CN115831264A - Method for calculating regional carbon dioxide emission by using electric quantity consumption data - Google Patents
Method for calculating regional carbon dioxide emission by using electric quantity consumption data Download PDFInfo
- Publication number
- CN115831264A CN115831264A CN202211591850.4A CN202211591850A CN115831264A CN 115831264 A CN115831264 A CN 115831264A CN 202211591850 A CN202211591850 A CN 202211591850A CN 115831264 A CN115831264 A CN 115831264A
- Authority
- CN
- China
- Prior art keywords
- matrix
- regional
- data
- consumption data
- carbon dioxide
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for calculating regional carbon dioxide emission by using electric quantity consumption data, which belongs to the technical field of accounting carbon dioxide emission in the power industry. The problem that the existing carbon emission accounting method is low in data timeliness is solved, the release of energy statistical data, carbon emission data and the like is delayed, and the response to a real-time event is lacked.
Description
Technical Field
The invention belongs to the technical field of accounting of carbon dioxide emission in the power industry, and particularly relates to a method for calculating regional carbon dioxide emission by using electric quantity consumption data.
Background
The current international mainstream carbon emission accounting system mainly comprises an international universal IPCC system, an American EPA system based on IPCC system improvement of the United states environmental protection agency and an EEA system based on IPCC system improvement of the European environmental agency, and various accounting methods and guidelines currently issued by the government of China are based on the IPCC system. The IPCC national greenhouse gas list guide is a national list compiling method appointed and adopted by each contracting prescription of the United nations climate change framework convention, is issued by climate change special committees between United nations governments, is a national greenhouse gas emission list guide with highest acceptance and widest application range so far, divides carbon accounting into 5 major categories and 20 emission subclasses of energy, industrial process and product use, agriculture and forestry and other land application, wastes, and the like, systematically guides the aspects of data collection, methodology selection, uncertainty, quality assurance and the like, and mostly takes the IPCC guide as a standard in a greenhouse gas accounting system of each country in the world.
The main calculation method for regional carbon dioxide emission is an emission factor method based on an IPCC system, the method belongs to a calculation method, required data mainly comprises various fossil fuel consumption data, electric power purchase (call-in) quantity and the like, and data sources comprise government statistical data, enterprise ledger, statistical report data and the like. Basic research work involves the collection and organization of various types of statistical data.
The existing accounting method has the following problems: 1. the emission factor method is adopted to calculate regional carbon dioxide emission amount, the government statistical data are needed, and the publishing of the government statistical yearbook data needs a large amount of data collection work, so that the delay is usually more than 18 months, and the result of calculating regional carbon dioxide emission by adopting the emission factor method has long hysteresis; 2. energy consumption data available for government statistics yearbook are usually counted by year, so that regional carbon dioxide emission calculated by adopting an emission factor method is annual carbon dioxide emission, and emission data of month and shorter periods cannot be calculated.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a method for calculating regional carbon dioxide emission by using electric quantity consumption data, and solves the problems in the background art.
The purpose of the invention is realized as follows: a method of calculating regional carbon dioxide emissions using electricity consumption data, comprising the steps of:
s1: establishing a measuring and calculating model database;
s2: extracting regional power consumption data and regional GDP data which are identical in time series from the model database;
s3: extracting regional total energy consumption data from the model database;
s4: extracting regional clean power production volume data from the model database;
s5: and (4) measuring and calculating the carbon dioxide emission of the current area.
Further, the model database includes a calculation of the regional historical annual total carbon dioxide emission, regional power production data, regional power consumption data, regional clean power production data, regional GDP data, and regional total power consumption data.
Further, the regional power consumption data are combined into a characteristic matrix trE, the size of the matrix is (n, 1), and n is more than or equal to 7; and forming the GDP data of the region into a target matrix trG, wherein the size of the matrix is (n, 1), n is more than or equal to 7, and the row number n of the characteristic matrix trE is consistent with that of the target matrix trG.
Further, performing a first Lasso regression fitting on the feature matrix trE and the target matrix trG by a Lasso regression method with a penalty coefficient of 0.01 to obtain a model coefficient matrix trW gdp The matrix size is (1, 2).
Further, the regional power consumption data and the regional GDP data form a characteristic matrix treG, the size of the matrix is (n, 2), and n is more than or equal to 7; and (3) forming the region GDP data into a target matrix treN, wherein the size of the matrix is (n, 1), n is more than or equal to 7, and the row number n of the characteristic matrix treG is consistent with that of the target matrix treN.
Further, performing a second Lasso regression fitting on the characteristic matrix treG and the target matrix treN by a Lasso regression method with a penalty coefficient of 0.01 to obtain a model coefficient matrix trW energy The matrix size is (1, 3).
Further, new characteristic unit GDP energy consumption data are constructed by using the regional GDP data and the regional total energy consumption data to form a characteristic matrix treA, the size of the matrix is (n, 5), and n is more than or equal to 7; extracting regional carbon dioxide emission from the model database as a target matrix trC, wherein the size of the matrix is (n, 1), and n is more than or equal to 7; the number of rows n of the feature matrix trEA and the target matrix trC is kept the same.
Further, after the feature matrix trEA and the target matrix trC are subjected to third-time Lasso regression fitting by a Lasso regression method with a penalty coefficient of 0.01, a model coefficient matrix trW is obtained all The matrix size is (1, 6).
Further, based on the current power consumption data and the current clean power production data, calculating an energy consumption data analysis model and a multivariate fitting model of power consumption, energy consumption and carbon emission by using the power consumption data so as to measure and calculate the emission of carbon dioxide in the current area.
Further, carrying out 0-1 standardization processing on each column of data of the feature matrix trEG, so that the whole matrix data can fall in a 0-1 interval; wherein the 0-1 normalization is also called dispersion normalization, and the formula is as follows:
in the formula, x new Is the converted new value; x is a numerical value in the feature matrix; x is the number of min Is the minimum of the columns in the feature matrix; x is the number of max Is the maximum value of the columns in the feature matrix; the purpose of the 0-1 normalization process is to eliminate the effect of singular values in the feature data samples.
The invention has the beneficial effects that: the method applies the machine learning technology to the calculation of regional carbon dioxide emission, greatly improves the calculation efficiency, reduces the cost of manpower and material resources consumed by regional carbon emission calculation and has better economy compared with the existing branch emission factor calculation method. The problem that the existing carbon emission accounting method is low in data timeliness is solved, the release of energy statistical data, carbon emission data and the like is delayed (generally delayed by 18 months), and the response to a real-time event is lacked. The problem that the existing carbon emission accounting data is low in resolution is solved, and energy consumption data which can be used in a government statistical yearbook are provincial level and city level from the aspect of region and no more subdivided region exists; the time-based annual data and the seasonal monthly statistical data are not available, which causes great limitation to the carbon emission accounting work. By using the power consumption data, no matter the region and the time period are accurately defined, the data has the remarkable advantages of high resolution and strong real-time performance.
Drawings
FIG. 1 is a schematic monthly carbon emissions graph of the present invention;
FIG. 2 is a schematic view of a model deviation ratio analysis of the present invention;
fig. 3 is a flow chart of a method of use of the present invention.
Detailed Description
The invention will be described in further detail with reference to the following drawings, which are provided for the purpose of illustration and explanation of the invention more clearly.
As shown in fig. 1 to 3, the present embodiment discloses a method for calculating regional carbon dioxide emissions by using electricity consumption data, which comprises the following steps:
s1: building a measuring and calculating model database; the database covers the historical annual total carbon dioxide emission, regional power production data, regional power consumption data, regional clean power production data, regional GDP data and regional total power consumption data of a measured region.
S2: extracting from the model databaseThe regional power consumption data and the regional GDP data which are the same in time series; wherein, the regional power consumption data are combined into a characteristic matrix trE, the matrix size is (n, 1) and n is more than or equal to 7; forming a target matrix trG by using the regional GDP data, wherein the size of the matrix is (n, 1) and n is more than or equal to 7, and the row number n of the characteristic matrix trE and the row number n of the target matrix trG are required to be kept consistent; performing first Lasso regression fitting on the characteristic matrix trE and the target matrix trG by a Lasso regression method with a penalty coefficient of 0.01 to obtain a model coefficient matrix trW gdp The matrix size is (1, 2). The GDP data analysis model for calculating the power consumption data obtained after the matrix parameters are extracted is as follows:
GDP＝a×ele C +b
wherein the value of a is a model coefficient matrix trW gdp In [1,1 ]]A value of (d); ele C Is regional power consumption data; the value of b is a model coefficient matrix trW gdp In [1,2 ]]The value of (c).
The Lasso regression is a regression algorithm for regularizing a linear regression cost function, and is characterized in that variable screening and complexity adjustment are carried out while a generalized linear model is fitted. Therefore, the modeling prediction can be carried out by using Lasso regression whether the target dependent variable is continuous or binary or multivariate discrete.
The Lasso regression adds an L1 norm of an ω vector with a penalty coefficient λ as a penalty term on the basis of linear regression (meaning of the L1 norm is the sum of absolute values of each element of the vector ω), so the regularization mode is also called L1 regularization, and a cost function for solving a model coefficient matrix is as follows:
the size of ω for which the cost function is minimal is required:
in the formula, omega is a model coefficient matrix of a demand solution; n is the data characteristic quantity of the input Lasso model; omega T A transformation matrix of ω; y is i Training a target value for the ith model; x is the number of i Characteristic values trained for the ith model; lambda is a model penalty coefficient; | ω | non-calculation 1 The L1 norm, which is ω, is the maximum of the sum of the absolute values of the columns in the matrix.
The objective of the Lasso regression is to solve the model coefficient matrix ω, which can be solved using Lasso in the linear _ model module in the Scikit-leann toolkit.
S3: extracting regional power consumption data, regional GDP data and regional total power consumption data which are the same in time sequence from the model database; the method comprises the following steps that region power consumption data and region GDP data form a feature matrix treG, the size of the matrix is (n, 2), and n is larger than or equal to 7; forming a target matrix treN by using the regional GDP data, wherein the matrix size is (n, 1) and n is more than or equal to 7, and the row number n of the characteristic matrix treG and the row number n of the target matrix treN are required to be kept consistent; performing secondary Lasso regression fitting on the characteristic matrix treG and the target matrix treN by a Lasso regression method with the penalty coefficient of 0.01 to obtain a model coefficient matrix trW energy The matrix size is (1, 3). The energy consumption data analysis model calculated by the power consumption data after the matrix parameters are extracted is as follows:
EN c ＝a×ele C +b×G gdp +c
wherein the value of a is a model coefficient matrix trW energy In [1,1 ]]A value of (d); ele C Is regional power consumption data; the value of b is a model coefficient matrix trW energy In [1,2 ]]A value of (d); g gdp Is a region GDP; b is a model coefficient matrix trW energy In [1,3 ]]The value of (c).
The method comprises the following specific steps:
(1) The feature matrix trEG is formed by using the local power consumption data as the 1 st column of the feature matrix trEG and the local GDP data as the 2 nd column of the feature matrix trEG, with the data lengths of the two columns being the same.
(2) Performing 0-1 standardization processing on each column of data of the feature matrix treG to enable the whole matrix data to fall in a 0-1 interval; wherein the 0-1 normalization is also called dispersion normalization, and the formula is as follows:
in the formula, x new Is the converted new value; x is a numerical value in the feature matrix; x is the number of min Is the minimum of the columns in the feature matrix; x is the number of max Is the maximum value of the columns in the feature matrix. The purpose of the 0-1 normalization process is to eliminate the effect of singular values in the feature data samples.
S4: extracting region GDP data, region total energy consumption data, region power consumption data and region clean power production data from a model database, wherein new characteristic unit GDP energy consumption data is constructed by using the region GDP data and the region total energy consumption data to form a characteristic matrix treA, the size of the matrix is (n, 5), and n is more than or equal to 7; and extracting the regional carbon dioxide emission from the model database to serve as a target matrix trC, wherein the size of the matrix is (n, 1), and n is larger than or equal to 7. The line number n of the characteristic matrix trE and the line number n of the target matrix trG are required to be consistent; performing third Lasso regression fitting on the characteristic matrix treA and the target matrix trC by a Lasso regression method with a penalty coefficient of 0.01 to obtain a model coefficient matrix trW all The matrix size is (1, 6). After matrix parameters are extracted, a multi-element fitting model of power consumption, energy consumption and carbon emission can be obtained as follows:
E all ＝a×G gdp +b×EN all +c×ele c +d×ele q +e×U g +f
wherein the value of a is a model coefficient matrix trW all In [1,1 ]]A value of (d); g gdp Is regional GDP data; the value of b is a model coefficient matrix trW all In [1,2 ]]A value of (d); EN all Regional energy consumption data; the value of c is the model coefficient matrix trW all In [1,3 ]]A value of (d); ele c Is regional power consumption data; the value of d is the model coefficient matrix trW all In [1,4 ]]A value of (d); ele q Cleaning power production volume data for the area; e is a model coefficient matrix trW all In [1,5 ]]A value of (d); u shape g Is unit GDP energy consumption data; the value of f is the model coefficient matrix trW all In [1,6 ]]The value of (c).
The method comprises the following specific steps:
(1) And (3) constructing new characteristic data unit GDP energy consumption data by using the region GDP data and the region total energy consumption data, wherein the method comprises the following steps:
in the formula of U g Is unit GDP energy consumption data; g gbp Is regional GDP data; ENx ll Is regional energy consumption data.
(2) Taking the GDP data of the region as the 1 st column of the feature matrix treA; taking the regional energy consumption data as the 2 nd column of the characteristic matrix treA; taking the regional power consumption data as the 3 rd column of the characteristic matrix trEA; the regional clean power production data is used as the 4 th column of the characteristic matrix trEA; the unit GDP energy consumption data is taken as the 5 th column of the feature matrix trEA.
(3) Carrying out 0-1 standardization processing on each column of data of the feature matrix treA in the same way as the 0-1 standardization processing in the supplementary details in the step 3 to obtain the feature matrix treA with all data falling in the 0-1 interval;
as the improvement of the technical scheme, the real-time performance of regional carbon dioxide calculation is stronger, the collection frequency of electric power data can reach the level of minutes or even the level of seconds, and the data quality is high. According to the scheme, the total carbon dioxide emission amount of the region can be measured and calculated only by using the power consumption data.
S5: and (4) calculating a GDP data analysis model by using the power consumption data obtained in the steps 2, 3 and 4, calculating an energy consumption data analysis model by using the power consumption data and calculating the carbon dioxide emission amount of the current region by using a multi-fitting model of power consumption, energy consumption and carbon emission based on the current power consumption and the current clean power production.
The method comprises the following specific steps:
(1) Using current electricity consumption data ele c Construction of a prediction matrix trP gdp And (3) substituting the matrix size (1, 1) into the GDP data analysis model calculated by the power consumption data obtained in the step (2) to obtain the current GDP fitting value P gdp ；
(2) Use of current power consumption data ele c Fitting values P to column 1 and current GDP gbp Forming a prediction matrix trP for column 2 en And (3) calculating an energy consumption data analysis model by using the electric power consumption data obtained in the step (3) after the matrix size (1, 2) is subjected to 0-1 standardization process detailed in the step (3) to obtain the current energy consumption fitting value P en ；
(3) Fitting value P using current GDP gdp And the current energy consumption fitting value P en Constructing the current unit energy consumption fitting value P u ；
(4) Fitting value P using current GDP gdp Column 1; current energy consumption fitting value P en Column 2; current power consumption data ele c Column 3; current clean power production ele q Column 4; current unit energy consumption fitting value P u Constructing a prediction matrix trP for column 5 all And (4) performing 0-1 standardization treatment detailed in the step 3 on the matrix size (1, 5), and substituting the matrix size into the power consumption, energy consumption and carbon emission multi-element fitting model obtained in the step 4 to obtain the fitted current regional carbon dioxide emission.
Compared with the existing branch emission factor calculation method, the method greatly improves the calculation efficiency, reduces the cost of manpower and material resources consumed by the regional carbon emission calculation, and has better economy. Meanwhile, the method eliminates the dependence on the statistical data of the energy activities, solves the problem of hysteresis and long period (year) of regional carbon emission calculation by using the prior art due to the characteristic of real-time acquisition of power consumption data, greatly enhances the effectiveness of the management of the carbon emission implementation process by the industry management department, and can play an important role in the double-carbon target management work of China.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, and any person skilled in the art can substitute or change the technical solution and its concept within the technical scope of the present invention.
Claims (10)
1. A method of calculating regional carbon dioxide emissions using electricity consumption data, comprising the steps of:
s1: building a measuring and calculating model database;
s2: extracting regional power consumption data and regional GDP data with the same time series from the model database;
s3: extracting regional total energy consumption data from the model database;
s4: extracting regional clean power production volume data from the model database;
s5: and (4) measuring and calculating the carbon dioxide emission in the current period area.
2. The method of calculating regional carbon dioxide emissions using electricity consumption data according to claim 1, wherein: the model database comprises the data of measuring and calculating the historical annual total carbon dioxide emission of a region, regional power production data, regional power consumption data, regional clean power production data, regional GDP data and regional total power consumption data.
3. The method of calculating regional carbon dioxide emissions using electricity consumption data according to claim 1, wherein: forming the regional power consumption data into a characteristic matrix trE, wherein the matrix size is (n, 1) and n is more than or equal to 7; and forming the GDP data of the region into a target matrix trG, wherein the size of the matrix is (n, 1), n is more than or equal to 7, and the row number n of the characteristic matrix trE is consistent with that of the target matrix trG.
4. The method of calculating regional carbon dioxide emissions using electricity consumption data according to claim 3, wherein: performing first Lasso regression fitting on the characteristic matrix trE and the target matrix trG by a Lasso regression method with a penalty coefficient of 0.01 to obtain a model coefficient matrix trW gdp The matrix size is (1, 2).
5. The method of calculating regional carbon dioxide emissions using electricity consumption data according to claim 3, wherein: forming a characteristic matrix treG by using the regional power consumption data and the regional GDP data, wherein the matrix size is (n, 2) and n is more than or equal to 7; and (3) forming the region GDP data into a target matrix treN, wherein the size of the matrix is (n, 1), n is more than or equal to 7, and the row number n of the characteristic matrix treG is consistent with that of the target matrix treN.
6. The method of calculating regional carbon dioxide emissions using electricity consumption data according to claim 5, wherein: performing secondary Lasso regression fitting on the characteristic matrix treG and the target matrix treN by a Lasso regression method with a penalty coefficient of 0.01 to obtain a model coefficient matrix trW energy The matrix size is (1, 3).
7. The method of calculating regional carbon dioxide emissions using electricity consumption data according to claim 1, wherein: constructing new characteristic unit GDP energy consumption data by using the regional GDP data and the regional total energy consumption data to form a characteristic matrix treA, wherein the matrix size is (n, 5) and n is more than or equal to 7; extracting regional carbon dioxide emission from the model database as a target matrix trC, wherein the size of the matrix is (n, 1), and n is more than or equal to 7; the number of rows n of the feature matrix trEA and the target matrix trC is kept the same.
8. The method of calculating regional carbon dioxide emissions using electricity consumption data according to claim 7, wherein: performing a third-time Lasso regression fitting on the characteristic matrix treA and the target matrix trC by a Lasso regression method with a penalty coefficient of 0.01 to obtain a model coefficient matrix trW all The matrix size is (1, 6).
9. The method of calculating regional carbon dioxide emissions using electricity consumption data according to claim 1, wherein: and calculating an energy consumption data analysis model and a multivariate fitting model of power consumption, energy consumption and carbon emission by using the power consumption data based on the current power consumption data and the current clean power production data so as to measure and calculate the emission of carbon dioxide in the current region.
10. The method of calculating regional carbon dioxide emissions using electricity consumption data according to claim 5, wherein: carrying out 0-1 standardization processing on each column of data of the feature matrix trEG, so that the whole matrix data can fall in a 0-1 interval; wherein the 0-1 normalization is also called dispersion normalization, and the formula is as follows:
in the formula, x new Is the converted new value; x is a numerical value in the feature matrix; x is a radical of a fluorine atom min Is the minimum of the columns in the feature matrix; x is the number of max Is the maximum value of the columns in the feature matrix; the purpose of the 0-1 normalization process is to eliminate the effect of singular values in the feature data samples.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211591850.4A CN115831264A (en) | 2022-12-09 | 2022-12-09 | Method for calculating regional carbon dioxide emission by using electric quantity consumption data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211591850.4A CN115831264A (en) | 2022-12-09 | 2022-12-09 | Method for calculating regional carbon dioxide emission by using electric quantity consumption data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115831264A true CN115831264A (en) | 2023-03-21 |
Family
ID=85546625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211591850.4A Pending CN115831264A (en) | 2022-12-09 | 2022-12-09 | Method for calculating regional carbon dioxide emission by using electric quantity consumption data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115831264A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167669A (en) * | 2023-04-26 | 2023-05-26 | 国网浙江省电力有限公司金华供电公司 | Carbon emission assessment method based on power consumption regression |
-
2022
- 2022-12-09 CN CN202211591850.4A patent/CN115831264A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167669A (en) * | 2023-04-26 | 2023-05-26 | 国网浙江省电力有限公司金华供电公司 | Carbon emission assessment method based on power consumption regression |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110264001A (en) | Electro-load forecast method based on multiple timings | |
| CN110716512A (en) | Environmental protection equipment performance prediction method based on coal-fired power plant operation data | |
| CN112801388B (en) | Power load prediction method and system based on nonlinear time series algorithm | |
| CN114169574A (en) | Method for predicting atmospheric pollution through industrial operation power index | |
| CN115860797B (en) | Electric quantity demand prediction method suitable for new electricity price reform situation | |
| CN115831264A (en) | Method for calculating regional carbon dioxide emission by using electric quantity consumption data | |
| Wang et al. | Reliable model of reservoir water quality prediction based on improved ARIMA method | |
| CN111600300A (en) | Robust optimization scheduling method considering wind power multivariate correlation ellipsoid set | |
| CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
| CN114140176A (en) | Adjustable capacity prediction method and device for load aggregation platform | |
| CN116187823A (en) | Regional carbon emission calculation method and device based on electric power data | |
| CN117251672A (en) | Regional industry multi-dimensional energy carbon emission calculation method and device based on electric power data | |
| CN116826745B (en) | Layered and partitioned short-term load prediction method and system in power system background | |
| CN107301499B (en) | Distribution feeder statistical line loss rate data cleaning method based on AMI data | |
| CN113344391A (en) | Method for evaluating artificial intelligence enterprise innovation efficiency based on DEA improved model | |
| CN116307298B (en) | Combined carbon emission prediction method based on multi-source heterogeneous tensor data | |
| CN117408833A (en) | Short-term load prediction method based on load identification | |
| CN110414776B (en) | Quick response analysis system for power utilization characteristics of different industries | |
| US20240097444A1 (en) | Hybrid system and method for distributed virtual power plants integrated intelligent net zero | |
| CN116384622A (en) | Carbon emission monitoring method and device based on electric power big data | |
| CN115713252A (en) | Water, wind, light and energy storage multi-energy complementary system comprehensive benefit evaluation scheme optimization method | |
| CN111027816B (en) | Photovoltaic power generation efficiency calculation method based on data envelope analysis | |
| CN117495435B (en) | FIG-IRELM-based sales volume interval prediction method and device | |
| Liu | Price Prediction of TSLA, BYD and NIO Based on ARIMA Model | |
| CN116050482A (en) | Rural area electric energy substitution potential prediction method |
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 |