Carbon emission prediction method and device, equipment and storage medium

Abstract

The invention discloses a carbon emission prediction method and device, equipment and a storage medium, and relates to the technical field of power electronics, and the method comprises the steps: obtaining the original power utilization data of a current region, and constructing a structured data set according to the original power utilization data and the data features of each piece of original power utilization data; target features are determined according to the importance of all data features in the structured data set, data screening is carried out on the structured data set based on the target features, a target data set is obtained, and the target data set is composed of the target features and original power utilization data corresponding to all the target features; inputting the target data set into a pre-trained prediction model, so that the prediction model determines a predicted power consumption data set of the current area according to the target data set; and determining a predicted carbon emission data set of the current region according to the predicted power consumption data set and the carbon emission factor of the current region. According to the technical scheme, the carbon emission of the current area is predicted, and the accuracy and efficiency of carbon emission prediction are improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of power electronics technology, and in particular to a carbon emission prediction method, device, equipment and storage medium. Background Art

[0002] As global climate change has an increasingly serious impact on the environment and society, monitoring and managing carbon emissions has become an important global issue. Companies and organizations increasingly need to accurately track carbon emissions to ensure that carbon emissions meet environmental regulations, improve energy efficiency, and promote sustainable development.

[0003] In the prior art, carbon emissions in a region are usually monitored by collecting electricity consumption data in the region. Specifically, the electricity consumption data can be statistically analyzed and visualized, and the data can be displayed on a display module to achieve intuitive data display, making it easier for staff to quickly grasp the carbon emissions in the region.

[0004] However, electricity consumption data are often complex and noisy. Unprocessed electricity consumption data contains a large amount of redundant information. Direct visualization of electricity consumption data is difficult to reveal the deep relationship between electricity consumption data and carbon emissions, which limits further analysis and prediction of carbon emissions. Summary of the invention

[0005] The present invention provides a carbon emission prediction method, device, equipment and storage medium, which realizes carbon emission prediction by analyzing and processing electricity consumption data.

[0006] In a first aspect, an embodiment of the present invention provides a carbon emission prediction method, comprising: obtaining original electricity consumption data of a current area, constructing a structured data set according to the original electricity consumption data and data features of each original electricity consumption data; determining a target feature according to the importance of each data feature in the structured data set, and performing data screening on the structured data set based on the target feature to obtain a target data set, wherein the target data set is composed of the target feature and the original electricity consumption data corresponding to each target feature; inputting the target data set into a pre-trained prediction model so that the prediction model determines a predicted electricity consumption data set for the current area according to the target data set; and determining a predicted carbon emission data set for the current area according to the predicted electricity consumption data set and a carbon emission factor for the current area.

[0007] The technical solution of the embodiment of the present invention provides a carbon emission prediction method. First, the original electricity consumption data of the current area can be obtained, and a structured data set can be constructed according to the original electricity consumption data and the data features of the original electricity consumption data to achieve structured processing of the original electricity consumption data. Secondly, the importance of each data feature in the structured data set can be determined, and the target feature can be determined according to the importance of each data feature to achieve the determination of the target feature with a greater contribution to the prediction of electricity consumption data. The target data set can also be constructed according to the original electricity consumption data corresponding to each target feature in the structured data set to achieve the construction of the target data set with a greater contribution to the prediction of electricity consumption data. Then, the target data set can be input into the prediction model, and the predicted electricity consumption data of the original electricity consumption data corresponding to each target feature in the target data set can be determined according to the prediction model to achieve the determination of the predicted electricity consumption data set of the current area, thereby achieving the prediction of the electricity consumption data of the current area. In addition, the prediction model can enhance the understanding of the data, improve the prediction accuracy and efficiency, and then determine the carbon emission factor of the current area. The predicted carbon emission data set of the current area is determined according to the predicted electricity consumption data set and the carbon emission factor of the current area, thereby achieving the prediction of carbon emissions in the current area, further improving the accuracy and efficiency of carbon emission prediction, and providing data support for carbon emission monitoring in the current area.

[0008] Furthermore, the target feature is determined according to the importance of each data feature in the structured data set, including: inputting the structured data set into a pre-trained importance determination model so that the importance determination model determines the importance of each data feature; sorting each data feature based on importance, and determining the target feature according to the sorting result.

[0009] Furthermore, the training process of the importance determination model includes: training the random forest model using a sample data set consisting of sample data and data features of the sample data and the importance of each data feature as training data to obtain the importance determination model.

[0010] Furthermore, the structured data set is screened based on the target features to obtain the target data set, including: determining the original power consumption data corresponding to each target feature in the structured data set; and constructing the target data set according to the target features and the original power consumption data corresponding to each target feature.

[0011] Furthermore, the training process of the prediction model includes: obtaining sample original electricity consumption data in a first historical time period, and obtaining target electricity consumption data corresponding to the sample original electricity consumption data in a second historical time period after the first historical time period; using the sample original electricity consumption data as training input and using the target electricity consumption data to guide the training output to perform network training to obtain a prediction model.

[0012] Furthermore, after determining the predicted carbon emission data set of the current region, the method further includes: determining the carbon emission situation of the current region according to the carbon emission threshold of the current region and the predicted carbon emission data set.

[0013] Furthermore, after obtaining the target data set, it also includes: determining the carbon emission data set based on the carbon emission factor of the current area and the original electricity consumption data corresponding to each target feature in the target data set; accordingly, after determining the predicted carbon emission data set of the current area, it also includes: displaying the carbon emission data set, predicted carbon emission data set and carbon emission situation based on a preset interface.

[0014] In a second aspect, an embodiment of the present invention further provides a carbon emission prediction device, comprising:

[0015] An acquisition module is used to acquire the original electricity consumption data of the current area and construct a structured data set according to the original electricity consumption data and data features of each original electricity consumption data;

[0016] A screening module, used to determine a target feature according to the importance of each data feature in the structured data set, and screen the structured data set based on the target feature to obtain a target data set, wherein the target data set is composed of the target feature and the original power consumption data corresponding to each target feature;

[0017] A processing module, used for inputting the target data set into a pre-trained prediction model, so that the prediction model determines the predicted electricity consumption data set of the current area according to the target data set;

[0018] The determination module is used to determine the predicted carbon emission data set of the current area according to the predicted electricity consumption data set and the carbon emission factor of the current area.

[0019] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising: 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 execute a carbon emission prediction method as described in any one of the first aspects.

[0020] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the carbon emission prediction method as described in any one of the first aspects.

[0021] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed on a computer, the computer executes the carbon emission prediction method provided in the first aspect.

[0022] It should be noted that the above computer instructions may be stored in whole or in part on a computer-readable storage medium. The computer-readable storage medium may be packaged together with the processor of the carbon emission prediction device, or may be packaged separately from the processor of the carbon emission prediction device, and this application does not limit this.

[0023] The description of the second, third, fourth and fifth aspects in this application can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second, third, fourth and fifth aspects can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.

[0024] In this application, the name of the above-mentioned carbon emission prediction device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this application, they fall within the scope of the claims of this application and their equivalent technologies.

[0025] These and other aspects of the present application will become more apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 A flowchart of a carbon emission prediction method provided by an embodiment of the present invention;

[0028] Figure 2 A flowchart of another carbon emission prediction method provided by an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of the structure of a carbon emission prediction device provided by an embodiment of the present invention;

[0030] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0032] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0033] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0034] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application 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 limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0035] It should be mentioned before discussing exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe various operations (or steps) as sequential processes, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to methods, functions, procedures, subroutines, subprograms, etc. In addition, the embodiments in the present invention and the features in the embodiments can be combined with each other without conflict.

[0036] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0037] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0038] Figure 1 A flowchart of a carbon emission prediction method provided by an embodiment of the present invention is provided. This embodiment can be applied to situations where carbon emissions need to be predicted based on electricity consumption data to improve the accuracy of carbon emission prediction. The method can be executed by a carbon emission prediction device, such as Figure 1 As shown, the specific steps include:

[0039] Step 110: Acquire original electricity consumption data of the current area, and construct a structured data set according to the original electricity consumption data and data features of each of the original electricity consumption data.

[0040] The data characteristics include at least the electrical equipment, the time of electricity consumption and the weather for electricity consumption.

[0041] The current region can be understood as the current enterprise region, current city, current area, etc. The original electricity consumption data can be understood as the electricity consumption data of the historical time period before the current moment. The selection of the historical time period is related to the time period of the carbon emissions to be predicted. If the carbon emissions one week after the current moment need to be predicted, the electricity consumption data of at least one week before the current moment can be selected as the original electricity consumption data. If the carbon emissions one month after the current moment need to be predicted, the electricity consumption data of at least one month before the current moment can be selected as the original electricity consumption data. The data features of the electricity consumption data can at least include the electricity consumption equipment, electricity consumption time, and electricity consumption weather.

[0042] Specifically, first, the original electricity consumption data of the current area can be obtained. Secondly, the original electricity consumption data can be processed to determine the structured data (X, a, b, c...) corresponding to the original electricity consumption data, wherein X represents the original electricity consumption data, and a, b, c all represent the data characteristics of the original electricity consumption data. Furthermore, a structured data set can be constructed according to the original electricity consumption data and the data characteristics of each original electricity consumption data. The structured data set is composed of multiple (X, a, b, c...).

[0043] In the embodiment of the present invention, a structured data set is constructed based on the acquired original power consumption data of the current area and the data features of the original power consumption data, so as to implement structured processing of the original power consumption data.

[0044] Step 120: determine a target feature according to the importance of each of the data features in the structured data set, and perform data screening on the structured data set based on the target feature to obtain a target data set.

[0045] The target data set is composed of the target features and the original electricity consumption data corresponding to each of the target features.

[0046] The importance of data features refers to the importance of data features to electricity consumption data prediction, which can measure the contribution of data features to electricity consumption data prediction. The greater the importance of data features, the greater their contribution to electricity consumption data prediction, and vice versa.

[0047] Specifically, the structured data set can be input into a pre-trained importance determination model, and the importance model can determine the importance of each data feature of each original power consumption data in the structured data set. The data features are sorted according to their importance, and a preset number of data features with greater importance are determined as target features, so as to determine the target features with greater contribution to the prediction of power consumption data from the data features of the original power consumption data.

[0048] It should be noted that the importance determination model is obtained by training the random forest model with a structured training data set consisting of training data and data features of the training data, as well as the importance of each data feature. The random forest model has good robustness to outliers and noise in the data, and the importance determination model obtained by training the random forest model is more stable in practical applications.

[0049] Furthermore, data screening can be performed in the structured data based on the target features, and the original power consumption data containing the target features in the structured data set can be determined as the original power consumption data corresponding to the target features. Of course, the target data set can be constructed based on the target features and the original power consumption data corresponding to each target feature. Since the target features contribute greatly to the prediction of power consumption data, the target data set constructed based on the target features and the original power consumption data corresponding to each target feature can be used for the prediction of power consumption data, and more accurate power consumption data can be predicted.

[0050] Since the target features obtained by feature selection have removed noise and irrelevant data features, the data quality of the target data set determined according to the target features is higher, and electricity consumption data prediction based on the target data set can improve the accuracy of the prediction.

[0051] In an embodiment of the present invention, a target feature is determined based on the importance of each data feature in a structured data set, so as to determine the target feature that contributes more to the prediction of electricity consumption data. A target data set is constructed based on the original electricity consumption data corresponding to each target feature in the structured data set, so as to construct the target data set that contributes more to the prediction of electricity consumption data.

[0052] Step 130: input the target data set into a pre-trained prediction model, so that the prediction model determines the predicted electricity consumption data set of the current area according to the target data set.

[0053] Among them, the prediction model is obtained by training a hybrid deep learning model with the sample original electricity consumption data obtained in the first historical time period and the target electricity consumption data corresponding to the sample original electricity consumption data obtained in the second historical time period after the first historical time period. The hybrid deep learning model can learn the data distribution of the sample original electricity consumption data and the target electricity consumption data corresponding to the sample original electricity consumption data, improve the prediction performance on unknown data, and can be used to predict future electricity consumption data based on the original electricity consumption data.

[0054] Specifically, the target data set can be input into the prediction model, and the prediction model can determine the predicted electricity consumption data of the original electricity consumption data corresponding to each target feature in the target data set, and obtain the predicted electricity consumption data corresponding to each target feature. According to the predicted electricity consumption data corresponding to each target feature, the predicted electricity consumption data set of the current area can be determined.

[0055] In an embodiment of the present invention, by inputting a target data set into a prediction model, the predicted power consumption data of the original power consumption data corresponding to each target feature in the target data set is determined according to the prediction model, so as to determine the predicted power consumption data set of the current area, thereby realizing the prediction of the power consumption data of the current area, and the prediction model can enhance the understanding of the data and improve the prediction accuracy and efficiency.

[0056] Step 140: Determine a predicted carbon emission dataset for the current region based on the predicted electricity consumption dataset and the carbon emission factor for the current region.

[0057] Among them, the carbon emission factor is a conversion coefficient used to convert electricity consumption data (usually measured in kilowatt-hours) into carbon emissions (usually measured in kilograms of carbon dioxide). The carbon emission factor is determined based on the average carbon emissions generated during power generation in the region. It is related to the region where the current region is located, the type of energy used for power generation in the region, and the power generation efficiency of the region. The database can store carbon emission factors for each region.

[0058] Specifically, first, the location of the current region can be determined, and the database can be searched according to the location of the current region to determine the carbon emission factor of the current region, which is the carbon emission factor of the current region. Secondly, the predicted electricity consumption data in the predicted electricity consumption data set can be multiplied by the carbon emission factor to obtain the predicted carbon emission data corresponding to each predicted electricity consumption data, and then the predicted carbon emission data corresponding to each target feature can be obtained. According to the predicted carbon emission data corresponding to each target feature, the predicted carbon emission data set of the current region can be determined.

[0059] In an embodiment of the present invention, a predicted carbon emission dataset for the current region is determined based on the predicted electricity consumption dataset and carbon emission factor of the current region, so as to realize the prediction of carbon emissions for the current region, further improve the accuracy and efficiency of carbon emission prediction, and provide data support for carbon emission monitoring in the current region.

[0060] The carbon emission prediction method provided by the embodiment of the present invention can first obtain the original electricity consumption data of the current area, construct a structured data set according to the original electricity consumption data and the data features of the original electricity consumption data, and realize the structured processing of the original electricity consumption data. Secondly, the importance of each data feature in the structured data set can be determined, and the target feature can be determined according to the importance of each data feature to realize the determination of the target feature with a greater contribution to the prediction of electricity consumption data. The target data set can also be constructed according to the original electricity consumption data corresponding to each target feature in the structured data set to realize the construction of the target data set with a greater contribution to the prediction of electricity consumption data. Then, the target data set can be input into the prediction model, and the predicted electricity consumption data of the original electricity consumption data corresponding to each target feature in the target data set can be determined according to the prediction model to realize the determination of the predicted electricity consumption data set of the current area, thereby realizing the prediction of the electricity consumption data of the current area. In addition, the prediction model can enhance the understanding of the data, improve the prediction accuracy and efficiency, and then determine the carbon emission factor of the current area. The predicted carbon emission data set of the current area is determined according to the predicted electricity consumption data set and the carbon emission factor of the current area, thereby realizing the prediction of carbon emissions in the current area, further improving the accuracy and efficiency of carbon emission prediction, and providing data support for carbon emission monitoring in the current area.

[0061] Figure 2 A flowchart of another carbon emission prediction method provided by an embodiment of the present invention. This embodiment is specific based on the above embodiment. In this embodiment, the method may also include:

[0062] Step 210: Acquire original electricity consumption data of the current area, and construct a structured data set according to the original electricity consumption data and data features of each of the original electricity consumption data.

[0063] Specifically, first, the original electricity consumption data of the current area can be obtained based on electricity meters, smart devices, sensors, etc. There are multiple types of electricity consumption equipment in the current area, such as refrigeration equipment, lighting equipment, communication equipment, etc. Therefore, the original electricity consumption data includes electricity consumption data of multiple types of electricity consumption equipment; there are multiple weather conditions in the historical time period, such as different humidity, different temperatures, and different sunshine hours, so the original electricity consumption data includes electricity consumption data of multiple weather conditions; the electricity consumption data of different periods in the historical time period are different, for example, the electricity consumption data of working days and non-working days are different, so the original electricity consumption data includes electricity consumption data of various periods, and rich electricity consumption data can be obtained by comprehensively considering the electricity consumption equipment, electricity consumption time, and electricity consumption weather. Secondly, the data characteristics of the original electricity consumption data can be determined, for example, the electricity consumption equipment, electricity consumption time, and electricity consumption weather of the original electricity consumption data can be determined.

[0064] Secondly, the raw electricity consumption data can be processed, specifically, the raw electricity consumption data can be cleaned, converted and integrated. Data cleaning is to remove errors, duplications or incomplete records in the data to ensure the accuracy and consistency of the data. Data conversion is to convert the data into a format suitable for analysis, for example, converting timestamps to dates and times, or standardizing energy consumption units. Data integration is to merge data from different sources and formats into a unified data set for easy analysis and processing. Specifically, data cleaning can be used to identify and remove outliers, such as extreme energy consumption readings caused by equipment failures or data recording errors. Data conversion can be used to convert data collected by different devices and sensors into a unified format and unit for subsequent analysis. Data integration can be used to integrate multi-dimensional raw electricity consumption data of different power consumption devices, different power consumption times, and different power consumption weather into one data set to reflect the overall power consumption situation. Of course, the raw electricity consumption data can be converted into structured data (X, a, b, c...), and the structured data corresponding to each raw electricity consumption data can be integrated to obtain a structured data set.

[0065] Data cleaning can eliminate noise and errors in raw electricity data and improve data reliability. Data conversion and integration can be used to analyze electricity data more comprehensively, and the resulting structured data sets are easier to process with visualization tools. Automated data processing can reduce manual intervention and reduce the cost and time of data processing.

[0066] In the embodiment of the present invention, by performing data processing on the acquired original power consumption data of the current area, a structured data set is constructed according to the original power consumption data, thereby achieving structured processing of the original power consumption data.

[0067] Step 220: Determine a target feature according to the importance of each of the data features in the structured data set.

[0068] In one embodiment, step 220 may specifically include: inputting the structured data set into a pre-trained importance determination model so that the importance determination model determines the importance of each of the data features; sorting each of the data features based on the importance, and determining the target feature according to the sorting result.

[0069] Specifically, the structured data set can be input into a pre-trained importance determination model, and the importance model can determine the importance of each data feature of each original power consumption data in the structured data set. The data features are sorted from large to small according to importance, and a preset number of data features with high rankings are determined as target features. Through feature selection, data features with small contribution to power consumption data prediction are removed, so as to determine the target features with large contribution to power consumption data prediction from the data features of the original power consumption data.

[0070] It should be noted that the training process of the importance determination model includes: training the random forest model using a sample data set consisting of sample data and data features of the sample data and the importance of each data feature as training data to obtain the importance determination model.

[0071] The random forest model has a built-in random forest algorithm, which is an integrated learning method that can improve the accuracy and robustness of the random forest model by building multiple decision trees and combining their prediction results. The random forest model can calculate the importance of each data feature, which measures the contribution of the data feature to the prediction of electricity consumption data. The importance determination model can be obtained by training the random forest model using a sample data set consisting of sample data and data features of the sample data and the importance of each data feature, where the sample data set contains multi-dimensional data features such as electricity consumption equipment, electricity consumption time, and electricity consumption weather. The importance determination model can calculate the importance of each data feature, which reflects the contribution of each data feature to the prediction of electricity consumption data.

[0072] In practical applications, other methods can also be used for feature selection, such as principal component analysis method, LASSO regression method, etc.

[0073] In the embodiment of the present invention, the target feature is determined according to the importance of each data feature in the structured data set, so that the target feature with a greater contribution to the prediction of electricity consumption data is determined among the data features.

[0074] Step 230: Screen the structured data set based on the target feature to obtain a target data set.

[0075] The target data set is composed of the target features and the original electricity consumption data corresponding to each of the target features.

[0076] In one implementation, step 230 may specifically include: determining original power usage data corresponding to each of the target features in the structured data set; and constructing the target data set according to the target features and the original power usage data corresponding to each of the target features.

[0077] Specifically, data screening can be performed in structured data based on target features, and the original power consumption data containing the target features in the structured data set can be determined as the original power consumption data corresponding to the target features. When the target features include power consumption equipment and power consumption time, the original power consumption data containing various power consumption equipment can be determined as the original power consumption data corresponding to various power consumption equipment, for example, the original power consumption data corresponding to power consumption equipment such as refrigeration equipment, lighting equipment, and communication equipment can be screened out; the original power consumption data containing power consumption time can also be determined as the original power consumption data corresponding to the power consumption time, for example, the original power consumption data corresponding to various power consumption times such as working days and non-working days can be screened out. A target data set can also be constructed based on the target features and the original power consumption data corresponding to each target feature. Since the target features contribute more to the prediction of power consumption data, the target data set constructed based on the target features and the original power consumption data corresponding to each target feature can be used to predict more accurate power consumption data.

[0078] In the embodiment of the present invention, the target data set is obtained by screening the structured data set according to the target features, so as to determine the original power consumption data corresponding to various target features.

[0079] Step 240: Determine a carbon emission data set according to the carbon emission factor of the current region and the original electricity consumption data corresponding to each of the target features in the target data set.

[0080] Specifically, the original electricity consumption data corresponding to each target feature in the target data set can be multiplied by the carbon emission factor to obtain the carbon emission data of the original electricity consumption data corresponding to each target feature, and then the carbon emission data corresponding to each target feature can be obtained. A carbon emission data set is constructed based on the target features and the carbon emission data corresponding to each target feature, and the carbon emission data set can reflect the carbon emission situation under different target features.

[0081] By determining the carbon emission data corresponding to the target characteristics, the carbon emissions under different target characteristics can be determined more accurately. Integrating carbon emission data under different target characteristics facilitates horizontal and vertical comparisons, identifies high-risk areas for carbon emissions, and facilitates staff to formulate targeted energy-saving and emission reduction measures. By identifying high-carbon emission electrical equipment and electricity consumption time, electricity consumption can be better managed. By optimizing energy use in high-risk areas for carbon emissions, energy costs can be reduced and operational efficiency can be improved.

[0082] In an embodiment of the present invention, the carbon emission data corresponding to each target feature is determined based on the carbon emission factor of the current area and the original electricity consumption data corresponding to each target feature in the target data set, and a carbon emission data set is constructed based on the target features and the carbon emission data corresponding to each target feature to achieve comprehensive statistics of carbon emissions under different target features.

[0083] Step 250: input the target data set into a pre-trained prediction model, so that the prediction model determines the predicted electricity consumption data set of the current area according to the target data set.

[0084] Specifically, the target data set may be input into the prediction model, and the prediction model may determine the predicted power consumption data of the original power consumption data corresponding to each target feature in the target data set, thereby obtaining the predicted power consumption data corresponding to each target feature.

[0085] In one embodiment, the training process of the prediction model includes: obtaining sample original electricity consumption data in a first historical time period, and obtaining target electricity consumption data corresponding to the sample original electricity consumption data in a second historical time period after the first historical time period; performing network training using the sample original electricity consumption data as training input and using the target electricity consumption data to guide training output, to obtain the prediction model.

[0086] The hybrid deep learning model consists of a convolutional neural network and a recurrent neural network, which is used to process complex data with time series characteristics. Convolutional neural networks can capture local features and spatial structure information in data, and are suitable for processing data with fixed structures, such as local features of electricity consumption data. Recurrent neural networks can process long-term dependencies in sequence data, and are suitable for predicting time series data, such as the long-term trend of electricity consumption data.

[0087] Specifically, the sample original electricity consumption data and the target electricity consumption data include electricity consumption data of different electricity consumption equipment, at different electricity consumption times and under different electricity consumption weather conditions. By processing the sample original electricity consumption data and the target electricity consumption data, data cleaning (removing erroneous and incomplete data), data conversion (unifying data formats and units) and data integration (merging data from different sources) can be performed to convert the sample original electricity consumption data and the target electricity consumption data into a structured format suitable for model training to obtain a sample structured data set. The structured data set includes the sample original electricity consumption data set corresponding to the sample original electricity consumption data and the target electricity consumption data set corresponding to the target electricity consumption data.

[0088] You can also use data segmentation to split the sample structured dataset into training dataset, validation dataset and test dataset. The training dataset is used for the initial training of the model to allow the model to learn the patterns and relationships in the data. The validation dataset is used to adjust the model parameters during the model training process, such as the learning rate and number of layers, to prevent overfitting. The test dataset is used to evaluate the generalization ability of the model after the final training of the model is completed, and to test the model's performance on unknown data.

[0089] Then, the training data set can be used to train the initial deep learning model that has completed the initial structure setting. This process includes forward propagation (calculating the predicted electricity consumption data corresponding to the sample original electricity consumption data) and back propagation (adjusting model parameters according to the target electricity consumption data and predicted electricity consumption data and errors corresponding to the sample original electricity consumption data). Through multiple iterations, the model gradually learns the patterns in the data.

[0090] It should be noted that the initial structure setting includes the number of network layers, the number of neurons in each network layer, and the loss function. The deep learning model consists of multiple layers of networks, and each layer converts and abstracts the input data. The number of layers determines the depth of the model, affecting the learning ability and complexity of the model. Each layer consists of multiple neurons, and the number of neurons determines the processing power of each layer. The setting of the number of neurons needs to balance the model's expressiveness and computational efficiency.

[0091] For example, a deep learning model can include an input layer, several hidden layers, and an output layer. The number of hidden layers can be experimented with starting from 2 to 4 or more. The number of neurons in the input layer should match the number of target features, i.e., one input neuron per target feature. The number of neurons in each hidden layer can be set to half to two-thirds of the number of neurons in the input layer, or to a power of 2 such as 64, 128, 256, etc. as a rule of thumb. For regression tasks, the output layer usually has one neuron.

[0092] The sample original electricity consumption data has 10 features. When training the deep learning model to determine the predicted electricity consumption data corresponding to the sample original electricity consumption data, the network structure of the deep learning model is as follows: the input layer is 10 neurons, the hidden layer 1 is 64 neurons, the hidden layer 2 is 128 neurons, the hidden layer 3 is 64 neurons, and the output layer is 1 neuron.

[0093] In practical applications, the appropriate network depth and number of neurons per layer can be designed according to the complexity of the electricity consumption data and the requirements of the prediction task. For example, for electricity consumption data with strong time series characteristics, a deeper network structure may be selected to capture long-term dependencies. The model's expressiveness can be improved by setting the number of network layers and neurons reasonably, enabling it to capture complex patterns in the data. The loss function is used to evaluate the difference between the predicted value and the actual value, and is the goal of optimization during the model training process. Choosing a suitable loss function is crucial for the model to learn the correct data pattern. When determining the predicted electricity consumption data corresponding to the sample original electricity consumption data, the mean square error (MSE) can be used as the loss function. Through the correct setting of the loss function, the model can better learn the distribution of the data and improve the prediction performance on unknown data. Through the reasonable use of the initial structure setting, a powerful deep learning model can be built to improve the accuracy and efficiency of electricity consumption data prediction.

[0094] The model can also be iteratively optimized based on the validation dataset and the test dataset to obtain a hybrid deep learning model. Specifically, during the model training process, the validation dataset is used to monitor the performance of the model, and the model is adjusted based on the validation results, such as changing the network structure and adjusting hyperparameters. This process is called iterative optimization. The purpose is to improve the accuracy and generalization ability of the model. Finally, the test dataset is used to evaluate the performance of the optimized hybrid deep learning model to ensure that the model performs well on new, unseen data.

[0095] The iterative optimization includes the following steps: using the validation data set to evaluate the performance of the model and obtain performance indicators; based on the performance indicators, optimizing the performance of the model to obtain an intermediate deep learning model; using the test data set to test the second deep learning model and obtain the indicators to be optimized; based on the indicators to be optimized, optimizing the second deep learning model to obtain a prediction model.

[0096] Through the above steps, it can be ensured that the hybrid deep learning model fully utilizes the sample original power consumption data and the target power consumption data during the training process, and the prediction ability of the model is improved through iterative optimization, and finally a prediction model that can accurately predict future power consumption data is obtained. The prediction model can capture the complex patterns and long-term dependencies in the power consumption data, and can achieve accurate power consumption prediction.

[0097] After the predicted power consumption data corresponding to each target feature is determined, a predicted power consumption data set for the current area may be constructed according to the predicted power consumption data corresponding to each target feature.

[0098] In an embodiment of the present invention, by inputting a target data set into a prediction model, the predicted power consumption data of the original power consumption data corresponding to each target feature in the target data set is determined according to the prediction model, so as to determine the predicted power consumption data set of the current area, thereby realizing the prediction of the power consumption data of the current area, and the prediction model can enhance the understanding of the data and improve the prediction accuracy and efficiency.

[0099] Step 260: Determine a predicted carbon emission dataset for the current region according to the carbon emission factor of the current region and the predicted electricity consumption dataset.

[0100] As mentioned above, each predicted electricity consumption data in the predicted electricity consumption data set can be multiplied by the carbon emission factor to obtain the predicted carbon emission data corresponding to each predicted electricity consumption data, and then the predicted carbon emission data corresponding to each target feature can be obtained. According to the predicted carbon emission data corresponding to each target feature, the predicted carbon emission data set of the current area can be determined.

[0101] Step 270: Determine the carbon emission situation of the current region according to the carbon emission threshold of the current region and the predicted carbon emission dataset.

[0102] Among them, the carbon emission threshold can be understood as the carbon emission cap set in accordance with sustainable development goals or industry standards, which may include daily, monthly or annual carbon emission thresholds.

[0103] Specifically, the carbon emission threshold and the predicted carbon emission data corresponding to each target feature in the predicted carbon emission data set can be compared to determine the carbon emission situation of different power consumption equipment and different power consumption time in the current area. Based on the carbon emission situation, the power consumption equipment and power consumption time with carbon emissions exceeding the threshold can be identified to provide a basis for subsequent decision-making.

[0104] In the embodiment of the present invention, the potential risk of exceeding the carbon emission standard can be discovered in time through the carbon emission situation in the current area, so as to facilitate taking measures to adjust in advance and reduce environmental pollution. Ensure that the carbon emissions in the current area meet the requirements of laws and regulations to avoid legal risks and potential economic losses. Through prediction and comparison, enterprises can evaluate the cost-effectiveness of different energy-saving and emission reduction measures and make economical and effective decisions. Providing data-based decision support facilitates making more scientific and reasonable management decisions.

[0105] Step 280: Display the carbon emission data set, the predicted carbon emission data set, and the carbon emission situation based on a preset interface.

[0106] Specifically, data visualization can present complex data through charts, graphs and other visual elements, making the data easier to understand and analyze. Integrating the carbon emission data set, predicted carbon emission data set and carbon emission situation based on the preset interface can provide a comprehensive perspective. Specifically, you can choose appropriate data visualization tools or software, such as Tableau, Power BI or a customized dashboard, to integrate the carbon emission data set, predicted carbon emission data set and carbon emission situation, and create charts such as line charts, bar charts, pie charts or heat maps to display the carbon emissions of different power-consuming equipment and different power consumption times.

[0107] In the embodiment of the present invention, by displaying the carbon emission data set, the predicted carbon emission data set and the carbon emission situation, it is convenient to visualize and monitor the carbon emission data set, the predicted carbon emission data set and the carbon emission situation, and it is more convenient to track the carbon emissions.

[0108] The carbon emission prediction method provided by the embodiment of the present invention can firstly obtain the original electricity consumption data of the current area, construct a structured data set according to the original electricity consumption data and the data features of the original electricity consumption data, and realize the structured processing of the original electricity consumption data. Secondly, the importance of each data feature in the structured data set can be determined, and the target feature can be determined according to the importance of each data feature to realize the determination of the target feature with a greater contribution to the prediction of electricity consumption data. The target data set can be constructed according to the original electricity consumption data corresponding to each target feature in the structured data set to realize the construction of the target data set with a greater contribution to the prediction of electricity consumption data. The carbon emission data corresponding to each target feature can also be determined according to the carbon emission factor of the current area and the original electricity consumption data corresponding to each target feature in the target data set. The target characteristics and the carbon emission data corresponding to each target characteristic are used to construct a carbon emission data set to achieve comprehensive statistics on carbon emissions under different target characteristics. Then the target data set can be input into the prediction model, and the predicted electricity consumption data of the original electricity consumption data corresponding to each target characteristic in the target data set is determined according to the prediction model to determine the predicted electricity consumption data set of the current area, thereby realizing the prediction of electricity consumption data in the current area. In addition, the prediction model can enhance the understanding of the data, improve the prediction accuracy and efficiency, and then the predicted carbon emission data set of the current area can be determined according to the predicted electricity consumption data set and carbon emission factors of the current area, thereby realizing the prediction of carbon emissions in the current area, further improving the accuracy and efficiency of carbon emission prediction, and providing data support for carbon emission monitoring in the current area.

[0109] In addition, the carbon emissions situation in the current area can be determined based on the carbon emissions threshold and predicted carbon emissions data set of the current area, and the carbon emissions data set, predicted carbon emissions data set and carbon emissions situation can be displayed based on the preset interface, so as to quickly identify the electrical equipment and electricity consumption time whose carbon emissions exceed the threshold, and provide a basis for subsequent decision-making.

[0110] Figure 3 This is a schematic diagram of the structure of a carbon emission prediction device provided by an embodiment of the present invention. The device can be applied to situations where carbon emissions need to be predicted based on electricity consumption data to improve the accuracy of carbon emission prediction. The device can be implemented by software and / or hardware and is generally integrated in electronic devices, such as computer devices.

[0111] like Figure 3 As shown, the device comprises:

[0112] An acquisition module 310 is used to acquire original power consumption data of the current area, and construct a structured data set according to the original power consumption data and data features of each of the original power consumption data;

[0113] A screening module 320, configured to determine a target feature according to the importance of each of the data features in the structured data set, and screen the structured data set based on the target feature to obtain a target data set, wherein the target data set is composed of the target feature and the original power consumption data corresponding to each of the target features;

[0114] A processing module 330 is used to input the target data set into a pre-trained prediction model so that the prediction model determines the predicted electricity consumption data set of the current area according to the target data set;

[0115] The determination module 340 is used to determine the predicted carbon emission dataset of the current area according to the predicted electricity consumption dataset and the carbon emission factor of the current area.

[0116] The carbon emission prediction device provided in this embodiment can first obtain the original electricity consumption data of the current area, construct a structured data set according to the original electricity consumption data and the data features of the original electricity consumption data, and realize the structured processing of the original electricity consumption data. Secondly, the importance of each data feature in the structured data set can be determined, and the target feature can be determined according to the importance of each data feature to realize the determination of the target feature that contributes more to the prediction of electricity consumption data. The target data set can also be constructed according to the original electricity consumption data corresponding to each target feature in the structured data set to realize the construction of the target data set that contributes more to the prediction of electricity consumption data. Then, the target data set can be input into the prediction model, and the predicted electricity consumption data of the original electricity consumption data corresponding to each target feature in the target data set can be determined according to the prediction model to realize the determination of the predicted electricity consumption data set of the current area, and then the prediction of the electricity consumption data of the current area can be realized. In addition, the prediction model can enhance the understanding of the data, improve the prediction accuracy and efficiency, and then the carbon emission factor of the current area can be determined. The predicted carbon emission data set of the current area is determined according to the predicted electricity consumption data set and the carbon emission factor of the current area, and the prediction of the carbon emissions of the current area can be realized, and the accuracy and efficiency of the carbon emission prediction can be further improved, providing data support for the carbon emission monitoring of the current area.

[0117] Based on the above embodiment, the screening module 320 is specifically used to: input the structured data set into a pre-trained importance determination model so that the importance determination model determines the importance of each of the data features; sort each of the data features based on the importance, and determine the target feature according to the sorting result; determine the original power consumption data corresponding to each of the target features in the structured data set; and construct the target data set based on the target features and the original power consumption data corresponding to each of the target features.

[0118] Based on the above embodiment, the device further includes: a determination module, which is used to determine the carbon emission data set according to the carbon emission factor of the current area and the original electricity consumption data corresponding to each target feature in the target data set after obtaining the target data set.

[0119] Based on the above embodiments, the device also includes: an execution module, which is used to determine the carbon emission situation of the current area according to the carbon emission threshold of the current area and the predicted carbon emission data set after determining the predicted carbon emission data set of the current area; and display the carbon emission data set, the predicted carbon emission data set and the carbon emission situation based on a preset interface.

[0120] On the basis of the above embodiments, the device also includes: a training module, which is used to train the random forest model using a sample data set composed of sample data and data features of the sample data and the importance of each data feature as training data to obtain the importance determination model; obtain sample original electricity consumption data in a first historical time period, and obtain target electricity consumption data corresponding to each sample original electricity consumption data in a second historical time period after the first historical time period; use the sample original electricity consumption data as training input and use the target electricity consumption data to guide training output to perform network training to obtain the prediction model.

[0121] The carbon emission prediction device provided in the embodiment of the present invention can execute the carbon emission prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the carbon emission prediction method.

[0122] It is worth noting that in the embodiment of the above-mentioned carbon emission prediction device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0123] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4 A block diagram of an exemplary electronic device 4 suitable for implementing embodiments of the present invention is shown. Figure 4 The electronic device 4 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0124] like Figure 4 As shown, the electronic device 4 is in the form of a general purpose computing electronic device. The components of the electronic device 4 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0125] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0126] The electronic device 4 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 4, including volatile and non-volatile media, removable and non-removable media.

[0127] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 4 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0128] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0129] The electronic device 4 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the electronic device 4, and / or any device that enables the electronic device 4 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 4 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. Figure 4 As shown, the network adapter 20 communicates with other modules of the electronic device 4 via the bus 18. It should be understood that although Figure 4Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 4, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0130] The processing unit 16 executes various functional applications and page displays by running the programs stored in the system memory 28, for example, implementing the carbon emission prediction method provided in the embodiment of the present invention, which includes:

[0131] Obtain original electricity consumption data of the current area, and construct a structured data set according to the original electricity consumption data and data features of each of the original electricity consumption data; determine a target feature according to the importance of each of the data features in the structured data set, and perform data screening on the structured data set based on the target feature to obtain a target data set, wherein the target data set is composed of the target feature and the original electricity consumption data corresponding to each of the target features; input the target data set into a pre-trained prediction model so that the prediction model determines a predicted electricity consumption data set for the current area according to the target data set; and determine a predicted carbon emission data set for the current area according to the predicted electricity consumption data set and a carbon emission factor for the current area.

[0132] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the carbon emission prediction method provided by any embodiment of the present invention.

[0133] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, for example, a carbon emission prediction method provided by an embodiment of the present invention is implemented. The method includes:

[0134] Obtain original electricity consumption data of the current area, and construct a structured data set according to the original electricity consumption data and data features of each of the original electricity consumption data; determine a target feature according to the importance of each of the data features in the structured data set, and perform data screening on the structured data set based on the target feature to obtain a target data set, wherein the target data set is composed of the target feature and the original electricity consumption data corresponding to each of the target features; input the target data set into a pre-trained prediction model so that the prediction model determines a predicted electricity consumption data set for the current area according to the target data set; and determine a predicted carbon emission data set for the current area according to the predicted electricity consumption data set and a carbon emission factor for the current area.

[0135] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, 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 above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0136] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0137] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0138] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0139] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0140] In addition, the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of national laws and regulations.

[0141] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A carbon emission prediction method, characterized in that: include: Acquire original electricity consumption data of the current area, and construct a structured data set according to the original electricity consumption data and data features of each of the original electricity consumption data; Determine a target feature according to the importance of each of the data features in the structured data set, and perform data screening on the structured data set based on the target feature to obtain a target data set, wherein the target data set is composed of the target feature and the original power consumption data corresponding to each of the target features; Inputting the target data set into a pre-trained prediction model so that the prediction model determines the predicted electricity consumption data set of the current area according to the target data set; A predicted carbon emission dataset for the current region is determined according to the predicted electricity consumption dataset and the carbon emission factor for the current region.

2. The carbon emission prediction method according to claim 1, characterized in that: Determining a target feature according to the importance of each of the data features in the structured data set includes: Inputting the structured data set into a pre-trained importance determination model so that the importance determination model determines the importance of each of the data features; The data features are sorted based on the importance, and the target feature is determined according to the sorting result.

3. The carbon emission prediction method according to claim 2, characterized in that: The training process of the importance determination model includes: The random forest model is trained using a sample data set consisting of sample data and data features of the sample data, as well as the importance of each data feature, as training data to obtain the importance determination model.

4. The carbon emission prediction method according to claim 1, characterized in that: The structured data set is screened based on the target feature to obtain a target data set, including: Determining original electricity consumption data corresponding to each of the target features in the structured data set; The target data set is constructed according to the target features and the original power consumption data corresponding to each of the target features.

5. The carbon emission prediction method according to claim 1, characterized in that: The training process of the prediction model includes: Acquire sample original power consumption data in a first historical time period, and acquire target power consumption data corresponding to the sample original power consumption data in a second historical time period after the first historical time period; The prediction model is obtained by performing network training using the sample original electricity consumption data as training input and the target electricity consumption data as training output guidance.

6. The carbon emission prediction method according to claim 1, characterized in that: After determining the predicted carbon emission dataset for the current region, the method further includes: The carbon emission situation of the current area is determined according to the carbon emission threshold of the current area and the predicted carbon emission data set.

7. The carbon emission prediction method according to claim 6, characterized in that: After obtaining the target data set, it also includes: Determine a carbon emission data set according to the carbon emission factor of the current region and the original electricity consumption data corresponding to each of the target features in the target data set; Accordingly, after determining the predicted carbon emission dataset of the current region, the method further includes: The carbon emission data set, the predicted carbon emission data set and the carbon emission situation are displayed based on a preset interface.

8. A carbon emission prediction device, characterized in that: include: An acquisition module, used to acquire original electricity consumption data of the current area, and construct a structured data set according to the original electricity consumption data and data features of each of the original electricity consumption data; A screening module, configured to determine a target feature according to the importance of each of the data features in the structured data set, and screen the structured data set based on the target feature to obtain a target data set, wherein the target data set is composed of the target feature and the original power consumption data corresponding to each of the target features; A processing module, configured to input the target data set into a pre-trained prediction model, so that the prediction model determines the predicted electricity consumption data set of the current area according to the target data set; A determination module is used to determine a predicted carbon emission dataset for the current area based on the predicted electricity consumption dataset and a carbon emission factor for the current area.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; 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 execute the carbon emission prediction method as described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to perform the carbon emission prediction method as described in any one of claims 1 to 7 when executed by a computer processor.

Images