CN117764601A - Carbon emission prediction method, device, equipment and medium based on electric power data - Google Patents
Carbon emission prediction method, device, equipment and medium based on electric power data Download PDFInfo
- Publication number
- CN117764601A CN117764601A CN202311570526.9A CN202311570526A CN117764601A CN 117764601 A CN117764601 A CN 117764601A CN 202311570526 A CN202311570526 A CN 202311570526A CN 117764601 A CN117764601 A CN 117764601A
- Authority
- CN
- China
- Prior art keywords
- carbon
- data
- enterprise
- model
- electric
- 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 324
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 323
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000005611 electricity Effects 0.000 claims abstract description 51
- 238000007781 pre-processing Methods 0.000 claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims description 27
- 230000000694 effects Effects 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 238000012790 confirmation Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 238000010219 correlation analysis Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 230000002265 prevention Effects 0.000 abstract description 2
- 238000000611 regression analysis Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000012417 linear regression Methods 0.000 description 4
- 229910001021 Ferroalloy Inorganic materials 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 3
- 239000004568 cement Substances 0.000 description 3
- 239000003245 coal Substances 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 239000010959 steel Substances 0.000 description 3
- 238000010200 validation analysis Methods 0.000 description 3
- 235000008733 Citrus aurantifolia Nutrition 0.000 description 2
- 235000011941 Tilia x europaea Nutrition 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 239000010426 asphalt Substances 0.000 description 2
- 239000000919 ceramic Substances 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 239000004571 lime Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000001604 Rao's score test Methods 0.000 description 1
- 238000003723 Smelting Methods 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000004939 coking Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 150000002739 metals Chemical class 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of enterprise carbon monitoring, and particularly provides a carbon emission prediction method, device, equipment and medium based on electric power data, wherein the method comprises the following steps: acquiring historical electricity consumption data and carbon emission data for data preprocessing; calculating the correlation between electricity consumption data and the carbon emission of corresponding enterprises, and confirming the enterprises needing carbon emission prediction in the area; selecting a corresponding model algorithm according to the data to establish an electric carbon model of each enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise; acquiring an electric carbon model corresponding to an enterprise, and calculating an electric carbon index by using the electric carbon model; and predicting the carbon emission of the enterprise according to the calculated electric carbon index and the electric quantity. When the comparison result shows that the carbon emission is equal to or higher than the emission threshold, sending out an out-of-standard discharge early warning; the control method is convenient to perform more effective prevention and control, and the reasonable control on the electric carbon emission is effectively improved.
Description
Technical Field
The invention relates to the technical field of enterprise carbon monitoring, in particular to a carbon emission prediction method, device, equipment and medium based on electric power data.
Background
The high-energy consumption and high-pollution enterprises do not fully utilize the electric power data when carrying out carbon emission accounting, so that the carbon energy efficiency measurement and calculation is inaccurate. The current situation of the carbon energy efficiency of enterprises cannot be predicted clearly, and the change relation of the electric power and the carbon emission cannot be realized.
In order to achieve the goal of carbon-to-peak carbon neutralization, economic sustainable development is realized, and modeling prediction technology of carbon emission becomes a hot spot problem of research. The current prediction method for carbon emission is various and comprises simple or complex models, and the prediction results of different models are different.
Some prediction methods often collect a large amount of electric power data samples for inspection and analysis when collecting the data samples, and abnormal data in the data samples can influence the processing speed and accuracy, so as to influence the monitoring effect on electric carbon emission. There is also a large amount of collected electric power data, and the electric power data is manually screened, identified, valuable data is found, and the carbon emission is predicted, so that a large amount of manpower and material resources are consumed, and a certain difficulty exists in application and popularization.
Disclosure of Invention
Aiming at the problem of inaccurate measurement and calculation of carbon energy efficiency, the invention provides a carbon emission prediction method, device, equipment and medium based on electric power data.
In a first aspect, the present invention provides a method for predicting carbon emission based on electric power data, including the steps of:
acquiring historical electricity consumption data and carbon emission data for data preprocessing;
calculating the correlation between electricity consumption data and the carbon emission of corresponding enterprises, and confirming the enterprises needing carbon emission prediction in the area;
selecting a corresponding model algorithm according to the data to establish an electric carbon model of each enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise;
acquiring an electric carbon model corresponding to an enterprise, and calculating an electric carbon index by using the electric carbon model;
and predicting the carbon emission of the enterprise according to the calculated electric carbon index and the electric quantity.
As a further limitation of the technical scheme of the present invention, the step of predicting the carbon emission of the enterprise according to the calculated electric carbon index and the electric quantity comprises:
and comparing the carbon emission with a set emission threshold, and sending out an out-of-standard discharge early warning when the comparison result shows that the carbon emission is equal to or higher than the emission threshold.
As a further limitation of the technical scheme of the invention, the step of acquiring historical electricity utilization data and carbon emission data for data preprocessing comprises the following steps:
acquiring historical electricity utilization data and carbon emission data of each enterprise in the area;
when single month data is missing in the data acquired by each enterprise, filling the missing data by adopting the average value of two months before and after; when multi-month data is missing in an enterprise, filling the missing data by adopting an average value of all months;
and carrying out normalization processing on the data after the filling processing.
As a further limitation of the technical scheme of the present invention, the step of calculating the correlation between the electricity consumption data and the carbon emission of the corresponding enterprises to confirm the enterprises in the area requiring the prediction of the carbon emission comprises:
carrying out correlation analysis on the electricity consumption and the carbon emission of each enterprise, and calculating the correlation coefficient of the electricity consumption and the carbon emission of each enterprise;
and selecting enterprises with absolute values of correlation coefficients larger than a set correlation threshold value, and determining that the enterprises need to predict the carbon emission in the region.
As a further limitation of the technical scheme of the invention, corresponding model algorithms are selected according to the data to establish the electric carbon model of each enterprise; the step of storing the electric carbon model after being associated with the corresponding enterprise comprises the following steps:
dividing the normalized data into a training data set and a test data set according to a set proportion;
creating various regression algorithm models, respectively training and optimizing the created models to obtain an electric carbon model, and carrying out effect analysis to calculate an effect evaluation score; wherein the closer the actual value of the carbon emission amount and the predicted value of the carbon emission amount are, the closer the effect evaluation score is to 1;
selecting a model with the highest evaluation score of each enterprise according to the effect evaluation score to determine the model as an electric carbon model of the enterprise;
and associating the electric carbon model with a corresponding enterprise and storing the electric carbon model.
As a further limitation of the technical scheme of the present invention, the step of obtaining an electrical carbon model corresponding to an enterprise and calculating an electrical carbon index using the electrical carbon model includes:
acquiring net purchase electric quantity of an enterprise and production data of the enterprise;
acquiring associated characteristic data related to the carbon emission of enterprises according to the production data;
obtaining an electrical carbon model associated with the enterprise from the electrical carbon models;
and inputting the associated characteristic data into the acquired electric carbon model to calculate an electric carbon index.
As a further limitation of the technical solution of the present invention, the step of obtaining an electric carbon model associated with the enterprise from the electric carbon models includes:
judging whether an associated electric carbon model exists according to enterprise information;
if yes, executing the steps: obtaining an electrical carbon model associated with the enterprise from the electrical carbon models;
if not, acquiring historical electricity consumption data and carbon emission data of the enterprise for data preprocessing;
selecting a corresponding model algorithm according to the data to establish an electric carbon model of the enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise; the method comprises the following steps: and obtaining an electric carbon model corresponding to the enterprise, and calculating an electric carbon index by using the electric carbon model.
In a second aspect, the present invention provides a carbon emission prediction apparatus based on electric power data, including a data acquisition preprocessing module, a demand confirmation module, an electric carbon model building module, an electric carbon index calculation module, and a carbon emission calculation module;
the data acquisition preprocessing module is used for acquiring historical electricity utilization data and carbon emission data to perform data preprocessing;
the demand confirmation module is used for calculating the correlation between the electricity consumption data and the carbon emission of the corresponding enterprises and confirming the enterprises needing carbon emission prediction in the area;
the electric carbon model building module is used for selecting a corresponding model algorithm according to the data to build an electric carbon model of each enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise;
the electric carbon index calculation module is used for obtaining an electric carbon model corresponding to an enterprise and calculating an electric carbon index by using the electric carbon model;
and the carbon emission amount calculation module is used for predicting the carbon emission amount of the enterprise according to the calculated electric carbon index and the electricity consumption.
As a further limitation of the technical scheme of the invention, the device also comprises a discharge capacity early warning module which is used for comparing the carbon discharge amount with a set discharge threshold value, and sending out discharge capacity exceeding early warning when the comparison result shows that the carbon discharge amount is equal to or higher than the discharge threshold value.
As a further limitation of the technical scheme of the invention, the data acquisition preprocessing module comprises a data acquisition unit, a data filling unit and a data processing unit;
the data acquisition unit is used for acquiring historical electricity utilization data and carbon emission data of each enterprise in the area;
the data filling unit is used for filling the missing data by adopting the average value of two months before and after when the data acquired by each enterprise has the single month data missing; when multi-month data is missing in an enterprise, filling the missing data by adopting an average value of all months;
and the data processing unit is used for carrying out normalization processing on the data after the filling processing.
As a further limitation of the technical scheme of the invention, the demand confirmation module comprises a correlation coefficient calculation unit and a demand confirmation unit;
the correlation coefficient calculation unit is used for carrying out correlation analysis on the electricity consumption and the carbon emission of each enterprise and calculating the correlation coefficient of the electricity consumption and the carbon emission of each enterprise;
and the demand confirmation unit is used for selecting enterprises with the absolute value of the correlation coefficient larger than the set correlation threshold value, and determining the enterprises to be subjected to carbon emission prediction in the area.
As a further limitation of the technical scheme of the invention, the electric carbon model building module comprises a data dividing unit, a model processing unit, a model confirming unit and an associated storage unit;
the data dividing unit is used for dividing the normalized data into a training data set and a test data set according to a set proportion;
the model processing unit is used for creating various regression algorithm models, respectively training and optimizing the created models to obtain an electric carbon model, and carrying out effect analysis and calculation on effect evaluation scores; wherein the closer the actual value of the carbon emission amount and the predicted value of the carbon emission amount are, the closer the effect evaluation score is to 1;
the model confirming unit is used for selecting a model with the highest evaluation score of each enterprise according to the effect evaluation score to be determined as an electric carbon model of the enterprise;
and the association storage unit is used for storing the electric carbon model after associating with the corresponding enterprise.
As a further limitation of the technical scheme of the invention, the electric carbon index calculation module comprises an enterprise data acquisition unit, a correlation data acquisition unit, an electric carbon model acquisition unit and an electric carbon index calculation unit;
the enterprise data acquisition unit is used for acquiring the net purchase electric quantity of an enterprise and the production data of the enterprise;
a related data acquisition unit for acquiring related characteristic data related to the carbon emission amount of the enterprise according to the production data;
an electric carbon model obtaining unit, configured to obtain an electric carbon model associated with the enterprise from electric carbon models;
and the electric carbon index calculation unit is used for inputting the associated characteristic data into the acquired electric carbon model to calculate the electric carbon index.
As a further limitation of the technical scheme of the invention, the device also comprises a judging module for judging whether the associated electric carbon model exists according to the enterprise information; if yes, triggering an electric carbon model acquisition unit; if not, triggering an electric carbon model building module;
the electric carbon model building module is also used for acquiring historical electricity consumption data and carbon emission data of the enterprise to perform data preprocessing; selecting a corresponding model algorithm according to the data to establish an electric carbon model of the enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise.
In a third aspect, the present invention further provides an electronic device, where the electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform the method of predicting carbon emissions of electrical power data as described in the first aspect.
In a fourth aspect, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions that cause the computer to execute the carbon emission prediction method of the electric power data according to the first aspect.
From the above technical scheme, the invention has the following advantages: and the collected data abnormal points are processed, so that the speed and accuracy of data processing are improved, and the prediction effect on the electric carbon emission is improved. Comparing the carbon emission with a set emission threshold, and sending out an out-of-standard discharge early warning when the comparison result shows that the carbon emission is equal to or higher than the emission threshold; the control method is convenient to perform more effective prevention and control, and the reasonable control on the electric carbon emission is effectively improved.
In addition, the invention has reliable design principle, simple structure and very wide application prospect.
It can be seen that the present invention has outstanding substantial features and significant advances over the prior art, as well as its practical advantages.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a schematic flow chart of a method of one embodiment of the invention.
Fig. 2 is a schematic block diagram of an apparatus of one embodiment of the invention.
Detailed Description
In order to make the technical solution of the present invention better understood by those skilled in the art, the technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a carbon emission prediction method based on electric power data, including the steps of:
step 1: acquiring historical electricity consumption data and carbon emission data for data preprocessing;
the data in the set time range of each enterprise is acquired, wherein the data can be about 13 months of energy consumption data, namely, the net purchase quantity of the enterprise and the production data of the corresponding month;
step 2: calculating the correlation between electricity consumption data and the carbon emission of corresponding enterprises, and confirming the enterprises needing carbon emission prediction in the area;
correlation analysis refers to analyzing two or more variable elements with correlation, so as to measure the correlation degree of two variable factors. There is a certain association or probability between elements of the correlation to be able to perform the correlation analysis. Common correlation coefficient analysis methods include Pearson correlation coefficients, spearman correlation coefficients, kendall correlation coefficients, which reflect the direction and extent of the trend of change between two variables, and the values of which are all [ -1, +1].0 indicates that the two variables are uncorrelated, positive values indicate positive correlations, negative values indicate negative correlations, and larger absolute values indicate stronger correlations.
In the embodiment of the invention, three methods of Pearson correlation coefficient, spearman correlation coefficient and Kendall correlation coefficient are respectively used for carrying out correlation analysis, and the specific analysis process of each method adopts the existing analysis process to carry out analysis, so that repeated description is omitted.
Step 3: selecting a corresponding model algorithm according to the data to establish an electric carbon model of each enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise;
step 4: acquiring an electric carbon model corresponding to an enterprise, and calculating an electric carbon index by using the electric carbon model;
step 5: and predicting the carbon emission of the enterprise according to the calculated electric carbon index and the electric quantity.
Step 6: and comparing the carbon emission with a set emission threshold, and sending out an out-of-standard discharge early warning when the comparison result shows that the carbon emission is equal to or higher than the emission threshold.
In some embodiments, the step of obtaining historical electricity usage data and carbon emission data for data preprocessing includes:
step 11: acquiring historical electricity utilization data and carbon emission data of each enterprise in the area;
step 12: when single month data is missing in the data acquired by each enterprise, filling the missing data by adopting the average value of two months before and after; when multi-month data is missing in an enterprise, filling the missing data by adopting an average value of all months;
step 13: and carrying out normalization processing on the data after the filling processing.
In some embodiments, calculating the electricity usage data and corresponding business carbon emissions correlations, the step of identifying businesses within the area that require carbon emissions prediction, comprises:
carrying out correlation analysis on the electricity consumption and the carbon emission of each enterprise, and calculating the correlation coefficient of the electricity consumption and the carbon emission of each enterprise;
and selecting enterprises with absolute values of correlation coefficients larger than a set correlation threshold value, and determining that the enterprises need to predict the carbon emission in the region.
The correlation coefficients of the electricity consumption and the carbon emission of each enterprise are analyzed and calculated by using the Pearson correlation coefficient, the Spearman correlation coefficient and the Kendall correlation coefficient methods respectively as shown in table 1:
TABLE 1
As can be seen from the table above: there is no obvious correlation between the electricity consumption and carbon emission of four enterprises of casting, refining, coking and basic chemistry (the absolute value of which is smaller than 0.5 correlation coefficient exists), and there is a certain correlation between the electricity consumption and carbon emission of eight industries of steel, asphalt waterproof material, nonferrous metal, ferroalloy, coal electricity, lime, cement and ceramics (the correlation coefficient is larger than 0.5).
By observing the original data, the data such as fossil fuel consumption in the asphalt waterproof material, lime and ceramic industries are obviously missing (continuous null value or zero value exists), and the original data of nine enterprises such as steel, coal power, smelting, cement and ferroalloy are relatively complete, so that the availability is high.
In conclusion, the data of the electricity consumption and the carbon emission of five enterprises of steel, nonferrous metals, ferroalloys, coal power and cement are selected to have certain correlation and availability, so that the five industries can be used for further analysis.
In some embodiments, a corresponding model algorithm is selected according to the data to establish an electrical carbon model of each enterprise; the step of storing the electric carbon model after being associated with the corresponding enterprise comprises the following steps:
step 31: dividing the normalized data into a training data set and a test data set according to a set proportion;
step 32: creating various regression algorithm models, respectively training and optimizing the created models to obtain an electric carbon model, and carrying out effect analysis to calculate an effect evaluation score; wherein the closer the actual value of the carbon emission amount and the predicted value of the carbon emission amount are, the closer the effect evaluation score is to 1;
step 33: selecting a model with the highest evaluation score of each enterprise according to the effect evaluation score to determine the model as an electric carbon model of the enterprise;
step 34: and associating the electric carbon model with a corresponding enterprise and storing the electric carbon model.
Regression analysis (regression analysis) refers to a statistical analysis method that determines the quantitative relationship of interdependence between two or more variables. Regression analysis is divided into unitary regression and multiple regression analysis according to the number of variables involved; according to the number of dependent variables, the analysis can be divided into simple regression analysis and multiple regression analysis; the relationship between independent and dependent variables can be classified into linear regression analysis and nonlinear regression analysis.
The electricity-carbon index research involves two variables, namely the useful electric quantity and the carbon emission, and the dependent variable only has the carbon emission, so that a unitary linear regression model or a nonlinear regression model is selected, and through the research, the models which can be selected are as follows: the method comprises the steps of (1) a linear regression model (2) a KNN regression model (3) an SVM regression model (4) a ridge regression model (5) a LASSO regression model (6) a multi-layer perceptron regression model (7) a decision tree regression model (8) a limit tree regression model (9) a random forest regression model (10) an AdaBoost regression model (11) and a Bagging regression model (12).
The historical month data of an enterprise is selected, and various regression models are used for effect analysis and calculation to obtain training set scores and test set scores as shown in table 2:
TABLE 2
| Sequence number | Model | Training set score | Test set score |
| 1 | Linear regression model | 0.8616069385811777 | 0.5981490416289698 |
| 2 | KNN regression model | 0.6519314213979289 | 0.03784365469438533 |
| 3 | SVM regression model | -0.051643031374819515 | -3.192907850534473 |
| 4 | Ridge regression model | 0.8666361688009367 | 0.7004867891168396 |
| 5 | LASSO regression model | 0.839496051857333 | 0.8583526664241465 |
| 6 | Regression model of multi-layer perceptron | -2.674427792693931 | -0.2130411666611014 |
| 7 | Decision tree regression model | 1.0 | 0.8133433459893219 |
| 8 | Limit tree regression model | 1.0 | 0.295115224821892 |
| 9 | Random forest regression model | 0.9562187043650837 | -0.3431983974479633 |
| 10 | AdaBoost regression model | 0.9955788545583345 | -0.8802837427029242 |
| 11 | Gradient lifting regression model | 0.9999997595177983 | 0.3642640107932482 |
| 12 | Bagging regression model | 0.9051836858520681 | 0.7514061446532129 |
In summary, the enterprise selects the electrical carbon model established by the decision tree regression model.
In some embodiments, the step of obtaining an electrical carbon model corresponding to the enterprise and calculating the electrical carbon index using the electrical carbon model comprises:
step 41: acquiring net purchase electric quantity of an enterprise and production data of the enterprise;
step 42: acquiring associated characteristic data related to the carbon emission of enterprises according to the production data;
step 43: obtaining an electrical carbon model associated with the enterprise from the electrical carbon models;
step 44: and inputting the associated characteristic data into the acquired electric carbon model to calculate an electric carbon index.
It should be noted that, before the step of obtaining the electric carbon model associated with the enterprise from the electric carbon models, the method includes: judging whether an associated electric carbon model exists according to enterprise information; if yes, executing the steps: obtaining an electrical carbon model associated with the enterprise from the electrical carbon models; if not, acquiring historical electricity consumption data and carbon emission data of the enterprise for data preprocessing; selecting a corresponding model algorithm according to the data to establish an electric carbon model of the enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise; the method comprises the following steps: and obtaining an electric carbon model corresponding to the enterprise, and calculating an electric carbon index by using the electric carbon model.
As shown in fig. 2, an embodiment of the present invention provides a carbon emission prediction apparatus based on electric power data, which includes a data acquisition preprocessing module, a demand confirmation module, an electric carbon model building module, an electric carbon index calculation module, and a carbon emission amount calculation module;
the data acquisition preprocessing module is used for acquiring historical electricity utilization data and carbon emission data to perform data preprocessing;
the demand confirmation module is used for calculating the correlation between the electricity consumption data and the carbon emission of the corresponding enterprises and confirming the enterprises needing carbon emission prediction in the area;
the electric carbon model building module is used for selecting a corresponding model algorithm according to the data to build an electric carbon model of each enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise;
the electric carbon index calculation module is used for obtaining an electric carbon model corresponding to an enterprise and calculating an electric carbon index by using the electric carbon model;
and the carbon emission amount calculation module is used for predicting the carbon emission amount of the enterprise according to the calculated electric carbon index and the electricity consumption.
The device also comprises a discharge capacity early warning module which is used for comparing the carbon discharge amount with a set discharge threshold value, and sending out discharge capacity exceeding early warning when the comparison result shows that the carbon discharge amount is equal to or higher than the discharge threshold value.
In some embodiments, the data acquisition preprocessing module comprises a data acquisition unit, a data filling unit and a data processing unit;
the data acquisition unit is used for acquiring historical electricity utilization data and carbon emission data of each enterprise in the area;
the data filling unit is used for filling the missing data by adopting the average value of two months before and after when the data acquired by each enterprise has the single month data missing; when multi-month data is missing in an enterprise, filling the missing data by adopting an average value of all months;
and the data processing unit is used for carrying out normalization processing on the data after the filling processing.
In some embodiments, the demand validation module includes a correlation coefficient calculation unit and a demand validation unit;
the correlation coefficient calculation unit is used for carrying out correlation analysis on the electricity consumption and the carbon emission of each enterprise and calculating the correlation coefficient of the electricity consumption and the carbon emission of each enterprise;
and the demand confirmation unit is used for selecting enterprises with the absolute value of the correlation coefficient larger than the set correlation threshold value, and determining the enterprises to be subjected to carbon emission prediction in the area.
In some embodiments, the electrical carbon model building module includes a data partitioning unit, a model processing unit, a model validation unit, and an associated storage unit;
the data dividing unit is used for dividing the normalized data into a training data set and a test data set according to a set proportion;
the model processing unit is used for creating various regression algorithm models, respectively training and optimizing the created models to obtain an electric carbon model, and carrying out effect analysis and calculation on effect evaluation scores; wherein the closer the actual value of the carbon emission amount and the predicted value of the carbon emission amount are, the closer the effect evaluation score is to 1;
the model confirming unit is used for selecting a model with the highest evaluation score of each enterprise according to the effect evaluation score to be determined as an electric carbon model of the enterprise;
and the association storage unit is used for storing the electric carbon model after associating with the corresponding enterprise.
In some embodiments, the electrical carbon index calculation module includes an enterprise data acquisition unit, an associated data acquisition unit, an electrical carbon model acquisition unit, and an electrical carbon index calculation unit;
the enterprise data acquisition unit is used for acquiring the net purchase electric quantity of an enterprise and the production data of the enterprise;
a related data acquisition unit for acquiring related characteristic data related to the carbon emission amount of the enterprise according to the production data;
an electric carbon model obtaining unit, configured to obtain an electric carbon model associated with the enterprise from electric carbon models;
and the electric carbon index calculation unit is used for inputting the associated characteristic data into the acquired electric carbon model to calculate the electric carbon index.
The device also comprises a judging module for judging whether the associated electric carbon model exists according to the enterprise information; if yes, triggering an electric carbon model acquisition unit; if not, triggering an electric carbon model building module;
the electric carbon model building module is also used for acquiring historical electricity consumption data and carbon emission data of the enterprise to perform data preprocessing; selecting a corresponding model algorithm according to the data to establish an electric carbon model of the enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise.
The embodiment of the invention also provides electronic equipment, which comprises: the device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are in communication with each other through the communication bus. The communication bus may be used for information transfer between the electronic device and the sensor. The processor may call logic instructions in memory to perform the following method: step 1: acquiring historical electricity consumption data and carbon emission data for data preprocessing; step 2: calculating the correlation between electricity consumption data and the carbon emission of corresponding enterprises, and confirming the enterprises needing carbon emission prediction in the area; step 3: selecting a corresponding model algorithm according to the data to establish an electric carbon model of each enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise; step 4: acquiring an electric carbon model corresponding to an enterprise, and calculating an electric carbon index by using the electric carbon model; step 5: and predicting the carbon emission of the enterprise according to the calculated electric carbon index and the electric quantity.
Further, the logic instructions in the memory described above may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Embodiments of the present invention provide a non-transitory computer readable storage medium storing computer instructions that cause a computer to perform the methods provided by the method embodiments described above, for example, including: step 1: acquiring historical electricity consumption data and carbon emission data for data preprocessing; step 2: calculating the correlation between electricity consumption data and the carbon emission of corresponding enterprises, and confirming the enterprises needing carbon emission prediction in the area; step 3: selecting a corresponding model algorithm according to the data to establish an electric carbon model of each enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise; step 4: acquiring an electric carbon model corresponding to an enterprise, and calculating an electric carbon index by using the electric carbon model; step 5: and predicting the carbon emission of the enterprise according to the calculated electric carbon index and the electric quantity.
Although the present invention has been described in detail by way of preferred embodiments with reference to the accompanying drawings, the present invention is not limited thereto. Various equivalent modifications and substitutions may be made in the embodiments of the present invention by those skilled in the art without departing from the spirit and scope of the present invention, and it is intended that all such modifications and substitutions be within the scope of the present invention/be within the scope of the present invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A carbon emission prediction method based on electric power data, characterized by comprising the steps of:
acquiring historical electricity consumption data and carbon emission data for data preprocessing;
calculating the correlation between electricity consumption data and the carbon emission of corresponding enterprises, and confirming the enterprises needing carbon emission prediction in the area;
selecting a corresponding model algorithm according to the data to establish an electric carbon model of each enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise;
acquiring an electric carbon model corresponding to an enterprise, and calculating an electric carbon index by using the electric carbon model;
and predicting the carbon emission of the enterprise according to the calculated electric carbon index and the electric quantity.
2. The method for predicting carbon emissions based on electrical power data of claim 1, wherein the step of predicting the carbon emissions of the enterprise based on the calculated electrical carbon index and the electricity consumption comprises:
and comparing the carbon emission with a set emission threshold, and sending out an out-of-standard discharge early warning when the comparison result shows that the carbon emission is equal to or higher than the emission threshold.
3. The method for predicting carbon emissions based on electrical power data of claim 2, wherein the step of obtaining historical electrical power usage data and carbon emissions data for data preprocessing comprises:
acquiring historical electricity utilization data and carbon emission data of each enterprise in the area;
when single month data is missing in the data acquired by each enterprise, filling the missing data by adopting the average value of two months before and after; when multi-month data is missing in an enterprise, filling the missing data by adopting an average value of all months;
and carrying out normalization processing on the data after the filling processing.
4. The method for predicting carbon emissions based on electrical power data as recited in claim 3, wherein the step of calculating a correlation between the electrical power data and the corresponding carbon emissions of the businesses, and identifying businesses in the area that require carbon emissions prediction, comprises:
carrying out correlation analysis on the electricity consumption and the carbon emission of each enterprise, and calculating the correlation coefficient of the electricity consumption and the carbon emission of each enterprise;
and selecting enterprises with absolute values of correlation coefficients larger than a set correlation threshold value, and determining that the enterprises need to predict the carbon emission in the region.
5. The method for predicting carbon emissions based on electrical data of claim 4, wherein the electrical carbon model of each enterprise is established by selecting a corresponding model algorithm based on the data; the step of storing the electric carbon model after being associated with the corresponding enterprise comprises the following steps:
dividing the normalized data into a training data set and a test data set according to a set proportion;
creating various regression algorithm models, respectively training and optimizing the created models to obtain an electric carbon model, and carrying out effect analysis to calculate an effect evaluation score; wherein the closer the actual value of the carbon emission amount and the predicted value of the carbon emission amount are, the closer the effect evaluation score is to 1;
selecting a model with the highest evaluation score of each enterprise according to the effect evaluation score to determine the model as an electric carbon model of the enterprise;
and associating the electric carbon model with a corresponding enterprise and storing the electric carbon model.
6. The method for predicting carbon emissions based on electrical data of claim 5, wherein the step of obtaining an electrical carbon model corresponding to the business and calculating an electrical carbon index using the electrical carbon model comprises:
acquiring net purchase electric quantity of an enterprise and production data of the enterprise;
acquiring associated characteristic data related to the carbon emission of enterprises according to the production data;
obtaining an electrical carbon model associated with the enterprise from the electrical carbon models;
and inputting the associated characteristic data into the acquired electric carbon model to calculate an electric carbon index.
7. The method of claim 6, wherein the step of obtaining an electrical carbon model associated with the business from an electrical carbon model is preceded by:
judging whether an associated electric carbon model exists according to enterprise information;
if yes, executing the steps: obtaining an electrical carbon model associated with the enterprise from the electrical carbon models;
if not, acquiring historical electricity consumption data and carbon emission data of the enterprise for data preprocessing;
selecting a corresponding model algorithm according to the data to establish an electric carbon model of the enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise; the method comprises the following steps: and obtaining an electric carbon model corresponding to the enterprise, and calculating an electric carbon index by using the electric carbon model.
8. The carbon emission prediction device based on the electric power data is characterized by comprising a data acquisition preprocessing module, a demand confirmation module, an electric carbon model building module, an electric carbon index calculation module and a carbon emission calculation module;
the data acquisition preprocessing module is used for acquiring historical electricity utilization data and carbon emission data to perform data preprocessing;
the demand confirmation module is used for calculating the correlation between the electricity consumption data and the carbon emission of the corresponding enterprises and confirming the enterprises needing carbon emission prediction in the area;
the electric carbon model building module is used for selecting a corresponding model algorithm according to the data to build an electric carbon model of each enterprise; and the electric carbon model is stored after being associated with the corresponding enterprise;
the electric carbon index calculation module is used for obtaining an electric carbon model corresponding to an enterprise and calculating an electric carbon index by using the electric carbon model;
and the carbon emission amount calculation module is used for predicting the carbon emission amount of the enterprise according to the calculated electric carbon index and the electricity consumption.
9. An electronic device, the electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores computer program instructions executable by at least one processor to enable the at least one processor to perform the method of predicting carbon emissions of electrical power data as claimed in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing computer instructions that cause the computer to perform the carbon emission prediction method of electric power data according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311570526.9A CN117764601A (en) | 2023-11-22 | 2023-11-22 | Carbon emission prediction method, device, equipment and medium based on electric power data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311570526.9A CN117764601A (en) | 2023-11-22 | 2023-11-22 | Carbon emission prediction method, device, equipment and medium based on electric power data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117764601A true CN117764601A (en) | 2024-03-26 |
Family
ID=90311194
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311570526.9A Pending CN117764601A (en) | 2023-11-22 | 2023-11-22 | Carbon emission prediction method, device, equipment and medium based on electric power data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117764601A (en) |
-
2023
- 2023-11-22 CN CN202311570526.9A patent/CN117764601A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019165673A1 (en) | Reimbursement form risk prediction method, apparatus, terminal device, and storage medium | |
| CN109685289B (en) | Method, device and system for forward prediction of blast furnace conditions | |
| CN104809658B (en) | A kind of rapid analysis method of low-voltage distribution network taiwan area line loss | |
| CN111275333A (en) | Pollution data processing method and device | |
| CN110991739A (en) | Construction method and prediction method of industry electric quantity demand prediction model | |
| CN111786385B (en) | Power grid operation and maintenance scheme planning method, system and equipment | |
| CN115689396B (en) | Pollutant emission control method, device, equipment and medium | |
| CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
| CN115423373A (en) | Method and system for evaluating carbon emission of park, electronic equipment and storage medium | |
| CN113988671A (en) | Enterprise credit risk assessment method, device and application | |
| CN114076841B (en) | Electricity stealing behavior identification method and system based on electricity consumption data | |
| CN110751316A (en) | Method and device for predicting resolution result and terminal equipment | |
| CN117521912A (en) | Carbon emission measuring and calculating model, comparison and evaluation method and application thereof | |
| CN117764601A (en) | Carbon emission prediction method, device, equipment and medium based on electric power data | |
| CN111311318A (en) | User loss early warning method, device, equipment and storage medium | |
| CN115994784A (en) | Price determination model and construction method thereof | |
| CN115034310A (en) | Multi-model prediction method and device for thermal efficiency of ethylene cracking furnace | |
| CN110727910B (en) | Method and system for realizing copying and collecting risk prediction and business linkage | |
| CN109189775B (en) | Industrial monitoring platform mass data processing system and method | |
| CN108123436B (en) | Voltage out-of-limit prediction model based on principal component analysis and multiple regression algorithm | |
| CN109754186B (en) | Probability calculation method and device based on energy consumption analysis | |
| CN115792476B (en) | Charging pile rectifying module abnormality early warning method, device, terminal and storage medium | |
| CN112102882A (en) | Quality control system and method for NGS detection process of tumor sample | |
| CN111626586B (en) | Data quality detection method, device, computer equipment and storage medium | |
| CN116542380B (en) | Power plant supply chain carbon footprint optimization method and device based on natural language |
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 |