CN115829113A - Carbon emission estimation method based on energy consumption data - Google Patents
Carbon emission estimation method based on energy consumption data Download PDFInfo
- Publication number
- CN115829113A CN115829113A CN202211490858.1A CN202211490858A CN115829113A CN 115829113 A CN115829113 A CN 115829113A CN 202211490858 A CN202211490858 A CN 202211490858A CN 115829113 A CN115829113 A CN 115829113A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- carbon emission
- consumption data
- data
- historical
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a carbon emission estimation method based on energy consumption data, which comprises the following steps: s1, acquiring historical industrial energy consumption data, and cleaning the historical industrial energy consumption data to obtain an energy data list; s2, obtaining the historical carbon emission of the regular industry according to the energy consumption data in the data list; s3, obtaining a historical carbon emission power coefficient of the regular industry according to the historical carbon emission of the regular industry; s4, taking the historical carbon emission power coefficient of the regular industry as a dependent variable, selecting an independent variable to construct an ARIMAX time sequence model and an XGboost gradient lifting decision tree model, outputting a test set fitting result and calculating the average deviation and the median deviation of each area of the two models; s5, selecting a model with the minimum output deviation as an optimal prediction model; and S6, obtaining real-time on-line industrial carbon emission measurement and calculation data by using the optimal prediction model. According to the scheme, the optimal model is selected according to the energy consumption characteristics of regional enterprises and industries to carry out corresponding carbon emission estimation, and the estimation result is accurate and reliable.
Description
Technical Field
The invention relates to the technical field of carbon emission measurement and prediction, in particular to a carbon emission estimation method based on energy consumption data.
Background
At present, the carbon emission is predicted by analyzing and predicting the carbon emission according to the influence of GDP, an industry added value and energy activity on the carbon emission, for example, the commonly used classical models comprise Kaya identity, MERGE model, IPAC model and the like; the carbon emission is also predicted by building a model through a data analysis method, common models comprise a polynary neural network, a DDEPM model, a GM (1,1) model and the like, and the models or the methods can provide effective theoretical analysis and feasible verification for measurement, calculation and prediction of the carbon emission. Because the carbon emission is difficult to directly measure, the carbon emission coefficient is usually multiplied by various energy consumption amounts to calculate the carbon emission, but the regional adaptability and updating timeliness of the carbon emission coefficient cannot be guaranteed due to the difference and change of the energy structure objectively existing in all parts of the country, so that the area adaptability is poor by adopting a single carbon emission prediction model, and the predicted smoke emission result is not reliable and accurate enough.
Disclosure of Invention
The invention aims to overcome the defect that the result is not reliable and accurate enough due to the fact that the carbon emission amount of different areas is measured and calculated through a single model in the prior art, and provides an energy consumption data-based carbon emission estimation method.
The purpose of the invention is realized by the following technical scheme: a carbon emission estimation method based on energy consumption data is provided, which comprises the following steps:
s1, acquiring historical industrial energy consumption data, and cleaning the historical industrial energy consumption data to obtain an energy data list;
s2, obtaining the historical carbon emission of the regular industry according to the energy consumption data in the data list;
s3, obtaining a historical carbon emission power coefficient of the regular industry according to the historical carbon emission of the regular industry;
s4, taking the historical carbon emission power coefficient of the regular industry as a dependent variable, selecting an independent variable to construct an ARIMAX time sequence model and an XGboost gradient lifting decision tree model, outputting a test set fitting result and calculating the average deviation and median deviation of each area of the two models;
s5, selecting a model with the minimum output deviation as an optimal prediction model;
and S6, obtaining real-time regular industry carbon emission measurement and calculation data by using the optimal prediction model.
Preferably, S1 comprises the steps of:
extracting the energy consumption data of the on-scale industry, and eliminating abnormal data in the energy consumption data list to obtain the cleaned on-scale energy
1 data list.
Preferably, the energy consumption data comprises energy types and energy quantity; the energy types include electric power, raw coal, heat, gasoline, diesel oil, fuel oil and natural gas.
Preferably, S2 comprises the steps of:
performing unit unification on a standard carbon emission conversion coefficient corresponding to the energy type in the energy consumption data and the energy consumption, and multiplying the unit unification to obtain the theoretical carbon emission of each energy;
and sequentially obtaining the theoretical carbon emission of each energy and summing up the theoretical carbon emission to obtain the historical carbon emission of the conventional industry.
Preferably, S3 comprises the steps of:
and taking the ratio of the historical carbon emission of the regular industry to the regular industry power consumption in the corresponding period as the historical carbon emission power coefficient of the regular industry.
Preferably, in S4, the output value deviations of the two models are calculated respectively, wherein the output value deviation calculation formula is as follows:
wherein, y i In order to be the true value of the value,
is a fitting value; and taking the average value of the test set deviation as the average deviation, and taking the median value of the test set deviation as the median deviation.
Preferably, S4 further comprises: and taking the year and the electricity consumption as independent variables, constructing an ARIMAX time sequence model, acquiring a data set by taking the year as a unit, dividing a test set and a training set, traversing the set value ranges of the p and q parameters, and automatically searching the parameter combination which enables the model BIC to be minimum.
Preferably, S4 further comprises: constructing an XGboost gradient lifting decision tree algorithm model by taking the industry, the year and the power consumption as independent variables; acquiring a data set by taking a year as a unit; and dividing the data set into a training set and a test set by adopting a leave-out method based on the proportion of 8:2, traversing the numerical value combination of the number of weak learners and the depth of the tree within a set range, and selecting the combination with the minimum average deviation as a model parameter.
Preferably, S6 comprises: and multiplying the power coefficient of the carbon emission of the regular industry obtained by the prediction of the optimal prediction model by the real-time electric quantity data of the regular industry to obtain the real-time carbon emission measurement and calculation data of the regular industry.
The invention has the following beneficial effects: an ARIMAX time sequence model and an XGboost gradient lifting decision tree model for carbon emission measurement and calculation are respectively constructed, an optimal model can be selected for corresponding carbon emission estimation according to energy consumption characteristics, regional energy structure characteristics and development changes of regional enterprises and industries, and estimation results are accurate and reliable.
Detailed Description
The invention is further described below with reference to examples.
Example (b):
a method for estimating carbon emissions based on energy consumption data, comprising the steps of:
s1, historical regular industry energy consumption data are obtained and cleaned to obtain a regular industry energy data list.
Wherein, S1 comprises the following steps:
and extracting the energy consumption data of the on-scale industry, and removing abnormal data in the energy consumption data list to obtain the cleaned on-scale energy data list.
Specifically, the regular industrial energy consumption data can be derived from comprehensive energy consumption and various energy summarizing energy consumption data of more than 30 enterprises with industrial industry scales recorded in 'statistical yearbook' in the cities of various parts and districts published by a statistical bureau, and the energy consumption data comprises electric power, raw coal, heat, gasoline, diesel oil, fuel oil, natural gas and the like.
And S2, obtaining the historical carbon emission of the regular industry according to the energy consumption data in the data list.
S2 comprises the following steps:
unifying and multiplying a standard carbon emission conversion coefficient corresponding to the energy type in the energy consumption data and the consumption of the energy in a unit to obtain the theoretical carbon emission of each energy;
and sequentially obtaining the theoretical carbon emission of each energy and summing up the theoretical carbon emission to obtain the historical carbon emission of the conventional industry.
The energy utilization data comprises energy types and energy quantity; the energy types include electric power, raw coal, heat, gasoline, diesel oil, fuel oil and natural gas.
And S3, obtaining the historical carbon emission power coefficient of the regular industry according to the historical carbon emission of the regular industry.
Specifically, the ratio of the historical carbon emission of the industry on the scale to the electricity consumption of the industry on the scale in the corresponding period is used as the historical carbon emission power coefficient of the industry on the scale.
And S4, taking the carbon emission power coefficient of the past year in the industry as a dependent variable, selecting an independent variable to construct an ARIMAX time sequence model and an XGboost gradient lifting decision tree model, outputting a test set fitting result and calculating the average deviation and the median deviation of each area of the two models.
And S4, respectively calculating the output value deviation of the two models, wherein the output value deviation calculation formula is as follows:
wherein, y i In order to be the true value of the value,
is a fitting value; and taking the average value of the test set deviation as the average deviation, and taking the median value of the test set deviation as the median deviation.
Further, S4 further includes: and taking the year and the electricity consumption as independent variables, constructing an ARIMAX time sequence model, acquiring a data set by taking the year as a unit, dividing a test set and a training set, traversing the set value ranges of the p and q parameters, and automatically searching the parameter combination which enables the model BIC to be minimum.
Further, S4 further includes: constructing an XGboost gradient lifting decision tree algorithm model by taking the industry, the year and the power consumption as independent variables; acquiring a data set by taking a year as a unit; and dividing the data set into a training set and a test set by adopting a leave-out method based on the proportion of 8:2, traversing the numerical value combination of the number of weak learners and the depth of the tree within a set range, and selecting the combination with the minimum average deviation as a model parameter.
And S5, selecting the model with the minimum output deviation as the optimal prediction model.
And S6, obtaining real-time on-line industrial carbon emission measurement and calculation data by using the optimal prediction model.
Specifically, the power coefficient of the carbon emission of the regular industry obtained by prediction of the optimal prediction model is multiplied by the real-time electric quantity data of the regular industry to obtain the real-time carbon emission measurement and calculation data of the regular industry.
The energy consumption data of the whole historical industry is obtained and is cleaned to obtain an industry whole energy data list, and as an alternative scheme of the embodiment, the carbon emission real-time measurement and calculation data of the whole industry can be obtained by utilizing the optimal prediction model according to the same method as the method of paragraph 0015-0027 of the application specification.
As an alternative of this embodiment, according to the same method as that described in paragraphs 0015-0027 of this application, the comprehensive energy consumption real-time measurement data of the whole industry is obtained by using the optimal prediction model.
Specifically, energy consumption data and industry types of more than 200 enterprises in a certain carbon transaction trial-run industrial park are obtained, energy consumption types mainly comprise electric power, heat power, natural gas and the like, the energy consumption types are cleaned to obtain an enterprise energy data list, and according to the method of the same paragraph number 0015-0027 in the application specification, the optimal prediction model is used for predicting and obtaining real-time carbon emission measurement and calculation data of the enterprises in the trial-run park.
As an alternative to this embodiment, the comprehensive energy consumption real-time measurement data of the enterprise in the pilot plant park is obtained by using the optimal prediction model according to the same method as that described in paragraphs 0015 to 0027 of this application.
The above-described embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention in any way, and other variations and modifications may be made without departing from the spirit of the invention as set forth in the claims.
Claims (9)
1. A method for estimating carbon emissions based on energy consumption data, comprising the steps of:
s1, acquiring historical industrial energy consumption data, and cleaning the historical industrial energy consumption data to obtain an energy data list;
s2, obtaining the historical carbon emission of the regular industry according to the energy consumption data in the data list;
s3, obtaining a historical carbon emission power coefficient of the regular industry according to the historical carbon emission of the regular industry;
s4, taking the historical carbon emission power coefficient of the regular industry as a dependent variable, selecting an independent variable to construct an ARIMAX time sequence model and an XGboost gradient lifting decision tree model, outputting a test set fitting result and calculating the average deviation and the median deviation of each area of the two models;
s5, selecting a model with the minimum output deviation as an optimal prediction model;
and S6, obtaining real-time on-line industrial carbon emission measurement and calculation data by using the optimal prediction model.
2. The method of estimating carbon emissions based on energy consumption data according to claim 1,
s1 comprises the following steps:
and extracting the energy consumption data of the on-scale industry, and removing abnormal data in the energy consumption data list to obtain the cleaned on-scale energy data list.
3. The method of estimating carbon emissions based on energy consumption data according to claim 1,
the energy utilization data comprises energy types and energy quantity; the energy types include electric power, raw coal, heat, gasoline, diesel oil, fuel oil and natural gas.
4. The method of estimating carbon emissions based on energy consumption data according to claim 3,
s2 comprises the following steps:
performing unit unification on a standard carbon emission conversion coefficient corresponding to the energy type in the energy consumption data and the energy consumption, and multiplying the unit unification to obtain the theoretical carbon emission of each energy;
and sequentially obtaining the theoretical carbon emission of each energy, adding and summarizing to obtain the historical carbon emission of the conventional industry.
5. The method for estimating carbon emissions based on energy consumption data according to claim 1 or 4, wherein S3 comprises the steps of:
and taking the ratio of the historical carbon emission of the regular industry to the electricity consumption of the regular industry in the corresponding period as the historical carbon emission power coefficient of the regular industry.
6. The method of estimating carbon emissions based on energy consumption data according to claim 1,
and S4, respectively calculating the output value deviation of the two models, wherein the output value deviation calculation formula is as follows:
wherein, y i In order to be the true value of the value,
is a fitting value; and taking the average value of the test set deviation as the average deviation, and taking the median value of the test set deviation as the median deviation.
7. The method of estimating carbon emissions based on energy consumption data according to claim 1,
s4 further comprises: and taking the year and the electricity consumption as independent variables, constructing an ARIMAX time sequence model, acquiring a data set by taking the year as a unit, dividing a test set and a training set, traversing the set value ranges of the p and q parameters, and automatically searching the parameter combination which enables the model BIC to be minimum.
8. The method of estimating carbon emissions based on energy consumption data according to claim 1,
s4 further comprises: constructing an XGboost gradient lifting decision tree algorithm model by taking industries, years and power consumption as independent variables; acquiring a data set by taking a year as a unit; and dividing the data set into a training set and a test set by adopting a leave-out method based on the proportion of 8:2, traversing the numerical value combination of the number of weak learners and the depth of the tree in a setting range, and selecting the combination with the minimum average deviation as a model parameter.
9. The method of estimating carbon emissions based on energy consumption data according to claim 1,
s6 comprises the following steps: and multiplying the power coefficient of the carbon emission of the regular industry obtained by the prediction of the optimal prediction model by the real-time electric quantity data of the regular industry to obtain the real-time carbon emission measurement and calculation data of the regular industry.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211490858.1A CN115829113A (en) | 2022-11-25 | 2022-11-25 | Carbon emission estimation method based on energy consumption data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211490858.1A CN115829113A (en) | 2022-11-25 | 2022-11-25 | Carbon emission estimation method based on energy consumption data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115829113A true CN115829113A (en) | 2023-03-21 |
Family
ID=85531540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211490858.1A Pending CN115829113A (en) | 2022-11-25 | 2022-11-25 | Carbon emission estimation method based on energy consumption data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115829113A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167669A (en) * | 2023-04-26 | 2023-05-26 | 国网浙江省电力有限公司金华供电公司 | Carbon emission assessment method based on power consumption regression |
-
2022
- 2022-11-25 CN CN202211490858.1A patent/CN115829113A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116167669A (en) * | 2023-04-26 | 2023-05-26 | 国网浙江省电力有限公司金华供电公司 | Carbon emission assessment method based on power consumption regression |
| CN116167669B (en) * | 2023-04-26 | 2023-07-21 | 国网浙江省电力有限公司金华供电公司 | Carbon emission assessment method based on power consumption regression |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111445060B (en) | Community carbon emission monitoring and predicting system and method | |
| CN114742294A (en) | Neural network algorithm for carbon emission prediction | |
| CN110716512A (en) | Environmental protection equipment performance prediction method based on coal-fired power plant operation data | |
| CN111489015A (en) | Atmosphere O based on multiple model comparison and optimization3Concentration prediction method | |
| CN105184388A (en) | Non-linear regression method for urban power load short-period prediction | |
| CN110751312A (en) | Multi-factor-based system dynamics life water demand prediction method and system | |
| CN104699991B (en) | Urban heating system year heating load Forecasting Methodology based on gray system theory | |
| CN114240086A (en) | Carbon emission monitoring method and device, storage medium and processor | |
| CN116739368A (en) | Industrial park carbon emission level monitoring and evaluating method based on energy big data | |
| CN106295106B (en) | A kind of photovoltaic plant reactive power support capability assessment method | |
| CN115829113A (en) | Carbon emission estimation method based on energy consumption data | |
| CN110533247B (en) | Monthly power consumption prediction method adopting temperature data anomaly point compensation | |
| Ibadullaev et al. | Empirical analysis of renewable and non-renewable energy resources consumption impact on economic development in Uzbekistan | |
| CN105260944A (en) | Method for calculating statistical line loss based on LSSVM (Least Square Support Vector Machine) algorithm and association rule mining | |
| CN115935784B (en) | Analysis method and system for fuel data in combustion system of building ceramic kiln | |
| CN116401962A (en) | Method for pushing optimal characteristic scheme of water quality model | |
| CN113420443B (en) | Accurate stink simulation method coupled with peak-to-average factor | |
| CN115561697A (en) | Intelligent ammeter error analysis method | |
| CN115470970A (en) | Electric quantity prediction method and system based on prophet-LightGBM combined model | |
| Tao et al. | Predictive Analysis of Yellow River Water and Sand Monitoring Data Based on the ARIMA Model | |
| CN113077105B (en) | Long-false-day load prediction method and device | |
| CN117007747A (en) | System and method for monitoring carbon emission in highway construction period | |
| Goh et al. | Challenges to Consumers Practices toward Renewable Energy in Household from a Socio-technical Perspective | |
| CN117672403A (en) | Method for predicting concentration trend of dissolved gas in power transformer oil | |
| Wang | Analysis of Key Factors Influencing Electrical Load Profiles |
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 |