CN114677052A - Natural gas load fluctuation asymmetry analysis method and system based on TARCH model - Google Patents

Natural gas load fluctuation asymmetry analysis method and system based on TARCH model Download PDF

Info

Publication number
CN114677052A
CN114677052A CN202210452567.7A CN202210452567A CN114677052A CN 114677052 A CN114677052 A CN 114677052A CN 202210452567 A CN202210452567 A CN 202210452567A CN 114677052 A CN114677052 A CN 114677052A
Authority
CN
China
Prior art keywords
natural gas
gas load
data set
tarch
model
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
Application number
CN202210452567.7A
Other languages
Chinese (zh)
Inventor
边根庆
孙世冲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian University of Architecture and Technology
Original Assignee
Xian University of Architecture and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xian University of Architecture and Technology filed Critical Xian University of Architecture and Technology
Priority to CN202210452567.7A priority Critical patent/CN114677052A/en
Publication of CN114677052A publication Critical patent/CN114677052A/en
Pending legal-status Critical Current

Links

Images

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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Abstract

The invention discloses a method and a system for analyzing asymmetry of natural gas load fluctuation based on a TARCH model, which comprises the steps of preprocessing an obtained natural gas data set, and dividing the natural gas data set according to year to form comparative analysis on a time span; using an ADF unit root inspection method to inspect whether a natural gas load sequence is stable or not so as to avoid a pseudo regression phenomenon in the regression process; the ARCH effect of the verified data set is verified, whether the data set has the ARCH effect is judged, finally, fluctuation asymmetry analysis based on a TARCH model is conducted on the data set judged through the ARCH effect, fluctuation asymmetry analysis is conducted on the gas load data set for natural gas through the TARCH model, the final analysis result is obtained, natural gas negative pressure prediction is conducted according to the analysis result, and prediction accuracy can be improved.

Description

Natural gas load fluctuation asymmetry analysis method and system based on TARCH model
Technical Field
The invention belongs to the field of data analysis, and particularly relates to a method and a system for analyzing asymmetry of natural gas load fluctuation based on a TARCH model.
Background
The natural gas is used as a clean and efficient energy source, the defects that wind energy and solar energy are not easy to store and unstable in supply can be effectively overcome, and the large trend that the natural gas replaces high-carbon and high-pollution coal cannot be reversed, so that the development of the natural gas can certainly drive the rapid development of urban natural gas. This is followed by a series of events such as: the replacement of urban gas sources, the planning of urban gas pipe networks, the construction of gas storage facilities and the like. In order to solve these problems, the research work of the gas load prediction method is very important.
The existing natural gas load prediction method is often lack of analysis on natural gas load characteristics, so that the natural gas load prediction is inaccurate, however, the natural gas load has remarkable non-linear characteristics such as periodicity, uncertainty and volatility, and a common mathematical model is difficult to accurately grasp the characteristics, so that the characteristics and the law of the natural gas load need to be analyzed, and accurate reference data is provided for the natural gas load prediction.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a system for analyzing the fluctuation asymmetry of the natural gas load based on a TARCH model, which are used for analyzing the fluctuation asymmetry characteristic of a natural gas load sequence and providing data support for natural gas load prediction.
The invention is realized by the following technical scheme:
a natural gas load fluctuation asymmetry analysis method based on a TARCH model comprises the following steps:
step 1, acquiring a natural gas load data set of a historical time period and preprocessing the natural gas load data set;
step 2, dividing the data set preprocessed in the step 1 into a plurality of natural gas data subsets according to time periods;
step 3, verifying the stationarity of each natural gas data subset, and verifying the ARCH effect of the natural gas data subset passing the stationarity verification by adopting a white noise test method;
and 4, performing fluctuation asymmetry analysis on the natural gas data subset which passes the ARCH effect verification by adopting a threshold autoregressive conditional variance model, and predicting the gas load for the natural gas according to the analysis result.
Preferably, the preprocessing is to process missing values and abnormal values in the natural gas load data set.
Preferably, abnormal values in the natural gas load data set are detected and removed by using a K-means algorithm, and missing values in the natural gas load data set are filled by using a mean interpolation method.
Preferably, the method for detecting and eliminating the abnormal value by using the K-nearest neighbor method comprises the following steps:
randomly selecting K sample points from the natural gas load data set as a centroid, calculating the distance between the residual samples and the centroid to divide the attribution degree of the samples to the clusters, calculating the distance between each sample and the centroid based on the clustering result, and judging the sample to be an abnormal value if the distance is greater than a threshold value.
Preferably, the ADF unit root test method is adopted in the step 3 to test the stability of the natural gas data subset.
Preferably, the method for verifying the ARCH effect by adopting a white noise test method in the step 3 comprises the following steps:
setting an original hypothesis H0 and an alternative hypothesis H1;
constructing statistics according to the original hypothesis H0 and the alternative hypothesis H1;
under the condition that the original hypothesis is established, the statistic Q (m) obeys chi-square distribution with the degree of freedom m, and a rejection region is obtained by combining a given significance level alpha;
and performing Lung-Box test on the natural gas data subset, and when the test result rejects the original hypothesis, the natural gas data subset has the ARCH effect.
Preferably, the expression of the statistic is as follows:
Figure BDA0003619338760000021
where T is the sample volume,
Figure BDA0003619338760000022
is the autocorrelation coefficient of the i-th order lag.
The rejection region is
Figure BDA0003619338760000023
Wherein alpha is quantile and m is highest order.
Preferably, the asymmetry analysis method of the threshold autoregressive conditional heteroscedasticity model is as follows;
the expression of the threshold autoregressive conditional heteroscedasticity model is as follows:
Figure BDA0003619338760000031
wherein σtFor the current fluctuation rate, epsilontWhite noise, μ, independently identically distributed with zero mean unit variancetFor current residual, It-1Is an illustrative variable, γ1Is a parameter;
if gamma is1Not equal to 0, the natural gas load dataset is asymmetric; if gamma is equal to1If the value is less than 0, the asymmetric effect is shown that the time sequence is influenced by positive impact more greatly than negative impact; if gamma is1> 0, the asymmetric effect appears as the time series is more affected by negative impacts than by positive impacts.
A system of a natural gas load fluctuation asymmetry analysis method based on a TARCH model comprises a data set construction module, a data set preprocessing module and a data set analysis module, wherein the data set construction module is used for constructing a natural gas load data set and preprocessing the natural gas load data set;
the segmentation module is used for dividing the natural gas load data set into a plurality of natural gas data subsets according to time periods;
the verification module is used for verifying the stationarity of each natural gas data subset and verifying the ARCH effect of the natural gas data subset passing the stationarity verification by adopting a white noise test method;
and the analysis module is used for carrying out fluctuation asymmetry analysis on the natural gas data subset which passes the ARCH effect verification by adopting a threshold autoregressive condition variance model and carrying out natural gas consumption load prediction according to an analysis result.
A computer arrangement comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of a TARCH model based natural gas load fluctuation asymmetry analysis method when executing the computer program.
Compared with the prior art, the invention has the following beneficial technical effects:
the invention designs a method for analyzing asymmetry of natural gas load fluctuation based on a TARCH model, which comprises the steps of preprocessing an obtained natural gas data set, and then dividing the natural gas data set according to year to form comparative analysis on a time span; using an ADF unit root inspection method to inspect whether a natural gas load sequence is stable or not so as to avoid a pseudo regression phenomenon in the regression process; the ARCH effect of the verified data set is verified, whether the data set has the ARCH effect is judged, finally, fluctuation asymmetry analysis based on a TARCH model is conducted on the data set judged through the ARCH effect, fluctuation asymmetry analysis is conducted on the gas load data set for natural gas through the TARCH model, the final analysis result is obtained, natural gas negative pressure prediction is conducted according to the analysis result, and prediction accuracy can be improved.
Drawings
FIG. 1 is a flow chart of the fluctuation asymmetry analysis of the TARCH model of the present invention;
FIG. 2 is a schematic diagram of the fluctuation sequence of the natural gas usage load of the present invention;
FIG. 3 is a diagram showing the results of the TARCH model analysis of the present invention.
Detailed Description
The present invention will now be described in further detail with reference to the attached drawings, which are illustrative, but not limiting, of the present invention.
Referring to fig. 1-3, a natural gas load fluctuation asymmetry analysis method based on a TARCH model includes the following steps:
step 1, acquiring a natural gas load data set of a historical time period, processing missing values and abnormal values in the natural gas load data set, detecting and removing the abnormal values by using a K-means algorithm, and filling the missing values by using a mean interpolation method.
Specifically, the missing values are filled by using a mean interpolation method, wherein the missing rate of some users is higher, and the users with higher missing rate are simply deleted. And filling the data with low deletion rate by adopting a mean interpolation method.
For example, during data collection or transmission, a missing condition may occur. For example, the data consumption of the user is lost due to damage or abnormality of the acquisition terminal of the natural gas meter, which results in failure of partial data acquisition, or loss or damage of the data file during data transmission. Therefore, missing value padding is also an important step, in which the missing rate of some users is high, and for the users with high missing rate, the users are simply deleted. For data with a low missing rate, a mean interpolation method is adopted for filling, for example, some users lack the natural gas consumption in 2018 and 12 months, and the average value of the natural gas consumption in 16 years and 17 years and 12 months is taken as a substitute value of a missing value.
And (3) detecting and removing abnormal values by using a K-nearest neighbor method: randomly selecting K sample points from the natural gas load data set as a centroid, calculating the distance between the residual samples and the centroid to divide the attribution degree of the samples to clusters, calculating the distance between each sample and the centroid based on the clustering result, and judging the sample to be an abnormal value if the distance is greater than a threshold value. When the model is used for judging the abnormal value of the natural gas load data set, the normal data and the abnormal data need to be ensured to be as complete as possible, otherwise, the clustering effect is influenced, and the abnormal value is influenced. The calculation method of the distance adopts an Euclidean distance method, the category number K of the clusters can be judged through an inflection point method, namely, the data agglomeration degree (SSE variance) is judged, when the agglomeration degree is sharply reduced along with the K value, an inflection point appears, and if the K value is continuously increased, the accuracy of natural gas load data classification is reduced.
And 2, dividing the natural gas load data set into a plurality of natural gas data subsets according to set rules. Segmenting the data set according to the size of the natural gas load data set in a partitioning mode of at least every other year so as to form comparative analysis on a time span;
specifically, in this embodiment, the natural gas data set is divided by year: the dataset may be segmented in partitions of at least every other year depending on the size of the dataset to form a comparative analysis over a span of time, such as three phases as partitioning the full segment 2015 into 1, 31, and 2020, 7, 19. The time range of the first stage is 2015 year 1 month 31 days to 2016 year 12 month 31 days, the time range of the second stage is 2017 year 1 month 1 days to 2018 year 12 month 31 days, and the time range of the third stage is 2019 year 1 month 1 days to 2020 year 7 month 19 days.
Step 3, respectively carrying out stability verification on the natural gas load sequence on the plurality of natural gas data subsets obtained in the step 2;
using ADF unit root test method to test whether the natural gas load sequence is stable or not so as to avoid the phenomenon of pseudo regression in the regression process, wherein the ADF test method adds dependent variable y to the right side of regression equationtThe hysteresis differential term controls the correlation of a high-order sequence, the probability value of the natural gas load sequence is obtained according to a regression equation, the probability value is compared with a set probability value, the stationarity of the natural gas load sequence is determined, and the basic equation expression of an ADF unit root test method is as follows:
Figure BDA0003619338760000061
Figure BDA0003619338760000062
the original assumption is that: the original assumption is that there is at least one unit root, and the alternative assumption is that there is no unit root in the sequence. The specific method comprises the following steps: a probability value P (typically 1%, 5% or 10%) is set before the test, and if the resulting test value is less than this probability value, the probability that the time series rejects the original hypothesis will be 1-P. The P value is set to 1% here, that is, if the unit root test value of the natural gas load sequence is less than 0.01, the probability that the sequence will be stable reaches 99%, and the sequence can be considered to be stable.
And 4, performing ARCH effect verification on the natural gas data subset which passes through the stationarity verification in the step 3.
The ARCH effect check is used for judging whether the data set has the ARCH effect, and the fluctuation asymmetry analysis based on the TACCH model can be carried out only through the ARCH effect judgment. The invention adopts a Lung-Box white noise test method, and has no ARCH effect when the test is not obvious and has ARCH effect when the test is obvious. Firstly, obtaining the residual error of the gas sequence for natural gas, and then carrying out Lung-Box white noise test on the square of the residual error.
The original hypothesis and the alternative hypothesis of the Lung-Box test are respectively:
h0 original data are all independent, i.e. overall correlation coefficient is 0, some of the observed correlations are only due to random sampling errors. Namely that
Figure BDA0003619338760000063
Where m is set to an upper bound.
H1 original data is not independent, namely at least some data exists
Figure BDA0003619338760000064
Wherein k < ═ m.
The statistics constructed were:
Figure BDA0003619338760000065
where T is the volume of the sample,
Figure BDA0003619338760000066
is the autocorrelation coefficient of the i-th order lag.
The statistic q (m) obeys a chi-square distribution with a degree of freedom m, under the condition that the original assumption holds. Given a significance level α, the rejection zone is
Figure BDA0003619338760000067
And performing Lung-Box test on the natural gas data subset, and when the test result rejects the original hypothesis, indicating that the natural gas data subset has the ARCH effect.
And 5, adopting a TARCH model (threshold autoregressive conditional variance model) to carry out fluctuation asymmetry analysis on the natural gas data subset which passes the ARCH effect verification.
In order to characterize the asymmetry of the time series fluctuations, the TARCH model adds a parameter to fit the possible asymmetry in the data based on the GARCH model. The basic equation is described as follows:
Figure BDA0003619338760000071
in the formula, σtFor the current fluctuation rate, epsilontWhite noise, μ, independently identically distributed with zero mean unit variancetIs the current residual. For the TARCH (1,1,1) model, It-1Is an illustrative variable: when u ist-1When less than 0, It-11 is ═ 1; otherwise, It-10. In this model, the impact (u) is positivet> 0) and negative impacts (u)t< 0) has different intensity effects on condition variance: the positive impact has an alpha1Has an impact of alpha in the negative direction1+β1The impact of (2). If gamma is1Not equal to 0, it is asymmetric; if gamma is1If the value is less than 0, the asymmetric effect is shown that the time sequence is influenced by positive impact more greatly than negative impact; if gamma is1If the impact is greater than 0, then the asymmetric effect is shown as the time series is affected more by the negative impact than by the positive impact[24]。
Fitting the natural gas data subset using a TARCH model to obtain ut-1、It-1、ut、α1、β1If the analysis result shows that the fluctuation asymmetry characteristic of the data set is more remarkable, the sigma in the formula is obtained by a one-step rolling time window prediction method through a TARCH (1,1) modelt、μtAnd an asymmetric term u2 tItAnd the prediction model is placed in a natural gas load prediction model by taking the parameter as a parameter, so that the prediction precision of the natural gas load is improved.
The invention provides a natural gas load fluctuation asymmetry analysis method of a TARCH model, which introduces characteristic engineering, and firstly carries out data preprocessing before carrying out fluctuation asymmetry analysis of the TARCH model, such as filling missing values by a mean filling method, removing possible abnormal values by a K-nearest neighbor method, and segmenting a data set, thereby enabling the analysis to be more accurate; and secondly, combining the volatility modeling analysis with the natural gas load, analyzing the fluctuation symmetry rule in the volatility modeling analysis, and predicting the natural gas load according to the analysis result.
Example 1
A natural gas load fluctuation asymmetry analysis method based on a TARCH model comprises the following steps:
1) and detecting and removing abnormal values in the acquired natural gas load data set by using a K-means algorithm, and filling missing values in the natural gas load data set by using a mean interpolation method.
2) Segmenting the data set according to the size of the natural gas load data set in a dividing mode every other year to obtain a plurality of natural gas data subsets so as to form comparative analysis on a time span;
3) and (3) using an ADF (automatic force analysis) unit root inspection method to inspect whether the natural gas load sequence is stable or not so as to avoid a pseudo regression phenomenon in the regression process.
The verification results are shown in table 1:
TABLE 1 ADF Unit root check results
Figure BDA0003619338760000081
The P values are all less than 0.01, which indicates that the original hypothesis is rejected under the verification level of 1%, so that the natural gas sequence passes the stability verification.
4) And verifying the natural gas data subset which passes the stability verification by adopting a Lung-Box white noise inspection method.
The verification results are shown in table 2:
TABLE 2 ARCH Effect check-up results
Figure BDA0003619338760000091
P values were all less than 0.01, indicating that the original hypothesis was rejected at the 1% check level, and therefore the natural gas usage train passed the ARCH effect check.
5) Fluctuation asymmetry analysis based on TARCH (1,1) model: and (3) carrying out fluctuation asymmetry analysis on the natural gas load data set by using a TARCH (1,1) model.
In order to characterize the asymmetry of time series fluctuations, the TARCH model adds a parameter to fit the possible asymmetry in the data based on the GARCH model. The basic equation is described as follows:
Figure BDA0003619338760000092
the analytical results are shown in table 3:
TABLE 3 results of the TARCH (1,1) model analysis
Figure BDA0003619338760000093
Figure BDA0003619338760000101
Note: variables RESID (-1) ^2, GARCH (-1) and RESID (-1) ^2 (RESID (-1)<0) Are respectively as
Figure BDA0003619338760000102
Coefficient of (a)1、β1And gamma1。
From the results of the analysis of the TARCH (1,1) model, it can be concluded that: (1) the stronger the fluctuation aggregation of the natural gas using sequence, the more easily the fluctuation asymmetry characteristic is shown; (2) when the natural gas air load has the fluctuation asymmetry characteristic, the influence of the negative impact on the fluctuation is larger than the influence of the positive impact on the fluctuation.
A system of a natural gas load fluctuation asymmetry analysis method based on a TARCH model comprises a data set construction module, a data set preprocessing module and a data set processing module, wherein the data set construction module is used for constructing a natural gas load data set and preprocessing the natural gas load data set;
the natural gas load data set is divided into a plurality of natural gas data subsets according to time periods;
the verification module is used for verifying the stationarity of each natural gas data subset and verifying the ARCH effect of the natural gas data subset passing the stationarity verification by adopting a white noise test method;
and the analysis module is used for carrying out fluctuation asymmetry analysis on the natural gas data subset which passes the ARCH effect verification by adopting a threshold autoregressive condition variance model and carrying out natural gas consumption load prediction according to an analysis result.
The division of the modules in the embodiments of the present invention is schematic, and is only a logical function division, and in actual implementation, there may be another division manner, and in addition, each functional module in each embodiment of the present invention may be integrated in one processor, or may exist alone physically, or two or more modules are integrated in one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
In yet another embodiment of the present invention, a computer device is provided that includes a processor and a memory for storing a computer program comprising program instructions, the processor for executing the program instructions stored by the computer storage medium. The Processor may be a Central Processing Unit (CPU), or may be other general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable gate array (FPGA) or other Programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc., which is a computing core and a control core of the terminal, and is specifically adapted to load and execute one or more instructions in a computer storage medium to implement a corresponding method flow or a corresponding function; the processor of the embodiment of the invention can be used for the operation of the natural gas load fluctuation symmetry analysis method based on the GARCH model.
In yet another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a Memory device in a computer device and is used for storing programs and data. It is understood that the computer readable storage medium herein can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also, one or more instructions, which may be one or more computer programs (including program code), are stored in the memory space and are adapted to be loaded and executed by the processor. It should be noted that the computer-readable storage medium may be a high-speed RAM memory, or may be a non-volatile memory (non-volatile memory), such as at least one disk memory. One or more instructions stored in the computer-readable storage medium may be loaded and executed by a processor to implement the corresponding steps of the above-described embodiments with respect to the method for analyzing natural gas load fluctuation symmetry based on the GARCH model.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.

Claims (10)

1. A natural gas load fluctuation asymmetry analysis method based on a TARCH model is characterized by comprising the following steps:
step 1, acquiring a natural gas load data set of a historical time period and preprocessing the natural gas load data set;
step 2, dividing the data set preprocessed in the step 1 into a plurality of natural gas data subsets according to time periods;
step 3, verifying the stationarity of each natural gas data subset, and verifying the ARCH effect of the natural gas data subset passing the stationarity verification by adopting a white noise inspection method;
and 4, performing fluctuation asymmetry analysis on the natural gas data subset which passes the ARCH effect verification by adopting a threshold autoregressive conditional variance model, and predicting the gas load for the natural gas according to the analysis result.
2. The method for analyzing asymmetry of natural gas load fluctuation based on the TARCH model according to claim 1, wherein the preprocessing is to process missing values and abnormal values in the natural gas load data set.
3. The natural gas load fluctuation asymmetry analysis method based on the TARCH model according to claim 2, characterized in that abnormal values in the natural gas load data set are detected and removed by using a K-means algorithm, and missing values in the natural gas load data set are filled by using a mean interpolation method.
4. The natural gas load fluctuation asymmetry analysis method based on the TARCH model according to claim 3, characterized in that the method for detecting and eliminating the abnormal values by using the K-nearest neighbor method is as follows:
randomly selecting K sample points from the natural gas load data set as a centroid, calculating the distance between the residual samples and the centroid to divide the attribution degree of the samples to the clusters, calculating the distance between each sample and the centroid based on the clustering result, and judging the sample to be an abnormal value if the distance is greater than a threshold value.
5. The method for analyzing asymmetry of natural gas load fluctuation based on the TARCH model of claim 1, wherein in step 3, an ADF root-mean-square method is used to test the stationarity of the natural gas data subset.
6. The asymmetry analysis method for natural gas load fluctuation based on the TARCH model according to claim 1, wherein the method for performing ARCH effect verification by using a white noise test in step 3 is as follows:
setting an original hypothesis H0 and an alternative hypothesis H1;
constructing statistics according to the original hypothesis H0 and the alternative hypothesis H1;
under the condition that the original hypothesis is established, the statistic Q (m) obeys chi-square distribution with the degree of freedom m, and a rejection region is obtained by combining a given significance level alpha;
and performing Lung-Box test on the natural gas data subset, and when the test result rejects the original hypothesis, the natural gas data subset has the ARCH effect.
7. The method for analyzing asymmetry of natural gas load fluctuation based on the TARCH model of claim 1, wherein the statistical quantity is expressed as follows:
Figure FDA0003619338750000021
where T is the sample volume,
Figure FDA0003619338750000022
is the autocorrelation coefficient of the i-th order lag;
the rejection region is
Figure FDA0003619338750000023
Wherein alpha is quantile and m is highest order.
8. The asymmetry analysis method for natural gas load fluctuation based on the TARCH model according to claim 1, characterized in that the asymmetry analysis method of the threshold autoregressive conditional variance model is as follows;
the expression of the threshold autoregressive conditional heteroscedasticity model is as follows:
Figure FDA0003619338750000024
wherein σtFor the current fluctuation rate, epsilontWhite noise, μ, independently co-distributed with zero mean unit variancetFor current residual, It-1Is an illustrative variable, γ1Is a parameter;
if gamma is1Not equal to 0, the natural gas load dataset is asymmetric; if gamma is1If the time sequence is less than 0, the asymmetric effect is shown that the time sequence is greatly influenced by positive impact than negative impact; if gamma is1> 0, the asymmetric effect appears as the time series is more affected by negative impacts than by positive impacts.
9. A system of the natural gas load fluctuation asymmetry analysis method based on the TARCH model according to any one of claims 1-8, comprising,
the data set construction module is used for constructing a natural gas load data set and preprocessing the natural gas load data set;
the segmentation module is used for dividing the natural gas load data set into a plurality of natural gas data subsets according to time periods;
the verification module is used for verifying the stationarity of each natural gas data subset and verifying the ARCH effect of the natural gas data subset passing the stationarity verification by adopting a white noise test method;
and the analysis module is used for carrying out fluctuation asymmetry analysis on the natural gas data subset which passes the ARCH effect verification by adopting a threshold autoregressive conditional heteroscedasticity model and carrying out natural gas consumption load prediction according to an analysis result.
10. A computer arrangement comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor when executing the computer program implements the steps of the method for analyzing asymmetry of natural gas load fluctuation based on a TARCH model according to any of the claims 1-8.
CN202210452567.7A 2022-04-27 2022-04-27 Natural gas load fluctuation asymmetry analysis method and system based on TARCH model Pending CN114677052A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210452567.7A CN114677052A (en) 2022-04-27 2022-04-27 Natural gas load fluctuation asymmetry analysis method and system based on TARCH model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210452567.7A CN114677052A (en) 2022-04-27 2022-04-27 Natural gas load fluctuation asymmetry analysis method and system based on TARCH model

Publications (1)

Publication Number Publication Date
CN114677052A true CN114677052A (en) 2022-06-28

Family

ID=82079431

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210452567.7A Pending CN114677052A (en) 2022-04-27 2022-04-27 Natural gas load fluctuation asymmetry analysis method and system based on TARCH model

Country Status (1)

Country Link
CN (1) CN114677052A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115130776A (en) * 2022-07-13 2022-09-30 江南大学 Wind power plant load prediction method based on Laplace asymmetric v-type TSVR

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115130776A (en) * 2022-07-13 2022-09-30 江南大学 Wind power plant load prediction method based on Laplace asymmetric v-type TSVR
CN115130776B (en) * 2022-07-13 2023-06-09 江南大学 Wind power plant load prediction method based on Law asymmetric v-type TSVR

Similar Documents

Publication Publication Date Title
CN109472004B (en) Comprehensive evaluation method, device and system for influences of climate change and human activities on hydrology and drought
CN107168995B (en) Data processing method and server
CN111639783A (en) Line loss prediction method and system based on LSTM neural network
CN113221960B (en) Construction method and collection method of high-quality vulnerability data collection model
CN114677052A (en) Natural gas load fluctuation asymmetry analysis method and system based on TARCH model
CN113569462A (en) Distribution network fault level prediction method and system considering weather factors
CN115034485A (en) Wind power interval prediction method and device based on data space
CN104021180A (en) Combined software defect report classification method
WO2019019429A1 (en) Anomaly detection method, device and apparatus for virtual machine, and storage medium
CN114662712A (en) Rotating machine state monitoring method based on Wasserstein depth digital twin model
CN113822336A (en) Cloud hard disk fault prediction method, device and system and readable storage medium
CN108446213A (en) A kind of static code mass analysis method and device
CN110287114B (en) Method and device for testing performance of database script
CN116992362A (en) Transformer fault characterization feature quantity screening method and device based on Xia Puli value
WO2022222230A1 (en) Indicator prediction method and apparatus based on machine learning, and device and storage medium
CN115357764A (en) Abnormal data detection method and device
CN114139408A (en) Power transformer health state assessment method
CN112732549B (en) Test program classification method based on cluster analysis
CN112712194A (en) Electric quantity prediction method and device for power consumption cost intelligent optimization analysis
CN114723173A (en) Natural gas load fluctuation symmetry analysis method and system based on GARCH model
CN112819085A (en) Model optimization method and device based on machine learning and storage medium
CN113139673A (en) Method, device, terminal and storage medium for predicting air quality
CN113919609A (en) Power distribution network model quality comprehensive evaluation method and system
CN110516659A (en) The recognition methods of ball-screw catagen phase, device, equipment and storage medium
CN115185920B (en) Method, device and equipment for detecting log type

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