CN116739867A - Method and device for measuring carbon emission of electric power system and computer equipment - Google Patents
Method and device for measuring carbon emission of electric power system and computer equipment Download PDFInfo
- Publication number
- CN116739867A CN116739867A CN202310774596.XA CN202310774596A CN116739867A CN 116739867 A CN116739867 A CN 116739867A CN 202310774596 A CN202310774596 A CN 202310774596A CN 116739867 A CN116739867 A CN 116739867A
- Authority
- CN
- China
- Prior art keywords
- data
- target
- carbon emission
- activity data
- measuring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 153
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 153
- 238000000034 method Methods 0.000 title claims abstract description 72
- 230000000694 effects Effects 0.000 claims abstract description 263
- 238000004364 calculation method Methods 0.000 claims abstract description 75
- 238000000605 extraction Methods 0.000 claims abstract description 63
- 238000004519 manufacturing process Methods 0.000 claims abstract description 27
- 238000005259 measurement Methods 0.000 claims description 73
- 238000012545 processing Methods 0.000 claims description 43
- 238000012549 training Methods 0.000 claims description 35
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 22
- 238000011176 pooling Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 description 11
- 238000012360 testing method Methods 0.000 description 6
- 238000003066 decision tree Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Educational Administration (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method and a device for measuring carbon emission of an electric power system and computer equipment. The method comprises the following steps: acquiring power activity data of a target power system, wherein the power activity data is used for representing power production activity, power consumption activity and activity level of predicted load activity of the target power system for generating carbon emission in a time period to be calculated; obtaining one-dimensional convolution characteristics corresponding to the electric power activity data according to the electric power activity data and a characteristic extraction layer of the target measuring and calculating model; according to the one-dimensional convolution characteristics and a target decision layer of the target calculation model, target carbon emission calculation data are obtained, and the target carbon emission calculation data are used for representing the carbon emission generated by the target power system in a calculation time period. The method can improve the efficiency of measuring and calculating the carbon emission.
Description
Technical Field
The present application relates to the field of carbon emission measurement technologies, and in particular, to a method and an apparatus for measuring carbon emission in an electric power system, and a computer device.
Background
The calculation of the carbon emission of the electric power system is significant for realizing the double-carbon target in China. In the traditional technology, the method for measuring the carbon emission of the electric power system mainly utilizes known carbon emission factors to combine with the power activity level of each link of the electric power system to measure and calculate the carbon emission in the time period to be measured of the target electric power system.
However, the above-described method for measuring the amount of carbon emissions in the electric power system is inefficient.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, an apparatus, and a computer device for measuring carbon emissions in an electric power system, which can improve the efficiency of measurement and calculation.
In a first aspect, the present application provides a method for measuring carbon emissions in an electrical power system. The method comprises the following steps:
acquiring power activity data of a target power system, wherein the power activity data is used for representing power production activity, power consumption activity and activity level of predicted load activity of the target power system for generating carbon emission in a time period to be calculated;
obtaining one-dimensional convolution characteristics corresponding to the electric power activity data according to the electric power activity data and a characteristic extraction layer of the target measuring and calculating model;
according to the one-dimensional convolution characteristics and a target decision layer of the target calculation model, target carbon emission calculation data are obtained, and the target carbon emission calculation data are used for representing the carbon emission generated by the target power system in a calculation time period.
In one embodiment, according to the feature extraction layer of the power activity data and the target measurement model, obtaining one-dimensional convolution features corresponding to the power activity data includes:
The electric power activity data are arranged in a matrix mode according to the electric power activity type to obtain activity matrix data;
carrying out one-dimensional convolution calculation processing on the active matrix data to obtain convolution data;
carrying out maximum pooling treatment on the convolution data to obtain characteristic data;
and carrying out one-dimensional expansion on the feature data to obtain one-dimensional convolution features.
In one embodiment, the number of target measurement models is a plurality; according to the feature extraction layer of the power activity data and the target measuring and calculating model, obtaining one-dimensional convolution features corresponding to the power activity data, wherein the one-dimensional convolution features comprise:
respectively inputting the electric power activity data into a feature extraction layer of each target measuring and calculating model to obtain one-dimensional convolution features output by each feature extraction layer;
obtaining target carbon emission measurement data according to a one-dimensional convolution characteristic and a target decision layer of a target measurement model, wherein the method comprises the following steps:
inputting each one-dimensional convolution characteristic into a target decision layer of a corresponding target measuring and calculating model respectively to obtain carbon emission measuring and calculating data output by each target decision layer;
and carrying out average value calculation processing on the plurality of carbon emission measurement data to obtain target carbon emission measurement data.
In one embodiment, obtaining power activity data for a target power system includes:
Acquiring initial production activity data, initial consumption activity data and initial predicted load data of a target power system;
performing null value removal processing on the initial production activity data, the initial consumption activity data and the initial predicted load data to obtain initial power activity data;
and carrying out standardization processing on the initial power activity data to obtain the power activity data.
In one embodiment, the method further comprises:
acquiring a plurality of historical power activity data and historical carbon emission data corresponding to each historical power activity data;
and performing iterative learning on the initial measuring and calculating model by utilizing the historical electric power activity data and the historical carbon emission data corresponding to the historical electric power activity data to obtain a target measuring and calculating model.
In one embodiment, the number of target measurement models is a plurality; iteratively learning the initial measurement model by utilizing each historical electric power activity data and the historical carbon emission data corresponding to each historical electric power activity data to obtain a target measurement model, wherein the method comprises the following steps of:
performing random extraction processing on the plurality of historical power activity data and historical carbon emission data corresponding to each historical power activity data to obtain a plurality of training data sets;
And respectively carrying out iterative learning on the initial measuring and calculating model by utilizing each training data set to obtain a plurality of target measuring and calculating models.
In a second aspect, the application also provides a device for measuring the carbon emission of the electric power system. The device comprises:
the system comprises an acquisition module, a load prediction module and a load prediction module, wherein the acquisition module is used for acquiring power activity data of a target power system, wherein the power activity data is used for representing power production activity, power consumption activity and activity level of prediction load activity of the target power system for generating carbon emission in a time period to be calculated;
the feature extraction module is used for obtaining one-dimensional convolution features corresponding to the electric power activity data according to the electric power activity data and a feature extraction layer of the target measuring and calculating model;
the target measuring and calculating module is used for obtaining target carbon emission measuring and calculating data according to the one-dimensional convolution characteristics and a target decision layer of the target measuring and calculating model, wherein the target carbon emission measuring and calculating data are used for representing the carbon emission generated by a target power system in a to-be-calculated time period.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the method according to the first aspect when the processor executes the computer program.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method according to the first aspect.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements the steps of the method according to the first aspect.
According to the method, the device and the computer equipment for calculating the carbon emission of the electric power system, through acquiring the electric power activity data of the target electric power system, according to the electric power activity data and the feature extraction layer of the target calculation model, one-dimensional convolution features corresponding to the electric power activity data are obtained, and according to the one-dimensional convolution features and the target decision layer of the target calculation model, target carbon emission calculation data are obtained, wherein the target carbon emission calculation data are used for representing the generated carbon emission of the target electric power system in a time period to be calculated; in the embodiment, the one-dimensional convolution characteristic corresponding to the electric power activity data is obtained through the characteristic extraction layer of the target measuring and calculating model, the advantage that the convolution calculation can extract obvious characteristics through a small amount of data is utilized, the problem that the complexity of a measuring and calculating process is high and the measuring and calculating efficiency is low due to the fact that a large amount of electric power activity data with long time span and carbon emission factors of different types of energy sources are required to be used for measuring and calculating the carbon emission in the traditional technology is avoided, the method only needs to obtain the electric power activity data in a time period to be measured when the measuring and calculating of the carbon emission is carried out, the obtaining difficulty is low, the used data amount is small, and the efficiency of the carbon emission measuring and calculating method can be effectively improved.
Drawings
FIG. 1 is a diagram of an application environment of a method for measuring carbon emissions of an electric power system according to an embodiment;
FIG. 2 is a flow chart of a method for measuring carbon emission of an electric power system according to an embodiment;
FIG. 3 is a flow chart illustrating steps for extracting one-dimensional convolution features in one embodiment;
FIG. 4 is a flow chart of a method for measuring carbon emission of an electric power system according to an embodiment;
FIG. 5 is a flowchart illustrating steps for acquiring power activity data in one embodiment;
FIG. 6 is a flow chart of a method for measuring carbon emissions of an electrical power system according to one embodiment;
FIG. 7 is a flow chart of a method for measuring carbon emissions of an electrical power system according to one embodiment;
FIG. 8 is a flow chart of a method for measuring carbon emission of an electric power system according to another embodiment;
FIG. 9 is a block diagram of an apparatus for measuring carbon emissions of an electrical power system according to an embodiment;
fig. 10 is an internal structural view of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The method for measuring the carbon emission of the power system, provided by the embodiment of the application, can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
The terminal 102 is used for acquiring power activity data of a target power system; the server 104 is used for obtaining one-dimensional convolution characteristics corresponding to the power activity data according to the power activity data and the characteristic extraction layer of the target measuring and calculating model; according to the one-dimensional convolution characteristics and a target decision layer of the target calculation model, target carbon emission calculation data are obtained, and the target carbon emission calculation data are used for representing the carbon emission generated by the target power system in a calculation time period.
In one embodiment, as shown in fig. 2, a method for measuring carbon emission of an electric power system is provided, which is described by taking the terminal 102 or the server 104 in fig. 1 as an example, and includes the following steps:
step 202, obtaining power activity data of a target power system. Wherein the power activity data is used to represent the activity level of the power production activity, the power consumption activity, and the predicted load activity of the target power system that generates carbon emissions during the time period to be calculated.
The power generation activities that produce carbon emissions in power systems include fossil combustion such as burning coal, gas, fuel oil, etc. to produce electricity; the power consumption activities comprise links of an energy supply chain such as fuel purchase, transportation and storage, electric energy conversion and electric energy transmission in the power transmission and distribution processes, electric energy consumption of a power terminal and the like; the predictive load activity includes estimation and prediction of power consumption activity of the power system, power scheduling and operational decision activity to ensure reliability of the power supply.
And 204, obtaining one-dimensional convolution characteristics corresponding to the electric power activity data according to the electric power activity data and the characteristic extraction layer of the target measuring and calculating model.
The feature extraction layer of the target measuring and calculating model is used for extracting one-dimensional convolution features of the electric power activity data.
The feature extraction layer can comprise a convolution layer, a pooling layer and a flattening layer, wherein the convolution layer carries out convolution operation for a plurality of times on the electric power activity data through convolution check, and the features of the electric power activity data are fully extracted; the pooling layer is used for downsampling the features extracted by the convolution layer, so that the stability of the features is enhanced, and meanwhile, the parameter number of the feature extraction layer is reduced, so that the calculation complexity in the feature extraction process is reduced; the flattening layer is used for carrying out one-dimensional flattening treatment on the pooled features to obtain one-dimensional convolution features, and is suitable for the measuring and calculating process of the target decision layer.
And 206, obtaining target carbon emission measurement data according to the one-dimensional convolution characteristics and a target decision layer of the target measurement model.
The target carbon emission measurement data is used for representing the generated carbon emission amount of the target power system in the to-be-measured time period.
For example, the target decision layer may calculate the one-dimensional convolution feature by using a decision method including random forest, adaptive enhancement, decision tree, and the like, to obtain target carbon emission calculation data.
Further, the decision parameters in the target decision layer may be obtained after the historical power data training.
In the above-mentioned power system carbon emission amount calculation method, by acquiring the power activity data of the target power system, the power activity data is used to represent the power production activity, the power consumption activity, and the activity level of the predicted load activity of the target power system for generating carbon emission in the time period to be calculated; obtaining one-dimensional convolution characteristics corresponding to the electric power activity data according to the electric power activity data and a characteristic extraction layer of the target measuring and calculating model; obtaining target carbon emission measurement data according to the one-dimensional convolution characteristics and a target decision layer of a target measurement model, wherein the target carbon emission measurement data is used for representing the generated carbon emission of a target power system in a to-be-measured calculation time period; in the embodiment, the feature extraction layer of the target measuring and calculating model is used for carrying out convolution calculation on the electric power activity data in the time period to be measured and calculated, so that compared with the traditional technology, the required data size is smaller, the comprehensive features can be extracted from the smaller data, the data size and the calculation complexity in the measuring and calculating process are effectively reduced, and the measuring and calculating efficiency of the electric power system carbon emission measuring and calculating method is improved.
In one embodiment, as shown in fig. 3, according to the feature extraction layer of the power activity data and the target measurement model, obtaining a one-dimensional convolution feature corresponding to the power activity data includes:
And 302, arranging the electric power activity data in a matrix according to the electric power activity type to obtain activity matrix data.
The power activity data can be divided into power production activity data, power consumption activity data and predicted load activity data according to the power activity type, and the power activity data is matrixed to obtain activity matrix data with the shape of (n, 3).
Step 304, performing one-dimensional convolution calculation processing on the active matrix data to obtain convolution data.
The one-dimensional convolution calculation processing can be completed by using a convolution layer in the feature extraction layer. The one-dimensional convolution calculation process can be expressed as:
wherein x [ i ] represents the ith active matrix data for one-dimensional convolution calculation, y [ i ] represents the convolution data obtained by the ith active matrix data for one-dimensional convolution calculation, b represents the bias, w [ j ] represents the jth convolution kernel participating in one-dimensional convolution calculation, S represents the stride of the convolution calculation, and F represents the length of the convolution kernel.
Illustratively, the number of convolution kernels of the convolution layer is set to 128 according to the size of the active matrix data, the size of the convolution kernels is set to 3*3 according to the power activity class, the activation function selects a ReLU (Rectified Linear Units, linear rectification unit) function and an initial offset is set to 0, so that the one-dimensional convolution calculation processing is performed on the active matrix data to obtain convolution data with the shape of (128×3).
And 306, carrying out maximum pooling processing on the convolution data to obtain characteristic data.
The maximum pooling processing refers to that convolution data obtained by carrying out one-dimensional convolution calculation processing on the active matrix data is compared with adjacent data in pairs, larger data in the convolution data are reserved, and smaller data are discarded. The main characteristics in the convolution data are reserved through the maximum pooling treatment, and the obtained characteristic data can improve the measuring accuracy and the generalization capability of the target measuring model.
And 308, performing one-dimensional expansion on the feature data to obtain one-dimensional convolution features.
The one-dimensional expansion processing refers to flattening the feature data obtained by performing the maximum pooling processing on the convolution data into a one-dimensional array to adapt to the input form of a target decision layer of a target measuring and calculating model, and if the feature data with the shape of (64×3) is subjected to one-dimensional expansion, the one-dimensional convolution feature with the shape of (192×1) can be obtained by an exemplary method.
In this embodiment, the power activity data are arranged in a matrix according to the power activity type to obtain activity matrix data; carrying out one-dimensional convolution calculation processing on the active matrix data to obtain convolution data; carrying out maximum pooling treatment on the convolution data to obtain characteristic data; carrying out one-dimensional expansion on the feature data to obtain one-dimensional convolution features; according to the embodiment, the feature extraction layer based on convolution calculation is used for carrying out feature extraction on the electric power activity data, the calculation complexity of the feature extraction layer of the target measuring and calculating model is reduced on the basis of fully extracting the features, and meanwhile, one-dimensional convolution feature data with high fitting degree and good generalization performance is prepared for the target decision layer.
In one embodiment, based on the embodiment shown in FIG. 2, as shown in FIG. 4, the number of target calculation models is multiple; according to the feature extraction layer of the power activity data and the target measuring and calculating model, obtaining one-dimensional convolution features corresponding to the power activity data, wherein the one-dimensional convolution features comprise:
step 402, the electric power activity data are respectively input into the feature extraction layers of the target measuring and calculating models, and one-dimensional convolution features output by the feature extraction layers are obtained.
The characteristic extraction layer of each target measuring and calculating model is provided with respective convolution layer parameters, pooling layer parameters and flattening layer parameters.
Obtaining target carbon emission measurement data according to a one-dimensional convolution characteristic and a target decision layer of a target measurement model, wherein the method comprises the following steps:
step 404, inputting each one-dimensional convolution characteristic into a corresponding target decision layer of the target calculation model to obtain carbon emission calculation data output by each target decision layer.
Wherein each target decision layer has its own decision layer parameters.
Step 406, performing mean value calculation processing on the plurality of carbon emission measurement data to obtain target carbon emission measurement data.
In the embodiment, electric power activity data are respectively input into a feature extraction layer of each target measuring and calculating model to obtain one-dimensional convolution features output by each feature extraction layer, each one-dimensional convolution feature is respectively input into a target decision layer of a corresponding target measuring and calculating model to obtain carbon emission measuring and calculating data output by each target decision layer, and average value calculation processing is carried out on a plurality of carbon emission measuring and calculating data to obtain target carbon emission measuring and calculating data; the average value of the target carbon emission measurement data is measured and calculated for a plurality of times through a plurality of target measurement and calculation models, so that the problem that the generalization capability of the models is influenced due to local optimization in the running process of the models is avoided, and the accuracy of the carbon emission measurement method of the electric power system can be improved.
In one embodiment, as shown in fig. 5, acquiring power activity data of a target power system includes:
step 502, obtaining initial production activity data, initial consumption activity data and initial predicted load data of a target power system.
The initial production activity data, the initial consumption activity data and the initial predicted load data of the target power system respectively refer to the power production activity, the power consumption activity and the predicted load activity of the target power system, which generate carbon emission in a time period to be calculated, and are directly acquired according to fixed frequency.
And 504, performing null value removal processing on the initial production activity data, the initial consumption activity data and the initial predicted load data to obtain initial power activity data.
The terminal for collecting the initial production activity data, the initial consumption activity data and the initial prediction load data may collect null values due to data loss, equipment faults and the like, and the null values can have adverse effects on the measurement result of the target measurement model in the data processing and analyzing process, so that null value removal processing is required before the data enter the target measurement model. Null removal refers to deleting or replacing data containing null values from the data set with other values, so that the data set can be more complete, and subsequent model measurement is more accurate.
For example, if the overall null value is small, the data of the initial production activity data, the initial consumption activity data or the initial prediction load data containing the null value can be deleted directly, but if the null value is large, the direct deletion can affect the accuracy of the target measuring and calculating model, and constants such as a global average value, a median value or an average value of adjacent data can be used for filling the null value to keep the data distribution.
And step 506, performing standardization processing on the initial power activity data to obtain power activity data.
The normalization of the initial power activity data may be expressed as follows:
wherein x represents initial power activity data, μ represents a mean value of the initial power activity data, σ represents a standard deviation of the initial power activity data, x n And the power activity data is obtained by the normalization processing of the initial power activity data.
In the embodiment, the initial power activity data is obtained by performing null value removal processing on the acquired initial production activity data, initial consumption activity data and initial predicted load data, so that the influence of the null value on the measuring and calculating result of the target measuring and calculating model is avoided; the initial power activity data is subjected to standardized processing to obtain power activity data so as to improve the generalization and convergence speed of the model, and the power activity data available for the target measuring and calculating model is obtained by preprocessing the directly acquired data, so that the consistency and accuracy of the input data of the target measuring and calculating model are improved.
In one embodiment, as shown in fig. 6, the method for measuring carbon emission of an electric power system further includes:
step 602, obtaining a plurality of historical power activity data and historical carbon emission data corresponding to each historical power activity data.
Wherein the plurality of historical power activity data includes data acquired at a fixed frequency and preprocessed for power production activity, power consumption activity, and predicted load activity of the target power system that produce carbon emissions in a past period of time; the historical carbon emission data corresponding to each historical power activity data refers to actual carbon emission data obtained by measuring or recording the carbon emission of the power production activity, the power consumption activity and the predicted load activity.
Step 604, iteratively learning the initial measurement model by using each historical power activity data and the historical carbon emission data corresponding to each historical power activity data to obtain a target measurement model.
The initial measurement model may be a machine learning model capable of performing autonomous learning and improving performance by using each historical electric power activity data and the historical carbon emission data corresponding to each historical electric power activity data, and performing iterative learning on the initial measurement model means training the initial measurement model by using each historical electric power activity data and the historical carbon emission data corresponding to each historical electric power activity data, and continuously updating parameters between layers in the training process to obtain the target measurement model with optimal parameters.
The initial measuring and calculating model comprises a feature extraction layer and a target decision layer, wherein the feature extraction layer can be a feature extraction network based on convolution calculation, takes each historical electric power activity data and the historical carbon emission data corresponding to each historical electric power activity data as training data, carries out convolution operation through convolution check training data, and extracts convolution features of the training data; the target decision layer can be an initial decision tree model constructed based on a LightGBM (Light Gradient Boosting Machine, light gradient elevator) algorithm, the convolution features extracted by the feature extraction layer are input into the initial decision tree model, a new weak classifier is added into the initial decision tree model in each iteration to reduce the error of an iteration prediction result before the initial decision tree model, and the initial calculation model is gradually perfected through continuous iteration training to obtain an optimal model meeting expected conditions as the target calculation model.
In the embodiment, the target measuring and calculating model is obtained by performing iterative learning on the initial measuring and calculating model by using the obtained historical electric power activity data and the historical carbon emission data corresponding to the historical electric power activity data, and the target measuring and calculating model is obtained based on the data with lower obtaining difficulty and the initial measuring and calculating model which can be autonomously learned and improved in performance, so that the complexity of obtaining the target measuring and calculating model is effectively reduced, the measuring and calculating complexity of the carbon emission of the electric power system is reduced, and the efficiency of the carbon emission amount measuring and calculating method of the electric power system is improved.
In one embodiment, based on the embodiment shown in FIG. 6, as shown in FIG. 7, the number of target calculation models is multiple; iteratively learning the initial measurement model by utilizing each historical electric power activity data and the historical carbon emission data corresponding to each historical electric power activity data to obtain a target measurement model, wherein the method comprises the following steps of:
step 702, performing random extraction processing on the plurality of historical power activity data and the historical carbon emission data corresponding to each historical power activity data to obtain a plurality of training data sets.
The training data set is obtained by randomly extracting a plurality of historical electric power activity data and historical carbon emission data corresponding to each historical electric power activity data according to a fixed proportion.
For example, a plurality of historical power activity data and historical carbon emission data corresponding to each historical power activity data are taken as a source data set, the source data set is randomly divided into K mutually exclusive subsets with similar sizes, 1 of the K subsets is selected as a test data set at a time to test model performance, the remaining K-1 subsets are taken as training data sets, namely each training data set comprises (K-1)/K groups of historical power activity data in the source data set and the corresponding historical carbon emission data.
And step 704, performing iterative learning on the initial measurement model by utilizing each training data set to obtain a plurality of target measurement models.
And inputting 1 training data set to the initial measuring and calculating model each time, and performing feature extraction and parameter optimization on the input training data set by using the initial measuring and calculating model to obtain a target measuring and calculating model corresponding to the input training data set.
In the above embodiment, the random extraction processing is performed on the plurality of historical power activity data and the historical carbon emission data corresponding to each historical power activity data to obtain a plurality of training data sets, and each training data set is used for respectively performing iterative learning on the initial measurement model to obtain a plurality of target measurement models; in this way, the acquired historical power activity data and the corresponding historical carbon emission data are fully and effectively utilized, so that the data waste is reduced as much as possible, the target measuring and calculating model can use less data to acquire measuring and calculating results with higher accuracy, and the efficiency of the power system carbon emission amount measuring and calculating method is improved.
In one embodiment, as shown in fig. 8, the electric power system carbon emission measurement method includes:
step 802, acquiring a plurality of historical power activity data and historical carbon emission data corresponding to each historical power activity data.
Wherein the plurality of historical power activity data comprise data which are acquired according to fixed frequency, are subjected to null value removal processing and normalization processing and are used for generating power production activity, power consumption activity and predicted load activity of carbon emission of a target power system in a past time period;
the historical carbon emission data corresponding to each historical electric power activity data refers to data obtained by scaling real carbon emission data obtained by measuring or recording the historical electric power activity data to be within 10, so that the accuracy of training results is prevented from being influenced by excessive or insufficient numerical values, and the training speed is increased.
Step 804, performing random extraction processing on the plurality of historical power activity data and the historical carbon emission data corresponding to each historical power activity data to obtain a plurality of training data sets.
Illustratively, a plurality of historical power activity data and historical carbon emission data corresponding to each historical power activity data are used as a source data set, the source data set is randomly divided into 5 mutually exclusive subsets of similar sizes, 1 of the mutually exclusive subsets is selected as a test data set at a time to test model performance, and the remaining 4 subsets are used as training data sets.
And step 806, performing iterative learning on the initial measurement model by using each training data set to obtain a plurality of target measurement models.
Illustratively, the source data set is randomly divided into 5 mutually exclusive subsets with similar sizes, and 1 is selected as the test data set each time, so that 5 target measuring and calculating models can be obtained, and the process for obtaining the 1 st target measuring and calculating model comprises the following steps:
the 1 st subset of the source data set is selected as the test data set and the remaining 4 subsets are selected as the first training data set.
And using the convolution feature extraction network as a feature extraction layer of the initial measuring and calculating model, and inputting the first training data set into the feature extraction layer of the initial measuring and calculating model to obtain a first convolution feature.
The decision layer of the initial measurement model is built based on the LightGBM algorithm, the first convolution characteristic is input into the decision layer, and meanwhile, the optimal parameters of the decision layer of the initial measurement model and the residual errors of the current measurement result are determined from possible combination forms of preset parameters in a grid search mode.
Further exemplary, the initial measurement model decision layer may be set to include the following preset parameters: the leaf number is [3, 10, 20]The method comprises the steps of carrying out a first treatment on the surface of the Maximum depth value of [ -1,5, 10]The method comprises the steps of carrying out a first treatment on the surface of the The learning rate is 0.01,0.1]The method comprises the steps of carrying out a first treatment on the surface of the The maximum iteration number is 30, 100, 200]A grid search method is adopted to generate 54 combinations of parameters in total, and R of model results is compared 2 The value judges the optimal parameter combination model, and the evaluation and calculation method of the R2 model is as follows:
wherein: m is the number of first convolution features; y is i Historical carbon emission data corresponding to the ith first convolution feature;a measurement result obtained by utilizing the ith first convolution characteristic; y is i Is an average of historical carbon emission data in the first training dataset. R is R 2 The values reflect the goodness of fit of the model, with closer to 1 indicating better fitting of the model and worse fitting closer to 0.
Selecting R in preset parameter combinations 2 The initial measuring and calculating model with the highest value and residual error of the measuring and calculating result meeting the preset condition is taken as the 1 st target measuring and calculating model.
Step 808, obtaining initial production activity data, initial consumption activity data, and initial predicted load data of the target power system.
And step 810, performing null value removal processing on the initial production activity data, the initial consumption activity data and the initial predicted load data to obtain initial power activity data.
Step 812, the initial power activity data is normalized to obtain power activity data.
Step 814, the electric power activity data are respectively input to the feature extraction layers of the target measuring and calculating models, and one-dimensional convolution features output by the feature extraction layers are obtained.
Optionally, the process of obtaining the one-dimensional convolution feature output by each feature extraction layer includes: the electric power activity data are arranged in a matrix mode according to the electric power activity type to obtain activity matrix data; carrying out one-dimensional convolution calculation processing on the active matrix data to obtain convolution data; carrying out maximum pooling treatment on the convolution data to obtain characteristic data; carrying out maximum pooling treatment on the convolution data to obtain characteristic data; and carrying out one-dimensional expansion on the feature data to obtain one-dimensional convolution features.
Step 816, inputting each one-dimensional convolution characteristic into the corresponding target decision layer of the target calculation model to obtain the carbon emission calculation data output by each target decision layer.
Step 818, performing mean value calculation processing on the plurality of carbon emission measurement data to obtain target carbon emission measurement data.
According to the embodiment, the one-dimensional convolution characteristics corresponding to the power activity data are obtained according to the acquired power activity data and the characteristic extraction layer of the target measuring and calculating model; obtaining target carbon emission measurement data according to the one-dimensional convolution characteristics and a target decision layer of a target measurement model, wherein the target carbon emission measurement data is used for representing the generated carbon emission of a target power system in a to-be-measured calculation time period; in the embodiment, the one-dimensional convolution characteristics of the power activity data are extracted by utilizing the characteristic extraction layer of the target calculation model, the characteristics that the characteristics can be fully extracted from less data by utilizing convolution calculation are utilized, the difficulty of characteristic extraction is effectively reduced on the premise of ensuring calculation accuracy, meanwhile, the power activity data for calculating the target carbon emission calculation data are low in acquisition difficulty, the calculation efficiency of the target carbon emission calculation data can be improved, the decision layer of the calculation model is constructed by utilizing the LightGBM algorithm, meanwhile, the optimal parameters are determined by utilizing grid search, a plurality of target calculation models are constructed by fully utilizing training data, the calculation complexity is simplified, the generalization performance of the target calculation model is considered, and the calculation efficiency of the power system carbon emission measurement calculation method is further improved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides an electric power system carbon emission measuring device for realizing the electric power system carbon emission measuring method. The implementation of the solution provided by the device is similar to that described in the above method, so the specific limitation in the embodiments of the device for measuring carbon emission of electric power system provided below may be referred to the limitation of the method for measuring carbon emission of electric power system hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 9, there is provided an electric power system carbon emission measurement device including: an acquisition module 902, a feature extraction module 904, and a target measurement module 906, wherein:
an acquisition module 902, configured to acquire power activity data of a target power system, where the power activity data is used to represent an activity level of a power production activity, a power consumption activity, and a predicted load activity of the target power system that generate carbon emissions in a time period to be calculated;
the feature extraction module 904 is configured to obtain one-dimensional convolution features corresponding to the power activity data according to the power activity data and a feature extraction layer of the target measurement model;
the target calculating module 906 is configured to obtain target carbon emission calculating data according to the one-dimensional convolution feature and a target decision layer of the target calculating model, where the target carbon emission calculating data is used to represent a carbon emission generated by the target power system in a time period to be calculated.
In one embodiment, the feature extraction module 904 includes a convolution unit, a pooling unit and a flattening unit, where the convolution unit performs matrix arrangement on the power activity data according to the power activity type to obtain activity matrix data, and performs one-dimensional convolution calculation on the activity matrix data to obtain convolution data; the pooling unit carries out maximum pooling treatment on the convolution data to obtain characteristic data; and the flattening unit performs one-dimensional expansion on the characteristic data to obtain one-dimensional convolution characteristics.
In one embodiment, the number of the target measuring and calculating models is multiple, and the feature extraction module 904 is configured to input the power activity data to feature extraction layers of the target measuring and calculating models respectively, so as to obtain one-dimensional convolution features output by each feature extraction layer; the target calculation module 906 is configured to input each one-dimensional convolution feature into a target decision layer of a corresponding target calculation model, so as to obtain carbon emission calculation data output by each target decision layer; and carrying out average value calculation processing on the plurality of carbon emission measurement data to obtain target carbon emission measurement data.
In one embodiment, the acquiring module 902 is configured to acquire initial production activity data, initial consumption activity data, and initial predicted load data of the target power system; performing null value removal processing on the initial production activity data, the initial consumption activity data and the initial predicted load data to obtain initial power activity data; and carrying out standardization processing on the initial power activity data to obtain the power activity data.
In one embodiment, the power system carbon emission measurement device further includes a training module, wherein the training module is configured to obtain a plurality of historical power activity data and historical carbon emission data corresponding to each of the historical power activity data; and performing iterative learning on the initial measuring and calculating model by utilizing the historical electric power activity data and the historical carbon emission data corresponding to the historical electric power activity data to obtain a target measuring and calculating model.
In one embodiment, the number of target measurement models is a plurality; the training module performs random extraction processing on the plurality of historical power activity data and historical carbon emission data corresponding to each historical power activity data to obtain a plurality of training data sets; and respectively carrying out iterative learning on the initial measuring and calculating model by utilizing each training data set to obtain a plurality of target measuring and calculating models.
The above-described respective modules in the electric power system carbon emission measurement device may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 10. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing the power activity data of the target power system or the historical power activity data of the power system and the historical carbon emission data corresponding to each historical power activity data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a method for measuring carbon emission of an electric power system.
It will be appreciated by those skilled in the art that the structure shown in FIG. 10 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. A method for measuring carbon emissions in an electrical power system, the method comprising:
acquiring power activity data of a target power system, wherein the power activity data is used for representing power production activity, power consumption activity and activity level of predicted load activity of the target power system for generating carbon emission in a time period to be calculated;
obtaining one-dimensional convolution characteristics corresponding to the electric power activity data according to the electric power activity data and a characteristic extraction layer of a target measuring and calculating model;
Obtaining target carbon emission measurement data according to the one-dimensional convolution characteristics and a target decision layer of the target measurement model, wherein the target carbon emission measurement data is used for representing the generated carbon emission of the target power system in the to-be-measured calculation time period.
2. The method according to claim 1, wherein the obtaining, according to the feature extraction layer of the power activity data and the target measurement model, the one-dimensional convolution feature corresponding to the power activity data includes:
the electric power activity data are arranged in a matrix mode according to the electric power activity type to obtain activity matrix data;
carrying out one-dimensional convolution calculation processing on the active matrix data to obtain convolution data;
carrying out maximum pooling treatment on the convolution data to obtain characteristic data;
and carrying out one-dimensional expansion on the characteristic data to obtain the one-dimensional convolution characteristic.
3. The method of claim 1, wherein the number of target measurement models is a plurality; the step of obtaining the one-dimensional convolution characteristic corresponding to the electric power activity data according to the characteristic extraction layer of the electric power activity data and the target measuring and calculating model comprises the following steps:
respectively inputting the electric power activity data to the feature extraction layers of the target measuring and calculating models to obtain the one-dimensional convolution features output by the feature extraction layers;
The obtaining target carbon emission measurement data according to the one-dimensional convolution characteristic and a target decision layer of the target measurement model comprises the following steps:
inputting each one-dimensional convolution characteristic into the corresponding target decision layer of the target measuring and calculating model respectively to obtain carbon emission measuring and calculating data output by each target decision layer;
and carrying out average value calculation processing on the plurality of carbon emission measurement data to obtain the target carbon emission measurement data.
4. The method of claim 1, wherein the acquiring power activity data of the target power system comprises:
acquiring initial production activity data, initial consumption activity data and initial predicted load data of the target power system;
performing null value removal processing on the initial production activity data, the initial consumption activity data and the initial predicted load data to obtain initial power activity data;
and carrying out standardization processing on the initial power activity data to obtain the power activity data.
5. The method according to claim 1, wherein the method further comprises:
acquiring a plurality of historical power activity data and historical carbon emission data corresponding to each of the historical power activity data;
And performing iterative learning on the initial measuring and calculating model by utilizing the historical electric power activity data and the historical carbon emission data corresponding to the historical electric power activity data to obtain the target measuring and calculating model.
6. The method of claim 5, wherein the number of target measurement models is a plurality; the iterative learning is performed on an initial measurement model by using each historical electric power activity data and the historical carbon emission data corresponding to each historical electric power activity data to obtain the target measurement model, and the method comprises the following steps:
performing random extraction processing on the plurality of historical power activity data and historical carbon emission data corresponding to each historical power activity data to obtain a plurality of training data sets;
and respectively carrying out iterative learning on the initial measuring and calculating model by utilizing each training data set to obtain a plurality of target measuring and calculating models.
7. An apparatus for measuring carbon emissions in an electrical power system, the apparatus comprising:
an acquisition module for acquiring power activity data of a target power system, the power activity data being used for representing power production activity, power consumption activity and activity level of predicted load activity of the target power system for generating carbon emission in a time period to be calculated;
The feature extraction module is used for obtaining one-dimensional convolution features corresponding to the electric power activity data according to the electric power activity data and a feature extraction layer of the target measuring and calculating model;
the target measuring and calculating module is used for obtaining target carbon emission measuring and calculating data according to the one-dimensional convolution characteristics and a target decision layer of the target measuring and calculating model, wherein the target carbon emission measuring and calculating data are used for representing the carbon emission generated by the target power system in the time period to be measured.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310774596.XA CN116739867A (en) | 2023-06-27 | 2023-06-27 | Method and device for measuring carbon emission of electric power system and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310774596.XA CN116739867A (en) | 2023-06-27 | 2023-06-27 | Method and device for measuring carbon emission of electric power system and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116739867A true CN116739867A (en) | 2023-09-12 |
Family
ID=87905931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310774596.XA Pending CN116739867A (en) | 2023-06-27 | 2023-06-27 | Method and device for measuring carbon emission of electric power system and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116739867A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114118537A (en) * | 2021-11-09 | 2022-03-01 | 南京航空航天大学 | Combined prediction method for carbon emission of airspace flight |
| CN114548552A (en) * | 2022-02-21 | 2022-05-27 | 国网北京市电力公司 | Carbon emission prediction method and device, and electronic device |
| CN115423215A (en) * | 2022-10-13 | 2022-12-02 | 北京恒华龙信数据科技有限公司 | Carbon emission prediction method and system based on hybrid machine learning |
| CN115526296A (en) * | 2022-10-12 | 2022-12-27 | 广东工业大学 | Carbon emission prediction method based on deep learning |
| CN115860173A (en) * | 2022-10-21 | 2023-03-28 | 国网电力科学研究院武汉能效测评有限公司 | Construction and prediction method and medium of carbon emission prediction model based on Stacking algorithm |
| CN115860188A (en) * | 2022-11-11 | 2023-03-28 | 国网福建省电力有限公司营销服务中心 | Carbon emission prediction method and system, medium and electronic device |
| CN116108963A (en) * | 2022-12-08 | 2023-05-12 | 国网福建省电力有限公司经济技术研究院 | Electric power carbon emission prediction method and equipment based on integrated learning module |
-
2023
- 2023-06-27 CN CN202310774596.XA patent/CN116739867A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114118537A (en) * | 2021-11-09 | 2022-03-01 | 南京航空航天大学 | Combined prediction method for carbon emission of airspace flight |
| CN114548552A (en) * | 2022-02-21 | 2022-05-27 | 国网北京市电力公司 | Carbon emission prediction method and device, and electronic device |
| CN115526296A (en) * | 2022-10-12 | 2022-12-27 | 广东工业大学 | Carbon emission prediction method based on deep learning |
| CN115423215A (en) * | 2022-10-13 | 2022-12-02 | 北京恒华龙信数据科技有限公司 | Carbon emission prediction method and system based on hybrid machine learning |
| CN115860173A (en) * | 2022-10-21 | 2023-03-28 | 国网电力科学研究院武汉能效测评有限公司 | Construction and prediction method and medium of carbon emission prediction model based on Stacking algorithm |
| CN115860188A (en) * | 2022-11-11 | 2023-03-28 | 国网福建省电力有限公司营销服务中心 | Carbon emission prediction method and system, medium and electronic device |
| CN116108963A (en) * | 2022-12-08 | 2023-05-12 | 国网福建省电力有限公司经济技术研究院 | Electric power carbon emission prediction method and equipment based on integrated learning module |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116882790B (en) | Carbon emission equipment management method and system for mine ecological restoration area | |
| CN115563477B (en) | Harmonic data identification method, device, computer equipment and storage medium | |
| CN113642716A (en) | Depth variation autoencoder model training method, device, equipment and storage medium | |
| CN112215398A (en) | Power consumer load prediction model establishing method, device, equipment and storage medium | |
| CN117556369B (en) | Power theft detection method and system for dynamically generated residual error graph convolution neural network | |
| CN117913796A (en) | Power economic coupling coordination relation determining method, device, equipment and storage medium | |
| CN117056776A (en) | Carbon emission monitoring method, apparatus, device, medium and computer program product | |
| CN112508734A (en) | Method and device for predicting power generation capacity of power enterprise based on convolutional neural network | |
| CN115471098B (en) | Carbon emission amount acquisition method, carbon emission amount acquisition device, computer device, and storage medium | |
| CN116664368A (en) | Carbon footprint acquisition method, device, computer equipment and storage medium | |
| CN116245380A (en) | Method and device for determining service problems of target service and computer equipment | |
| CN116739867A (en) | Method and device for measuring carbon emission of electric power system and computer equipment | |
| CN116191398A (en) | Load prediction method, load prediction device, computer equipment and storage medium | |
| CN112256735B (en) | Power consumption monitoring method and device, computer equipment and storage medium | |
| CN117933677B (en) | Regional frequency modulation-based associated data prediction method and device for hydropower plant | |
| CN117114712A (en) | Power utilization side carbon monitoring method, model training method, device and computer equipment | |
| CN115544276B (en) | Metering device knowledge graph construction method and metering device archive checking method | |
| CN114154679B (en) | Spark-based PCFOA-KELM wind power prediction method and device | |
| CN116110630A (en) | Reactor core thermal power measurement method and device in DCS system | |
| CN117437104A (en) | County carbon emission prediction method, county carbon emission prediction device, county carbon emission prediction computer device, and county carbon emission prediction storage medium | |
| CN117057241A (en) | Frequency response characteristic modeling method, frequency response characteristic analysis method and device | |
| Liu et al. | Short-Term Load Prediction Based on Typical Daily Feature Selection and Time Convolutional Neural Network | |
| CN117952320A (en) | Method and device for metering carbon emission of production enterprise and computer equipment | |
| CN114352485A (en) | Wind speed prediction method and device for wind driven generator and computer equipment | |
| CN116911977A (en) | Virtual resource processing method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |