CN117952806A - Intelligent low-carbon management method and system for realizing carbon-to-peak carbon neutralization - Google Patents
Intelligent low-carbon management method and system for realizing carbon-to-peak carbon neutralization Download PDFInfo
- Publication number
- CN117952806A CN117952806A CN202410218173.4A CN202410218173A CN117952806A CN 117952806 A CN117952806 A CN 117952806A CN 202410218173 A CN202410218173 A CN 202410218173A CN 117952806 A CN117952806 A CN 117952806A
- Authority
- CN
- China
- Prior art keywords
- curve segment
- carbon
- data
- curve
- ith
- 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.)
- Withdrawn
Links
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 118
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 83
- 238000007726 management method Methods 0.000 title claims abstract description 28
- 238000006386 neutralization reaction Methods 0.000 title claims abstract description 25
- 230000008859 change Effects 0.000 claims abstract description 50
- 230000002159 abnormal effect Effects 0.000 claims abstract description 34
- 238000012937 correction Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 5
- 230000005856 abnormality Effects 0.000 claims description 15
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013523 data management Methods 0.000 abstract description 2
- 230000005611 electricity Effects 0.000 description 9
- 238000010248 power generation Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data management for carbon neutralization, in particular to an intelligent low-carbon management method and system for realizing carbon peak carbon neutralization, comprising the following steps: obtaining a plurality of curve segments according to the carbon emission data, obtaining initial abnormal degree of each curve segment according to the data change amplitude of each curve segment and the number of contained data, obtaining correction coefficient of each curve segment according to the data change amplitude of each curve segment, and obtaining true abnormal degree of each curve segment; obtaining parameters between each curve segment and the corresponding target curve segment according to the real abnormal degree of each curve segment, and obtaining corrected autoregressive orders according to the parameters between each curve segment and the corresponding target curve segment and the number of data in the marked curve segment between each curve segment and the corresponding target curve segment; and then predicting, and storing and managing the predicted data. The invention processes the carbon emission data and improves the accuracy of carbon emission prediction.
Description
Technical Field
The invention relates to the technical field of data management for carbon neutralization, in particular to an intelligent low-carbon management method and system for realizing carbon peak carbon neutralization.
Background
The intelligent low-carbon management method and system are management methods for realizing real-time monitoring, analysis and optimization of energy consumption and carbon emission by applying technical means such as big data, the Internet of things, artificial intelligence and the like. Along with the improvement of environmental awareness and the increase of energy saving and emission reduction demands of enterprises, the market demands of the intelligent low-carbon management system are gradually expanded. Various bodies of enterprises seek to reduce carbon emission through an intelligent low-carbon management method so as to realize sustainable development.
The energy industry is typically an enterprise with relatively large carbon emissions. It is often desirable to predict future carbon emissions based on the historical carbon emissions of the business to optimize the future carbon emissions of the business. The ARIMA model is a commonly used predictive algorithm that consists of an autoregressive model AR, a differential process, and a moving average model. The order of the autoregressive AR at all observation points in the prediction process is the same, but because of the presence of abnormal data in the historical carbon emission data, if prediction is performed by the ARIMA model with unchanged autoregressive order according to the historical carbon emission data with the abnormal data, a larger error exists in the predicted result.
Disclosure of Invention
The invention provides an intelligent low-carbon management method and system for realizing carbon peak carbon neutralization, which are used for solving the existing problems.
The intelligent low-carbon management method and system for realizing the carbon-to-carbon peak neutralization adopt the following technical scheme:
one embodiment of the present invention provides an intelligent low carbon management method for achieving carbon-to-peak carbon neutralization, comprising the steps of:
Collecting carbon emission data;
Obtaining a plurality of curve segments according to the carbon emission data, obtaining a data change amplitude of each curve segment according to the carbon emission data in each curve segment, obtaining initial abnormal degree of each curve segment according to the data change amplitude of each curve segment and the number of contained data, obtaining a correction coefficient of each curve segment according to the data change amplitude of each curve segment, and correcting the initial abnormal degree according to the correction coefficient of each curve segment to obtain true abnormal degree of each curve segment;
obtaining parameters between each curve segment and the other curve segment according to the real abnormal degree of each curve segment, and obtaining a target curve segment of each curve segment according to the parameters between each curve segment and the other curve segment; obtaining corrected autoregressive orders according to parameters between each curve segment and the corresponding target curve segment;
And predicting the future carbon emission according to the corrected autoregressive order, and storing and managing the predicted data.
Further, the method for obtaining a plurality of curve segments according to the carbon emission data comprises the following specific steps:
Performing linear fitting on the carbon emission data by using a least square method to obtain a carbon emission curve, dividing the curve between adjacent extreme points in the carbon emission curve into a curve segment, and obtaining a plurality of curve segments; wherein the extreme points include a maximum point and a minimum point.
Further, the calculation formula of the data change amplitude of each curve segment is as follows:
Where S i,max represents the maximum carbon emission data in the ith curve segment, S i,min represents the minimum carbon emission data in the ith curve segment, T i represents the number of data included in the ith curve segment, b i represents the data change amplitude of the ith curve segment, and i represents the absolute value symbol.
Further, the calculation formula of the initial anomaly degree of each curve segment is as follows:
Where b i represents the data change amplitude of the ith curve segment, b j represents the data change amplitude of the jth curve segment, G represents the number of curve segments, G i represents the number of data contained in the ith curve segment, G j represents the number of data contained in the jth curve segment, Y i represents the initial anomaly of the ith curve segment, and i represents the absolute value sign.
Further, the calculation formula of the correction coefficient of each curve segment is as follows:
Where b i denotes the data change amplitude of the i-th curve segment, b i+2 denotes the data change amplitude of the i+2th curve segment, b i-2 denotes the data change amplitude of the i-2th curve segment, X i denotes the correction coefficient of the i-th curve segment, and i denotes the absolute value symbol.
Further, the true anomaly degree of each curve segment comprises the following specific steps:
and obtaining the true anomaly degree of each curve segment according to the product of the initial anomaly degree of each curve segment and the correction coefficient of each curve segment.
Further, the obtaining the parameter between each curve segment and the other curve segment according to the true anomaly degree of each curve segment, and obtaining the target curve segment of each curve segment according to the parameter between each curve segment and the other curve segment, includes the following specific steps:
the calculation formula of the parameters between each curve segment and the other curve segment is as follows:
Wherein Y 'i represents the true degree of abnormality of the ith curve segment, Y' i-n represents the true degree of abnormality of the ith-nth curve segment, B represents the average value of the true degrees of abnormality of all the curve segments, I represents the absolute value sign, and C i,n represents the parameter between the ith curve segment and the nth curve segment preceding the ith curve segment;
the process of obtaining the target curve segment of each curve segment is as follows: selecting another curve segment corresponding to the smallest parameter between the ith curve segment and another curve segment in front of the ith curve segment, and recording the another curve segment as a target curve segment of the ith curve segment.
Further, the corrected autoregressive order is obtained according to the parameters between each curve segment and the corresponding target curve segment, and the method comprises the following specific steps:
And marking a curve segment between the ith curve segment and a target curve segment of the ith curve segment as a marked curve segment, obtaining all data numbers in the marked curve segment, marking the data numbers as s, and obtaining the h data in the ith curve segment according to a time sequence, wherein the corrected autoregressive order when fitting and predicting according to the former data of the h data in the ith curve segment is as follows: p=s+h.
Further, the predicting the future carbon emission according to the corrected autoregressive order comprises the following specific steps:
the prediction formula of the corrected ARIMA model is as follows:
D＝AR(p)+I(d)+MA(q)
Wherein, p represents the corrected autoregressive order, D is the original differential order, q is the moving average order, D is the predicted data, AR represents the autoregressive hysteresis term, I represents the differential term, and MA represents the moving average hysteresis term;
and predicting through the corrected ARIMA model to obtain predicted data.
The invention also provides an intelligent low-carbon management system for realizing the carbon reaching peak carbon neutralization, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes any one of the steps when executing the computer program.
The technical scheme of the invention has the beneficial effects that: according to the method, the initial anomaly degree of each curve segment is obtained according to the data change amplitude and the contained data number of each curve segment by analyzing the carbon emission data, the true anomaly degree of each corrected curve segment is obtained by correcting the initial anomaly degree of each curve segment, and the accuracy of acquiring the anomaly data is improved; and obtaining the corrected orders of the autoregressive parts in the autoregressive moving average model through the real abnormal degrees of all curve segments, and reducing the calculation of the data quantity and improving the accuracy of data prediction through the corrected autoregressive orders.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a smart low-carbon management method for achieving carbon-to-carbon neutralization according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted for achieving the preset aim of the present invention, the following detailed description of specific embodiments, structures, features and effects thereof will be given with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the intelligent low-carbon management method and system for realizing carbon peak-to-carbon neutralization.
Referring to fig. 1, a flowchart of a smart low-carbon management method for achieving carbon-to-peak carbon neutralization according to an embodiment of the invention is shown, the method includes the following steps:
step S001: carbon emission data is collected.
In order to predict the carbon emission data using the ARIMA model, the collected carbon emission data is subject to a large deviation due to interference by other factors. In order to analyze whether there is abnormal data in the carbon emission data, it is necessary to analyze it, so this step collects the carbon emission data first and then analyzes it.
Specifically, the carbon emission generated by the combustion of coal in the production process of the power generation enterprises is collected, and all carbon emission data of the power generation enterprises in one year are obtained by taking the day as a unit.
Thus, carbon emission data was obtained.
Step S002: obtaining a plurality of curve segments according to the carbon emission data, obtaining the data change amplitude of each curve segment according to the carbon emission data in each curve segment, obtaining the initial anomaly degree of each curve segment according to the data change amplitude of each curve segment and the number of contained data, obtaining the correction coefficient of each curve segment according to the data change amplitude of each curve segment, and correcting the initial anomaly degree according to the correction coefficient of each curve segment to obtain the true anomaly degree of each curve segment.
It should be noted that in daily electricity consumption, electricity consumption conditions in different seasons and different time periods of each day are different, namely, in summer, the electricity consumption is large due to the use of an air conditioner, and the electricity consumption is large due to the use of an air conditioner and a small sun in winter, so that the electricity consumption is obviously increased in summer and winter compared with spring and autumn; the electricity consumption is more in the middle, upper and lower days of the day than in other time periods of the day, and abnormal conditions can be caused in the electricity consumption peak period due to the fact that the electricity consumption can exceed a certain limiting value, so that urban power failure can be caused; the power generation enterprises generally have no carbon emission when the city fails, and the power generation plant usually stops generating power activities when the city fails, so that the acquired carbon emission of the power generation enterprises belongs to abnormal data.
(1) And obtaining a plurality of curve segments according to the carbon emission data.
Further, since the obtained carbon emission data has abnormal data, the occurrence of the abnormal data is caused by one time, so that the abnormal data is reflected in a time period, that is, the abnormal data occurs only in a certain period, and for such a case, the obtained carbon emission data is subjected to a sectional analysis.
Specifically, the carbon emission data is subjected to linear fitting through a five-time polynomial by using a least square method to obtain a fitted curve, the fitted curve is recorded as a carbon emission curve, and all extreme points in the carbon emission curve are obtained; wherein the extreme points include a maximum point and a minimum point. In this embodiment, curve fitting is performed using a polynomial fitting of five times, but the present invention is not limited to this, and the practitioner may be determined according to the specific situation.
Segmenting a carbon emission curve according to extreme points, wherein the specific operation is as follows: and dividing the curve between adjacent extreme points in the carbon emission curve into a curve section to obtain a plurality of curve sections.
So far, a plurality of curve segments are obtained.
(2) And obtaining the data change amplitude of each curve segment according to the carbon emission data in each curve segment, and obtaining the initial anomaly of each curve segment according to the data change amplitude of each curve segment and the number of contained data.
It should be noted that, the data number and the data change amplitude corresponding to each curve segment are different, so that the abnormal condition of each curve can be analyzed according to the data number and the data change amplitude corresponding to each curve segment; when the number of data contained in each curve segment is larger, the corresponding curve segment is more abnormal, and conversely, the curve segment is more normal; and under normal conditions, the data change amplitude of the carbon emission amount in the same time should be the same, so that the difference between the data change amplitude of each curve segment and the average value of the data change amplitudes of all curve segments is obtained for analysis.
Specifically, the formula for calculating the data change amplitude of each curve segment, namely the data change amplitude of each curve segment, is:
Where S i,max represents the maximum carbon emission data in the ith curve segment, S i,min represents the minimum carbon emission data in the ith curve segment, T i represents the number of data included in the ith curve segment, b i represents the data change amplitude of the ith curve segment, and i represents the absolute value symbol.
Obtaining initial anomaly of each curve segment according to the data change amplitude of each curve segment and the number of contained data, wherein the initial anomaly is expressed as follows by a formula:
Where b i represents the data change amplitude of the ith curve segment, b j represents the data change amplitude of the jth curve segment, G represents the number of curve segments, G i represents the number of data contained in the ith curve segment, G j represents the number of data contained in the jth curve segment, Y i represents the initial anomaly of the ith curve segment, and i represents the absolute value sign.
Wherein,The larger the absolute value of the difference between the data change amplitude of the ith curve segment and the average value of the data change amplitudes of all the curve segments is, the larger the value is, and the larger the initial anomaly degree of the corresponding curve segment is; conversely, the smaller the value, the less the initial anomaly representing the corresponding curve segment. /(I)The larger the value of the ratio of the number of data contained in the ith curve segment to the total number of data contained in all curve segments is, the larger the initial degree of anomaly of the corresponding curve segment is; conversely, the smaller the value, the less the initial anomaly representing the corresponding curve segment.
(3) And obtaining the correction coefficient of each curve segment according to the data change amplitude of each curve segment.
It should be noted that, when the electricity consumption reaches a peak but does not reach a limit, the carbon emission amount at the moment is higher, so that the data at the moment is abnormal compared with the data at other times, and the trend in the abnormal curve segment may be unchanged, but can be corrected according to the data change amplitude of the curve segment with the same adjacent trend; therefore, the correction is carried out according to the data change amplitude values of the adjacent curve segments with the same trend in the curve segments, and the correction coefficient is analyzed according to the data change amplitude values of the curve segments.
Specifically, a correction coefficient of each curve segment is obtained according to the change amplitude of each curve segment, and the correction coefficient is expressed as follows:
where b i denotes the data change amplitude of the i-th curve segment, b i+2 denotes the data change amplitude of the i+2th curve segment, b i-2 denotes the data change amplitude of the i-2th curve segment, X i denotes the correction coefficient of the i-th curve segment, and i denotes the absolute value symbol. Wherein the purpose of adding 0.1 to the denominator is to prevent the denominator from being 0.
When the difference of the data change amplitude values of the curve segments with the same adjacent trend is larger, the initial abnormal degree of the corresponding curve segment is required to be corrected, namely the correction coefficient is larger; wherein the difference represents the absolute value of the difference.
It should be further noted that, since each curve segment is composed of curves of adjacent extreme points, each curve segment has either an ascending trend or a descending trend.
(4) And correcting the initial abnormal degree according to the correction coefficient of each curve segment to obtain the true abnormal degree of each curve segment.
Specifically, the initial anomaly degree is corrected according to the correction coefficient of each curve segment to obtain the true anomaly degree of each curve segment, and the true anomaly degree is expressed as follows:
Yi ′＝Xi×Yi
Where Y i represents the initial anomaly of the ith curve segment, X i represents the correction factor of the ith curve segment, and Y i ′ represents the true anomaly of the ith curve segment.
Wherein, when the initial abnormal degree of the curve segment is larger, the correction coefficient is larger, and the true abnormal degree of the corrected curve segment is also larger.
Thus, the true degree of abnormality of each curve segment is obtained.
Step S003: obtaining parameters between each curve segment and the other curve segment according to the real abnormal degree of each curve segment, and obtaining a target curve segment of each curve segment according to the parameters between each curve segment and the other curve segment; and obtaining corrected autoregressive orders according to the parameters between each curve segment and the corresponding target curve segment.
After the true degree of abnormality of each curve segment is obtained in the above steps, the adaptive order of the observation point is determined according to the true degree of abnormality of the curve segment where the observation point is located. Since the greater the true degree of abnormality of a curve segment, the greater the likelihood that the curve segment contains abnormal data, when determining the adaptive order, the number of data contained between a curve segment with the smallest difference from the true degree of the curve segment should be selected as much as possible as the order of the autoregressive portion in the ARIMA model, and the data is predicted again according to the new order obtained. The closer the curve segment with the smallest difference in true outliers is, the less data is needed at the time of prediction, and the smaller the corresponding autoregressive order is.
Specifically, the average value of the true outliers of all curve segments is obtained according to the true outliers of each curve segment,The parameters between each curve segment and the other curve segment are obtained according to the true abnormal degree of the curve segments and the average value of the true abnormal degrees of all the curve segments, and are expressed as follows by formulas:
Where Y 'i represents the true anomaly of the ith curve segment, Y' i-n represents the true anomaly of the ith-nth curve segment, B represents the mean of the true anomalies of all curve segments, I represents the absolute value sign, and C i,n represents the parameter between the ith curve segment and the ith-nth curve segment.
Wherein when Y 'i -B is less than or equal to 0, the true degree of abnormality of the ith curve segment is below the mean value of the true degrees of all curve segments, namely the molecular subtraction is negative, and the smaller the Y' i-Y′i-n is, the smaller the difference between the true degrees of the ith curve segment and the ith-n curve segments is, namely the smaller the parameters between the corresponding curve segments are. When Y 'i -B >0, it indicates that the true degree of abnormality of the ith curve segment is above the mean value of the true degrees of abnormality of all curve segments, i.e., the numerator is subtracted as a positive number, the smaller Y' i-Y′i-n, the smaller the difference between the true degree of abnormality of the ith curve segment and the ith-n curve segment, i.e., the smaller the parameters between the corresponding curve segments.
The number of curve segments closest to the actual difference degree is selected as the order of autoregressive, so that the calculated amount can be reduced during prediction, and the situations of over fitting and less fitting are prevented.
The order of the autoregressive is obtained according to the parameters between the two curve segments, specifically, another curve segment corresponding to the smallest parameter between the ith curve segment and the other curve segment before the ith curve segment is selected and recorded as the target curve segment of the ith curve segment. And marking a curve segment between the ith curve segment and a target curve segment of the ith curve segment as a marked curve segment, obtaining all data numbers in the marked curve segment, marking the data numbers as s, and obtaining the h data in the ith curve segment according to a time sequence, wherein the corrected autoregressive order when fitting and predicting according to the former data of the h data in the ith curve segment is as follows: p=s+h.
Thus, the corrected autoregressive order is obtained.
Step S004: and predicting the future carbon emission according to the corrected autoregressive order, and storing and managing the predicted data.
The ARIMA model is divided into three parts, including autoregressive order, differential order and moving average order. The differential order and the moving average order are unchanged, the differential order and the moving average order are determined through the ACF graph, and a method for obtaining the ACF graph is a known technology and will not be described in detail herein. The prediction formula of the corrected ARIMA model is:
D＝AR(p)+I(d)+MA(q)
Where p represents the corrected autoregressive order, D is the original differential order, q is the moving average order, D is the predicted data, AR represents the autoregressive hysteresis term, I represents the differential term, and MA represents the moving average hysteresis term.
And predicting through the corrected ARIMA model to obtain predicted data.
And then carrying out storage management on the predicted data.
The embodiment provides an intelligent low-carbon management system for realizing carbon peak-to-carbon neutralization, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes steps S001 to S004 when executing the computer program.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. An intelligent low-carbon management method for realizing carbon peak carbon neutralization is characterized by comprising the following steps:
Collecting carbon emission data;
Obtaining a plurality of curve segments according to the carbon emission data, obtaining a data change amplitude of each curve segment according to the carbon emission data in each curve segment, obtaining initial abnormal degree of each curve segment according to the data change amplitude of each curve segment and the number of contained data, obtaining a correction coefficient of each curve segment according to the data change amplitude of each curve segment, and correcting the initial abnormal degree according to the correction coefficient of each curve segment to obtain true abnormal degree of each curve segment;
obtaining parameters between each curve segment and the other curve segment according to the real abnormal degree of each curve segment, and obtaining a target curve segment of each curve segment according to the parameters between each curve segment and the other curve segment; obtaining corrected autoregressive orders according to parameters between each curve segment and the corresponding target curve segment;
And predicting the future carbon emission according to the corrected autoregressive order, and storing and managing the predicted data.
2. The intelligent low-carbon management method for realizing carbon-to-carbon neutralization according to claim 1, wherein the obtaining a plurality of curve segments according to the carbon emission data comprises the following specific steps:
Performing linear fitting on the carbon emission data by using a least square method to obtain a carbon emission curve, dividing the curve between adjacent extreme points in the carbon emission curve into a curve segment, and obtaining a plurality of curve segments; wherein the extreme points include a maximum point and a minimum point.
3. The intelligent low-carbon management method for realizing carbon-to-carbon neutralization according to claim 1, wherein the calculation formula of the data change amplitude of each curve segment is as follows:
Where S i,max represents the maximum carbon emission data in the ith curve segment, S i,min represents the minimum carbon emission data in the ith curve segment, T i represents the number of data included in the ith curve segment, b i represents the data change amplitude of the ith curve segment, and i represents the absolute value symbol.
4. The intelligent low-carbon management method for realizing carbon-to-carbon neutralization according to claim 1, wherein the calculation formula of the initial anomaly degree of each curve segment is as follows:
Where b i represents the data change amplitude of the ith curve segment, b j represents the data change amplitude of the jth curve segment, G represents the number of curve segments, G i represents the number of data contained in the ith curve segment, G j represents the number of data contained in the jth curve segment, Y i represents the initial anomaly of the ith curve segment, and i represents the absolute value sign.
5. The intelligent low-carbon management method for realizing carbon-to-carbon neutralization according to claim 1, wherein the calculation formula of the correction coefficient of each curve segment is as follows:
Where b i denotes the data change amplitude of the i-th curve segment, b i+2 denotes the data change amplitude of the i+2th curve segment, b i-2 denotes the data change amplitude of the i-2th curve segment, X i denotes the correction coefficient of the i-th curve segment, and i denotes the absolute value symbol.
6. The intelligent low-carbon management method for realizing carbon-to-carbon neutralization according to claim 1, wherein the true anomaly of each curve segment comprises the following specific steps:
and obtaining the true anomaly degree of each curve segment according to the product of the initial anomaly degree of each curve segment and the correction coefficient of each curve segment.
7. The intelligent low-carbon management method for realizing carbon-peak-carbon neutralization according to claim 1, wherein the obtaining parameters between each curve segment and another curve segment according to the true degree of abnormality of each curve segment and obtaining the target curve segment of each curve segment according to the parameters between each curve segment and another curve segment comprises the following specific steps:
the calculation formula of the parameters between each curve segment and the other curve segment is as follows:
wherein Y i 'represents the true degree of abnormality of the ith curve segment, Y' i-n represents the true degree of abnormality of the ith-nth curve segment, B represents the average value of the true degrees of abnormality of all the curve segments, I represents the absolute value sign, and C i,n represents the parameter between the ith curve segment and the nth curve segment preceding the ith curve segment;
the process of obtaining the target curve segment of each curve segment is as follows: selecting another curve segment corresponding to the smallest parameter between the ith curve segment and another curve segment in front of the ith curve segment, and recording the another curve segment as a target curve segment of the ith curve segment.
8. The intelligent low-carbon management method for realizing carbon-to-carbon neutralization according to claim 1, wherein the corrected autoregressive order is obtained according to parameters between each curve segment and the corresponding target curve segment, comprising the following specific steps:
And marking a curve segment between the ith curve segment and a target curve segment of the ith curve segment as a marked curve segment, obtaining all data numbers in the marked curve segment, marking the data numbers as s, and obtaining the h data in the ith curve segment according to a time sequence, wherein the corrected autoregressive order when fitting and predicting according to the former data of the h data in the ith curve segment is as follows: p=s+h.
9. The intelligent low-carbon management method for realizing carbon-to-carbon neutralization according to claim 1, wherein the predicting of the future carbon emission according to the corrected autoregressive order comprises the following specific steps:
the prediction formula of the corrected ARIMA model is as follows:
D＝AR(p)+I(d)+MA(q)
Wherein, p represents the corrected autoregressive order, D is the original differential order, q is the moving average order, D is the predicted data, AR represents the autoregressive hysteresis term, I represents the differential term, and MA represents the moving average hysteresis term;
and predicting through the corrected ARIMA model to obtain predicted data.
10. A smart low carbon management system for achieving carbon-to-peak carbon neutralization comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor, when executing the computer program, performs the steps of a smart low carbon management method for achieving carbon-to-peak carbon neutralization as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410218173.4A CN117952806A (en) | 2024-02-28 | 2024-02-28 | Intelligent low-carbon management method and system for realizing carbon-to-peak carbon neutralization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410218173.4A CN117952806A (en) | 2024-02-28 | 2024-02-28 | Intelligent low-carbon management method and system for realizing carbon-to-peak carbon neutralization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117952806A true CN117952806A (en) | 2024-04-30 |
Family
ID=90803724
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410218173.4A Withdrawn CN117952806A (en) | 2024-02-28 | 2024-02-28 | Intelligent low-carbon management method and system for realizing carbon-to-peak carbon neutralization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117952806A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118278954A (en) * | 2024-05-07 | 2024-07-02 | 深圳中迈信息技术有限公司 | Smart city carbon neutralization data acquisition method and system |
-
2024
- 2024-02-28 CN CN202410218173.4A patent/CN117952806A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118278954A (en) * | 2024-05-07 | 2024-07-02 | 深圳中迈信息技术有限公司 | Smart city carbon neutralization data acquisition method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116307652A (en) | A smart grid artificial intelligence resource allocation method | |
| CN117294019B (en) | Environment-friendly building energy consumption monitoring method and system based on Internet of things | |
| CN119200486B (en) | A smart energy integrated management method and system for dual carbon regulation | |
| CN112766535B (en) | Building load prediction method and system considering load curve characteristics | |
| CN117829374A (en) | Prediction method and system for power consumption of iron and steel enterprises | |
| CN118536638B (en) | Power optimization method and system based on intelligent data processing analysis and digital twin | |
| CN118693887B (en) | An optimization method for controlling wind power prediction error during black start of overcapacity energy storage | |
| CN117952806A (en) | Intelligent low-carbon management method and system for realizing carbon-to-peak carbon neutralization | |
| CN113516271A (en) | Wind power cluster power day-ahead prediction method based on space-time neural network | |
| CN118033784A (en) | Meteorological prediction method and system for micro-topography overhead transmission line | |
| CN117521501A (en) | NSGA-based LSTM prediction energy power generation method and system | |
| CN111626476B (en) | Wind power plant wind power generation capacity prediction method | |
| CN119831618A (en) | Carbon emission prediction system and method | |
| CN114676866A (en) | Method, device and storage medium for correcting load prediction before day based on error correction | |
| CN114219182B (en) | Abnormal weather scene wind power prediction method based on reinforcement learning | |
| CN119134282A (en) | A photovoltaic power generation prediction method and system based on convolutional neural network | |
| CN117634678A (en) | Low-carbon park carbon emission prediction method based on actual operation scene | |
| CN116187516A (en) | Big data-based analysis and correction method | |
| CN113469413B (en) | Error correction method for weather forecast in short-term load prediction | |
| CN119940665B (en) | A method, system, device and medium for predicting user load in power market | |
| CN118780449B (en) | A method for predicting power load | |
| CN119830188A (en) | Intelligent battery life monitoring and predicting method | |
| CN119852981A (en) | BP neural network-based photovoltaic power station power prediction method and system | |
| CN120031275A (en) | Multi-time-scale-based mountain area power grid source and network load storage collaborative planning method | |
| CN120389386A (en) | New energy output prediction method and system based on Monte Carlo Dropout |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20240430 |
|
| WW01 | Invention patent application withdrawn after publication |