission intensity, and ultimately improving the monitoring effect of the enterprise's total carbon emissions.

[0136] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0137] Based on the same inventive concept, this application also provides a carbon emission monitoring device for implementing the carbon emission monitoring method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more carbon emission monitoring device embodiments provided below can be found in the limitations of the carbon emission monitoring method described above, and will not be repeated here.

[0138] In one embodiment, such as Figure 6 As shown, a carbon emission monitoring device is provided, comprising: a data acquisition module 602, a carbon emission intensity determination module 604, and a carbon emission calculation module 606, wherein:

[0139] The data acquisition module 602 is used to acquire the target power load data and target equipment status recognition model of the electrical equipment in the target object within a preset time range. The target status recognition model is trained based on the target historical power load data and the target equipment status information corresponding to the target historical power load data.

[0140] The carbon emission intensity determination module 604 is used to input the target power load data into the target equipment status identification model, obtain the target equipment status corresponding to the target power load data, and determine the target carbon emission intensity of the target power-consuming equipment based on the target equipment status.

[0141] The carbon emission calculation module 606 is used to determine the total carbon emissions of a target object within a preset time range based on the target carbon emission intensity.

[0142] In one embodiment, the carbon emission intensity determination module 604 is further configured to: determine the target carbon emission intensity corresponding to the target equipment state in a preset mapping table between equipment state and equipment carbon emission intensity, based on the target equipment state.

[0143] In one embodiment, the data acquisition module 602 is further configured to: acquire historical power load data of electrical equipment within a historical time range; detect whether there is missing data in the historical power load data, and if there is missing data in the historical power load data, fill in the missing data to obtain updated historical power load data; and acquire a target equipment status recognition model, including: training a target equipment status recognition model based on the updated historical power load data and the target equipment status information corresponding to the target historical power load data.

[0144] In one embodiment, the data acquisition module 602 is further configured to: divide the historical time range into several consecutive time periods, supplement missing data based on the historical power load data in each time period, and obtain updated historical power load data.

[0145] In one embodiment, the data acquisition module 602 is further configured to: determine the target time period in which the missing data is located, and determine the historical power load data of two time periods adjacent to the target time period and their corresponding preset weights; and fill in the missing data according to the historical power load data of the two time periods adjacent to the target time period and their corresponding preset weights.

[0146] In one embodiment, the carbon emission calculation module 606 is further configured to: determine the direct carbon emissions of the target object based on the target carbon emission intensity; determine the indirect carbon emissions of the target object based on the marginal carbon emission factor of the target object within a preset time range; and determine the total carbon emissions of the target object within the preset time range based on the direct and indirect carbon emissions.

[0147] The modules in the aforementioned carbon emission monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0148] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores historical power load data, real-time power load data, operating status information, and marginal carbon emission factors of the target object for each electrical device within the target object. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a carbon emission monitoring method.

[0149] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a carbon emission monitoring method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0150] Those skilled in the art will understand that Figure 7 and Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0151] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0152] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0153] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0154] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0155] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0156] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0157] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for monitoring carbon emissions, characterized in that, The method includes: Obtain target power load data of electrical equipment in the target object within a preset time range, and obtain a target equipment status recognition model. The target equipment status recognition model is trained based on the target historical power load data and the target equipment status information corresponding to the target historical power load data. The target power load data is input into the target equipment status identification model to obtain the target equipment status corresponding to the target power load data, and the target carbon emission intensity of the electrical equipment is determined based on the target equipment status. Based on the target carbon emission intensity, determine the total carbon emissions of the target object within a preset time range; The generation process of the target device state recognition model includes: Obtain historical power load data of the electrical equipment within a historical time range; The system detects whether there are missing data in the historical power load data. If there are missing data in the historical power load data, the historical time range is divided into several consecutive time periods. Determine the target time period in which the missing data is located, and determine the historical power load data and their corresponding preset weights for two time periods adjacent to the target time period; Based on the historical power load data of two time periods adjacent to the target time period and their corresponding preset weights, the missing data is filled in to obtain the updated historical power load data; The target equipment status recognition model is trained based on the updated historical power load data and the target equipment status information corresponding to the target historical power load data.

2. The method according to claim 1, characterized in that, Determining the target carbon emission intensity of the electrical equipment based on the target equipment status includes: Based on the target equipment status, the target carbon emission intensity corresponding to the target equipment status is determined in a preset mapping table between equipment status and equipment carbon emission intensity.

3. The method according to claim 1, characterized in that, The step of determining the total carbon emissions of the target object within a preset time range based on the target carbon emission intensity includes: The direct carbon emissions of the target object are determined based on the target carbon emission intensity. The indirect carbon emissions of the target object are determined based on the marginal carbon emission factor of the target object within a preset time range; Based on the direct carbon emissions and the indirect carbon emissions, the total carbon emissions of the target object within a preset time range are determined.

4. A carbon emission monitoring device, characterized in that, The device includes: A data acquisition module is used to acquire target power load data and a target equipment status recognition model for electrical equipment within a preset time range. The target equipment status recognition model is trained based on historical power load data and target equipment status information corresponding to the historical power load data. The generation process of the target equipment status recognition model includes: acquiring historical power load data of the electrical equipment within a historical time range; detecting whether there is missing data in the historical power load data; if there is missing data, dividing the historical time range into several consecutive time periods; determining the target time period where the missing data is located, and determining the historical power load data and corresponding preset weights of the two time periods adjacent to the target time period; filling in the missing data based on the historical power load data and corresponding preset weights of the two time periods adjacent to the target time period to obtain updated historical power load data; and training the target equipment status recognition model based on the updated historical power load data and the target equipment status information corresponding to the target historical power load data. The carbon emission intensity determination module is used to input the target power load data into the target equipment status identification model, obtain the target equipment status corresponding to the target power load data, and determine the target carbon emission intensity of the electrical equipment based on the target equipment status. The carbon emission calculation module is used to determine the total carbon emissions of the target object within a preset time range based on the target carbon emission intensity.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

Images