CN117172347A - Carbon emission prediction method based on energy big data - Google Patents
Carbon emission prediction method based on energy big data Download PDFInfo
- Publication number
- CN117172347A CN117172347A CN202310814459.4A CN202310814459A CN117172347A CN 117172347 A CN117172347 A CN 117172347A CN 202310814459 A CN202310814459 A CN 202310814459A CN 117172347 A CN117172347 A CN 117172347A
- Authority
- CN
- China
- Prior art keywords
- carbon emission
- prediction
- data
- energy
- impact
- 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
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 177
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 176
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000012937 correction Methods 0.000 claims abstract description 5
- 238000004088 simulation Methods 0.000 claims abstract description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 238000007637 random forest analysis Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000001364 causal effect Effects 0.000 claims description 8
- 238000007621 cluster analysis Methods 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 239000002737 fuel gas Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a carbon emission prediction method based on energy big data, which relates to the technical field of carbon emission prediction and comprises the following steps: s1, integrating carbon emission influence factor data; s2, constructing a carbon emission prediction model; s3, training a prediction model and performing impact simulation; s4, impact analysis of carbon emission prediction; s5, carbon emission prediction and result correction. According to the carbon emission prediction method based on the energy big data, a mathematical equation relation is established through researching the relation between the preliminary prediction of carbon emission and impact prediction, a preliminary prediction result of carbon emission is calculated, the preliminary prediction result is corrected by utilizing the mathematical equation relation, a carbon emission prediction model is built, impact of each influence factor on the prediction model under different conditions is simulated, influence of differences of carbon emission influence factors of different fields and different equipment on the prediction model is avoided, interference on carbon emission prediction is avoided, and accuracy and reliability of the carbon emission prediction result are improved.
Description
Technical Field
The invention relates to the technical field of carbon emission prediction, in particular to a carbon emission prediction method based on energy big data.
Background
The large energy data is related technologies and applications for comprehensively acquiring, processing, analyzing and applying energy data such as electric power, fuel gas, petroleum and the like and related fields such as economy, population, geography, climate and the like. With the continuous penetration of the technology and application of the 5G, AI intelligent and internet of things, on the basis of mobile internet and enterprise informatization, the technology of large data, blockchain and the like is relied on, the collection, analysis and fusion of structured and unstructured information are realized, and the timely, accurate, credible, available and traceable mass data collection is realized. The method not only deeply fuses the energy production, management, consumption and related technical revolution with big data ideas, but also can find a new direction for the development of the energy industry and the innovation of business modes.
For example, patent document 202111516267.2 discloses a method for predicting carbon emission in energy industry based on electric power data, and the patent constructs a conversion relation between electric power data-energy consumption data-carbon emission in energy industry, improves a carbon emission management function based on electric power data in energy industry, predicts and pre-warns carbon emission of enterprises, fully digs carbon emission reduction potential of enterprises, predicts and pre-warns carbon emission of important energy enterprises, finally realizes data-driven multi-industry energy consumption and carbon emission panoramic prediction, and simultaneously digs carbon emission reduction potential of important energy enterprises for service, and develops energy conservation and consumption reduction.
However, the carbon emission prediction method similar to the above-mentioned document still has the following drawbacks:
the existing carbon emission prediction method generally carries out carbon emission prediction by constructing a carbon emission prediction model and substituting related parameters and variable calculation, and the accuracy and reliability of a carbon emission prediction result directly depend on the prediction model, but as the carbon emission influence factors of different fields and even different equipment have differences, the prediction model is easily influenced by the differences, thereby causing interference to the carbon emission prediction and influencing the accuracy and reliability of the carbon emission prediction result.
Therefore, there is an urgent need to improve the shortcomings, and the present invention is to research and improve the existing structure and shortcomings, and provide a carbon emission prediction method based on big energy data.
Disclosure of Invention
The invention aims to provide a carbon emission prediction method based on energy big data, so as to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions: a carbon emission prediction method based on energy big data comprises the following specific steps:
s1, integrating carbon emission influence factor data:
analyzing and determining carbon emission influencing factors in the energy industry, connecting an energy information database, calling relevant information data about the carbon emission influencing factors in the database, establishing an energy information data set, setting a plurality of subsets in the energy information data set, placing different carbon emission influencing factor information data in the subsets, and establishing information subsets of different carbon emission influencing factor categories;
s2, constructing a carbon emission prediction model:
cleaning and correcting data in the data subset, judging the importance degree of influence factors through a random forest algorithm, sorting the influence factors according to importance, selecting main influence factors, generating a feature matrix, and constructing a carbon emission prediction model;
s3, training a prediction model and performing impact simulation:
training the carbon emission prediction model according to the feature matrix to check the carbon emission prediction model, performing preliminary prediction of carbon emission according to the numerical value of each input influence factor after training, adjusting the parameters of the influence factors, simulating impact under different conditions, and performing carbon emission prediction;
s4, impact analysis of carbon emission prediction:
researching the relation between preliminary prediction and impact prediction of carbon emission, analyzing impact conditions and change rules of influencing factors by combining energy data, determining the internal relevance of the two by cluster analysis and association rule analysis, drawing a causal relation graph, and establishing a mathematical equation relation;
s5, carbon emission prediction and result correction:
and (3) transferring energy data in the energy information database, substituting the energy data into a carbon emission prediction model to calculate a preliminary prediction result of carbon emission, correcting the preliminary prediction result by utilizing a mathematical equation relation, removing interference caused by impact of influencing factors on the carbon emission prediction, and calculating a final carbon emission prediction result.
Further, in the step S1, the energy information data set { Edb _co2} = { Δco2_1} + { Δco2_2} + { Δco2_3} + … + { Δco2_n }, where co2_1, co2_2, co2_3, …, and co2_n respectively represent different carbon emission influencing factors, { Δco2_1}, { Δco2_2}, { Δco2_3}, …, and { Δco2_n } respectively represent information subsets corresponding to the different influencing factors.
Further, in the step S1, the carbon emission influencing factor information data in the same information subset are independent and do not interfere with each other, and the carbon emission influencing factor information data in different information subsets are not overlapped and interacted with each other.
Further, the specific operation of the random forest algorithm in step S2 is to combine a plurality of decision trees together, and each time the subset of data is randomly selected with a put back, and part of the features are randomly selected as input.
Further, the random forest algorithm in step S2 is a Bagging algorithm using a decision tree as an estimator, the final result is counted by a combiner, the combiner selects a plurality of classification results as the final result in the classification problem, and averages a plurality of regression results as the final result in the regression problem.
Further, in the step S2, the ranking of the influencing factors takes importance as a ranking basis, and the ranking rule from big importance to small importance is followed, the higher the ranking result of the influencing factors is, the higher the importance degree of the influencing factors is, otherwise, the lower the ranking result is, the lower the importance degree of the influencing factors is.
Further, the main influencing factor selection basis in the step S2 is the sorting result of the influencing factors, and the main influencing factor refers to the influencing factor with the front sorting result and high importance.
Further, the formula of the carbon emission prediction in the step S3 is as follows:
wherein C is the carbon emission prediction result, i=1, 2, 3, …, n, k is the importance parameter, P i Carbon emission coefficient, D, being the i-th major contributor i Consumption as the i-th main influencing factor.
Further, the operation of the cluster analysis in the step S4 is to classify the data of the preliminary prediction and the impact prediction into different classes or clusters, and then combine the classification results to analyze, and the class required to be classified by the cluster is unknown.
Further, the operation of association rule analysis in step S4 is to find frequent patterns, associations, correlations or causal structures existing between the preliminary predictions and the impact predictions in the preliminary prediction and impact prediction data.
The invention provides a carbon emission prediction method based on energy big data, which has the following beneficial effects: according to the method, the influence carbon emission factors of the energy industry are determined through analysis, the energy information database is connected to obtain data, an energy information data set and information subsets of different carbon emission influence factor categories are established, importance degrees of the influence factors are judged through a random forest algorithm, main influence factors are selected through sequencing, a characteristic matrix is generated, a carbon emission prediction model is built, model training is conducted, initial prediction of carbon emission is conducted after training, parameters of the influence factors are adjusted, impact is simulated, carbon emission prediction is conducted, the relation between the initial prediction of carbon emission and the impact prediction is researched, impact conditions and change rules of the influence factors are analyzed, a mathematical equation relation is established after cluster analysis and association rule analysis, the energy data are substituted into the carbon emission prediction model to calculate a preliminary prediction result of carbon emission, the mathematical equation relation is utilized to correct the preliminary prediction result to obtain a final carbon emission prediction result, the improved carbon emission prediction method not only builds a carbon emission prediction model, impact on the prediction model under different conditions is simulated, the influence on the carbon emission influence factors in different fields and different equipment is avoided, and the reliability of the prediction model is improved, and the carbon emission reliability is prevented.
Drawings
FIG. 1 is a schematic diagram of the overall operation flow of a carbon emission prediction method based on energy big data;
FIG. 2 is a schematic diagram of the operation flow of step S1 of the carbon emission prediction method based on the big energy data of the present invention;
FIG. 3 is a schematic diagram of the operation flow of step S2 of the carbon emission prediction method based on the big energy data according to the present invention;
FIG. 4 is a schematic diagram of the operation flow of step S3 of the carbon emission prediction method based on the big energy data according to the present invention;
FIG. 5 is a schematic diagram of the operation flow of step S4 of the carbon emission prediction method based on the big energy data according to the present invention;
fig. 6 is a schematic diagram of a process flow of step S5 of the carbon emission prediction method based on energy big data according to the present invention.
Detailed Description
Embodiments of the present invention are described in further detail below with reference to the accompanying drawings and examples. The following examples are illustrative of the invention but are not intended to limit the scope of the invention.
As shown in fig. 1 to 6, a carbon emission prediction method based on energy big data includes the following specific steps:
s1, integrating carbon emission influence factor data:
analyzing and determining carbon emission influencing factors in the energy industry, connecting an energy information database, calling relevant information data about the carbon emission influencing factors in the database, establishing an energy information data set, setting a plurality of subsets in the energy information data set, placing different carbon emission influencing factor information data in the subsets, establishing information subsets of different carbon emission influencing factor categories, wherein the carbon emission influencing factor information data in the same information subset are mutually independent and mutually noninterfere, and the carbon emission influencing factor information data in the different information subsets are not overlapped and interacted;
the energy information data set { Edb _co2} = { Δco2_1} + { Δco2_2} + { Δco2_3} + { Δco2_n }, wherein co2_1, co2_2, co2_3, …, co2_n respectively represent different carbon emission influencing factors, { Δco2_1}, { Δco2_2}, { Δco2_3}, …, { Δco2_n } respectively represent information subsets corresponding to the different influencing factors;
s2, constructing a carbon emission prediction model:
cleaning and correcting data in the data subset, judging the importance degree of influence factors through a random forest algorithm, sorting the influence factors according to importance, selecting main influence factors, generating a feature matrix, and constructing a carbon emission prediction model;
the specific operation of the random forest algorithm is that a plurality of decision trees are combined together, each time, a data subset is randomly selected with a put back, and part of characteristics are randomly selected as input; the random forest algorithm is a Bagging algorithm taking a decision tree as an estimator, the final result is counted through a combiner, the combiner selects most classification results as the final result in the classification problem, and averages a plurality of regression results as the final result in the regression problem;
the influence factor ranking takes importance as a ranking basis, and follows a ranking rule with importance from big to small, the higher the ranking result of the influence factor is, the higher the importance degree of the influence factor is, otherwise, the lower the ranking result is, the lower the importance degree of the influence factor is; the main influence factor is selected according to the sorting result of the influence factors, and the main influence factor refers to the influence factor with the front sorting result and high importance;
s3, training a prediction model and performing impact simulation:
training the carbon emission prediction model according to the feature matrix to check the carbon emission prediction model, performing preliminary prediction of carbon emission according to the numerical value of each input influence factor after training, adjusting the parameters of the influence factors, simulating impact under different conditions, and performing carbon emission prediction;
the carbon emission prediction formula is as follows:
wherein C is the carbon emission prediction result, i=1, 2, 3, …, n, k is the importance parameter, P i Carbon emission coefficient, D, being the i-th major contributor i Consumption as the i-th main influencing factor;
s4, impact analysis of carbon emission prediction:
researching the relation between preliminary prediction and impact prediction of carbon emission, analyzing impact conditions and change rules of influencing factors by combining energy data, determining the internal relevance of the two by cluster analysis and association rule analysis, drawing a causal relation graph, and establishing a mathematical equation relation;
the operation of cluster analysis is to classify the data of preliminary prediction and impact prediction into different classes or clusters, and then analyze the data by combining the classification results, wherein the classes required to be classified by the clusters are unknown; the operation of association rule analysis is to find frequent patterns, associations, correlations, or causal structures existing between preliminary predictions and impact predictions in the preliminary prediction and impact prediction data;
s5, carbon emission prediction and result correction:
and (3) transferring energy data in the energy information database, substituting the energy data into a carbon emission prediction model to calculate a preliminary prediction result of carbon emission, correcting the preliminary prediction result by utilizing a mathematical equation relation, removing interference caused by impact of influencing factors on the carbon emission prediction, and calculating a final carbon emission prediction result.
In summary, as shown in fig. 1 to 6, the carbon emission prediction method based on the energy big data includes the following specific steps:
s1, integrating carbon emission influence factor data:
analyzing and determining carbon emission influencing factors in the energy industry, connecting an energy information database, calling relevant information data about the carbon emission influencing factors in the database, establishing an energy information data set, setting a plurality of subsets in the energy information data set, placing different carbon emission influencing factor information data in the subsets, and establishing information subsets of different carbon emission influencing factor categories; the carbon emission influence factor information data in the same information subset are mutually independent and mutually noninterfere, and the carbon emission influence factor information data in different information subsets are not overlapped and interacted;
the energy information data set { Edb _co2} = { Δco2_1} + { Δco2_2} + { Δco2_3} + { Δco2_n }, wherein co2_1, co2_2, co2_3, …, co2_n respectively represent different carbon emission influencing factors, { Δco2_1}, { Δco2_2}, { Δco2_3}, …, { Δco2_n } respectively represent information subsets corresponding to the different influencing factors;
s2, constructing a carbon emission prediction model:
the data in the data subset is cleaned and corrected, the importance degree of the influence factors is judged through a random forest algorithm, the specific operation of the random forest algorithm is to combine a plurality of decision trees, each time the data subset is randomly selected with a put back, and part of characteristics are randomly selected as input; the random forest algorithm is a Bagging algorithm taking a decision tree as an estimator, the final result is counted by a combiner, the combiner selects most classification results as the final result in the classification problem, in the regression problem, averages a plurality of regression results as the final result, the influence factors are ranked according to importance, the influence factors are ranked according to the importance as ranking basis, and the ranking rule from big importance to small importance is followed, the ranking result of the influence factors indicates that the higher the importance degree of the influence factors is, otherwise, the lower the importance degree of the influence factors is indicated after the ranking result is, the main influence factors are selected, the selected basis of the main influence factors is the ranking result of the influence factors is the influence factors with the front ranking result and the high importance, the feature matrix is generated, and the carbon emission prediction model is constructed;
s3, training a prediction model and performing impact simulation:
training the carbon emission prediction model according to the feature matrix to check the carbon emission prediction model, performing preliminary prediction of carbon emission according to the numerical value of each input influence factor after training, adjusting the parameters of the influence factors, simulating impact under different conditions, and performing carbon emission prediction;
the carbon emission prediction formula is as follows:
wherein C is the carbon emission prediction result, i=1, 2, 3, …, n, k is the importance parameter, P i Carbon emission coefficient, D, being the i-th major contributor i Consumption as the i-th main influencing factor;
s4, impact analysis of carbon emission prediction:
researching the relation between the preliminary prediction of carbon emission and impact prediction, analyzing the impact condition and the change rule of influencing factors by combining energy data, classifying the data of the preliminary prediction and the impact prediction into different classes or clusters through cluster analysis and association rule analysis, analyzing by combining the classification result, wherein the class required to be classified by the clusters is unknown, searching the frequent mode, association, correlation or causal structure existing between the preliminary prediction and the impact prediction in the data of the preliminary prediction and the impact prediction, determining the internal association of the preliminary prediction and the impact prediction, drawing a causal relation graph, and establishing a mathematical equation relation;
s5, carbon emission prediction and result correction:
and (3) transferring energy data in the energy information database, substituting the energy data into a carbon emission prediction model to calculate a preliminary prediction result of carbon emission, correcting the preliminary prediction result by utilizing a mathematical equation relation, removing interference caused by impact of influencing factors on the carbon emission prediction, and calculating a final carbon emission prediction result.
The invention determines the influence carbon emission factors of the energy industry through analysis, and connects the energy information database to retrieve data, so as to establish an energy information data set and information subsets of different carbon emission influence factor types, and judges the importance degree of the influence factors through a random forest algorithm, then orders and selects main influence factors, generates a characteristic matrix, builds a carbon emission prediction model, carries out model training, carries out preliminary prediction of carbon emission after training, adjusts parameters of the influence factors again, simulates impact and carries out carbon emission prediction, researches the relation between the preliminary prediction of carbon emission and the impact prediction, analyzes the impact condition and the change rule of the influence factors, establishes a mathematical equation relation after cluster analysis and association rule analysis, substitutes the energy data into a carbon emission prediction model to calculate the preliminary prediction result of carbon emission, corrects the preliminary prediction result by utilizing the mathematical equation relation to obtain the final carbon emission prediction result, and the improved carbon emission prediction method not only builds a carbon emission prediction model, but also simulates the impact on the prediction model caused by the influence factors under different conditions, avoids the influence of carbon emission on the prediction model, and avoids the influence of different equipment on the carbon emission of the prediction model, thereby improving the accuracy and the reliability of the carbon emission prediction result, and the carbon emission prediction result is prevented from being affected by the improved
The embodiments of the invention have been presented for purposes of illustration and description, and are not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.
Claims (10)
1. The carbon emission prediction method based on the energy big data is characterized by comprising the following specific steps:
s1, integrating carbon emission influence factor data:
analyzing and determining carbon emission influencing factors in the energy industry, connecting an energy information database, calling relevant information data about the carbon emission influencing factors in the database, establishing an energy information data set, setting a plurality of subsets in the energy information data set, placing different carbon emission influencing factor information data in the subsets, and establishing information subsets of different carbon emission influencing factor categories;
s2, constructing a carbon emission prediction model:
cleaning and correcting data in the data subset, judging the importance degree of influence factors through a random forest algorithm, sorting the influence factors according to importance, selecting main influence factors, generating a feature matrix, and constructing a carbon emission prediction model;
s3, training a prediction model and performing impact simulation:
training the carbon emission prediction model according to the feature matrix to check the carbon emission prediction model, performing preliminary prediction of carbon emission according to the numerical value of each input influence factor after training, adjusting the parameters of the influence factors, simulating impact under different conditions, and performing carbon emission prediction;
s4, impact analysis of carbon emission prediction:
researching the relation between preliminary prediction and impact prediction of carbon emission, analyzing impact conditions and change rules of influencing factors by combining energy data, determining the internal relevance of the two by cluster analysis and association rule analysis, drawing a causal relation graph, and establishing a mathematical equation relation;
s5, carbon emission prediction and result correction:
and (3) transferring energy data in the energy information database, substituting the energy data into a carbon emission prediction model to calculate a preliminary prediction result of carbon emission, correcting the preliminary prediction result by utilizing a mathematical equation relation, removing interference caused by impact of influencing factors on the carbon emission prediction, and calculating a final carbon emission prediction result.
2. The method according to claim 1, wherein the energy information data set { Edb _co2} = { Δco2_1} + { Δco2_2} + { Δco2_3} + … + { Δco2_n }, wherein co2_1, co2_2, co2_3, …, and co2_n represent different carbon emission influencing factors, and { Δco2_1}, { Δco2_2}, { Δco2_3}, …, { Δco2_n } represent information subsets corresponding to the different influencing factors, respectively.
3. The method for predicting carbon emission based on big energy data according to claim 1, wherein the carbon emission influencing factor information data in the same information subset in step S1 are independent and non-interfering, and the carbon emission influencing factor information data in different information subsets are not overlapped and interacted.
4. The method for predicting carbon emissions based on big energy data according to claim 1, wherein the specific operation of the random forest algorithm in step S2 is to combine a plurality of decision trees, and each time the subset of data is randomly selected with a put back, and part of the features are randomly selected as input.
5. The method for predicting carbon emission based on big energy data as set forth in claim 4, wherein the random forest algorithm in step S2 is a Bagging algorithm using a decision tree as an estimator, the final result is counted by a combiner, the combiner selects a majority of classification results as the final result in the classification problem, and averages a plurality of regression results as the final result in the regression problem.
6. The method for predicting carbon emission based on big energy data according to claim 1, wherein the ranking of the influencing factors in step S2 takes importance as a ranking basis, and follows a ranking rule with big importance to small importance, the higher the ranking result of the influencing factors is, the higher the importance of the influencing factors is, and conversely, the lower the ranking result is, the lower the importance of the influencing factors is.
7. The method for predicting carbon emissions based on big energy data as claimed in claim 6, wherein the main influencing factor in step S2 is selected based on the ranking result of influencing factors, and the main influencing factor refers to the influencing factor with the ranking result being the front and high importance.
8. The method for predicting carbon emissions based on energy big data according to claim 1, wherein the formula for predicting carbon emissions in step S3 is as follows:
wherein C is the carbon emission prediction result, i=1, 2, 3, …, n, k is the importance parameter, P i Carbon emission coefficient, D, being the i-th major contributor i Consumption as the i-th main influencing factor.
9. The method for predicting carbon emissions based on big energy data according to claim 1, wherein the operation of the clustering analysis in step S4 is to classify the data of preliminary prediction and impact prediction into different classes or clusters, and analyze the data in combination with the classification result, and the class required to be classified by the clustering is unknown.
10. The method according to claim 1, wherein the operation of association rule analysis in step S4 is to find frequent patterns, associations, correlations or causal structures existing between preliminary predictions and impact predictions among the preliminary prediction and impact prediction data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310814459.4A CN117172347A (en) | 2023-07-04 | 2023-07-04 | Carbon emission prediction method based on energy big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310814459.4A CN117172347A (en) | 2023-07-04 | 2023-07-04 | Carbon emission prediction method based on energy big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117172347A true CN117172347A (en) | 2023-12-05 |
Family
ID=88932555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310814459.4A Pending CN117172347A (en) | 2023-07-04 | 2023-07-04 | Carbon emission prediction method based on energy big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117172347A (en) |
-
2023
- 2023-07-04 CN CN202310814459.4A patent/CN117172347A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109461025B (en) | Electric energy substitution potential customer prediction method based on machine learning | |
| CN102780765A (en) | Cloud manufacturing service resource match and combination method based on performance fusion | |
| CN117829914B (en) | Digital media advertisement effect evaluation system | |
| EP4131031A1 (en) | Recommendation method and device based on automatic feature grouping | |
| CN114418035A (en) | Decision tree model generation method and data recommendation method based on decision tree model | |
| CN106649479A (en) | Probability graph-based transformer state association rule mining method | |
| CN113537807A (en) | Enterprise intelligent wind control method and device | |
| CN117556369A (en) | Power theft detection method and system for dynamically generated residual error graph convolution neural network | |
| CN114741972A (en) | Construction method of seasonal prediction model of air pollutant concentration | |
| CN114757468A (en) | Root cause analysis method for flow execution abnormity in flow mining | |
| CN106407379A (en) | Hadoop platform based movie recommendation method | |
| CN116128544A (en) | Active auditing method and system for electric power marketing abnormal business data | |
| CN111159559A (en) | Method for constructing recommendation engine according to user requirements and user behaviors | |
| CN111552882B (en) | News influence calculation method and device, computer equipment and storage medium | |
| CN117828277A (en) | Method and system for monitoring stability of all-link data of power system | |
| CN116775882B (en) | Intelligent government affair message processing method and equipment | |
| Yang et al. | MOOC Learner's Final Grade Prediction Based on an Improved Random Forests Method. | |
| Wiesweg et al. | Data-driven risk management for requirements engineering: An automated approach based on Bayesian networks | |
| Pham et al. | Predictive analysis of the supply chain management using machine learning approaches: Review and taxonomy | |
| CN117172347A (en) | Carbon emission prediction method based on energy big data | |
| CN114265954B (en) | Graph representation learning method based on position and structure information | |
| CN116108963A (en) | Electric power carbon emission prediction method and equipment based on integrated learning module | |
| CN113837486B (en) | RNN-RBM-based distribution network feeder long-term load prediction method | |
| CN112581177B (en) | Marketing prediction method combining automatic feature engineering and residual neural network | |
| CN115310004A (en) | Graph nerve collaborative filtering recommendation method fusing project time sequence relation |
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 |