CN112580880A - Capacity prediction method, computer processor and terminal equipment - Google Patents

Capacity prediction method, computer processor and terminal equipment Download PDF

Info

Publication number
CN112580880A
CN112580880A CN202011542335.8A CN202011542335A CN112580880A CN 112580880 A CN112580880 A CN 112580880A CN 202011542335 A CN202011542335 A CN 202011542335A CN 112580880 A CN112580880 A CN 112580880A
Authority
CN
China
Prior art keywords
capacity
sequence
time
value
instant
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.)
Granted
Application number
CN202011542335.8A
Other languages
Chinese (zh)
Other versions
CN112580880B (en
Inventor
梁健睿
吴志刚
韩文哲
查雅行
刘昕
罗庆勇
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.)
China Communications Information Technology Group Co ltd
Original Assignee
China Communications Information Technology Group Co ltd
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 China Communications Information Technology Group Co ltd filed Critical China Communications Information Technology Group Co ltd
Priority to CN202011542335.8A priority Critical patent/CN112580880B/en
Publication of CN112580880A publication Critical patent/CN112580880A/en
Application granted granted Critical
Publication of CN112580880B publication Critical patent/CN112580880B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3051—Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a capacity prediction method, a computer processor and a terminal device. When the capacity is predicted, two prediction processes are provided according to whether the detected capacity is abnormally changed. When the detected capacity is not abnormally changed, capacity prediction is carried out according to a mean value method; when the abnormal change of the capacity is detected, the time range of the abnormal change of the capacity needs to be judged, the abnormal capacity in the time range is smoothed, and finally the capacity is predicted according to an average method. Therefore, the invention can accurately predict the capacity change and effectively control the operation and maintenance cost.

Description

Capacity prediction method, computer processor and terminal equipment
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a capacity prediction method, a computer processor, and a terminal device.
Background
With the rapid development of information technology, the information amount shows a remarkable growth trend, and the resource pool in companies engaged in businesses such as software technology is more and more in resource and usage amount. In daily operation and maintenance work of a data center, for example, in order to realize real-time monitoring and operation and maintenance of the capacities of a server disk, a CPU, a network and the like, relatively accurate prediction needs to be made on the capacities of the disk, the CPU, the network and the like so as to accurately react to capacity changes.
In the prior art, a capacity prediction method mainly uses static prediction as a main method, and mainly depends on a capacity value in a past period of time to calculate a mean value type of the capacity value in a period of time, so as to obtain a predicted value in the future. The prediction method excessively depends on the capacity value of a certain past time, and when the capacity of the server rapidly increases or decreases due to accidental situations at a certain moment, the capacity prediction value is larger or smaller at a certain moment, so that the accuracy is influenced.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
The invention aims to provide a capacity prediction method, a computer processor and terminal equipment, so as to solve the technical problem that the accuracy of a predicted value is not high due to accidental situations in the conventional capacity prediction.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a capacity prediction method, including the following steps:
s1, detecting whether the capacity is abnormally changed:
if yes, go to step S2;
if the detection result is no, executing step S4;
s2, judging the time range of the capacity abnormal change;
s3, smoothing the abnormal capacity in the time range;
and S4, capacity prediction is carried out according to the mean value method.
As a further technical solution, the step S1 includes:
s11, calculating the first order difference of the capacity at each sequence moment;
defining: { atIs the time series of volumes, { btIs the first order differential time sequence of the capacity, and t is atA time period of };
then, the first order difference of the capacity at each sequence instant satisfies the following relationship:
bi＝ai-ai-1
in the formula, aiIs { atValue at sequence instant i, biIs { btThe value at sequence instant i, i being the sequence instant in { t };
s12, calculation of btMean μ and standard deviation σ over a time period { t };
the calculation formula of the mean value μ is as follows:
Figure BDA0002855039690000021
where n is the length of the time period t, biIs { btThe value at sequence instant i;
the calculation formula of the standard deviation σ is as follows:
Figure BDA0002855039690000022
where n is the length of the time period t, biIs { btThe value at sequence instant i; μ is { b }tMean over a period of time { t };
s13, comparison bi(mu-f σ, mu + f σ) and (mu-f σ, mu + f σ) to determine whether or not the capacity has abnormally changed at the sequence time i, where f is preA defined safety factor;
if it is
Figure BDA0002855039690000031
Then determine { atWhen an abnormal change occurs, step S2 is executed;
if b isiE (μ -f σ, μ + f σ), then { a is determinedtNo abnormal change occurs, step S4 is executed.
As a further technical scheme, the value of the safety factor f is in a direct proportion relation with the confidence coefficient, and the safety factor f is less than or equal to 3.
As a further technical solution, the step S2 includes:
s21, according to the judgment result of the step S13, all b not in the section (mu-f sigma, mu + f sigma) is addediExtracting;
s22, according to the extracted biAnd determining a time region of the abnormal capacity change.
As a further technical solution, the step S3 includes:
s31, carrying out trend removing operation on the abnormal capacity part;
s32, filling the capacity missing part after the trend removing operation;
definition, { ktIs { a }tTime series of missing part volumes after detrending operations; { ytIs { a }tTime series of remaining fraction of capacity after detrending operation, { x }tIs { y }tTime period of { x } { ntThe length of the time period is m;
then, establish { ytAnd { x }tThe regression equation of (1):
yi＝a+bxi
in the formula, yiIs { ytValue at sequence instant i, xiIs { xtThe value at sequence time i, i being the sequence time;
the calculation formula of the constant term a and the slope term b in the regression equation is as follows:
Figure BDA0002855039690000032
Figure BDA0002855039690000033
Figure BDA0002855039690000041
Figure BDA0002855039690000042
in the formula, yiIs { ytValue at sequence instant i, xiIs { xtThe value at sequence instant i, i being the sequence instant, m being { x }tLength of time period of { t }, n is the length of time period of { t };
according to the calculated constant term a and the slope term b, the capacity deficiency value time sequence { k is processed according to the following formulatThe filling is carried out, and the filling is carried out,
y＝a+bKj
in the formula, j is an arbitrary integer from 1 to m-n, and y is a time-series value of the volume to be filled.
As a further technical solution, the step S4 includes:
s41, performing stationarity test on the time sequence of the capacity by adopting a unit root detection method;
if the time series of the capacity is the unstable series, executing step S42;
if the time series of the capacity check result is a stationary sequence, executing step S43;
s42, processing the unstable sequence by adopting a difference or logarithm method and obtaining a new capacity time sequence, returning to the step S41 to carry out stability test on the new capacity time sequence until the test result of the new capacity time sequence is a stable sequence;
s43, adopting a moving average method or an exponential decay average method to predict the stable sequence to obtain a time sequence of the capacity of the next sequence moment, and defining the stable sequence as { d }tD is the time sequence of the capacity of the next sequence timet+1；
S44, reducing d by adopting an anti-differential or anti-logarithmic methodt+1To obtain a time series of predicted capacities at+1。
In a second aspect, the present invention provides a computer processor comprising:
the capacity abnormity detection module is used for detecting whether the capacity is abnormally changed;
the capacity abnormal time judging module is used for judging the time range of the capacity abnormal change when the capacity abnormal detection module detects that the capacity is abnormally changed;
the capacity exception smoothing processing module is used for smoothing the exception capacity in the time range;
and the capacity prediction module is used for predicting the capacity according to the mean value method.
In a third aspect, the present invention provides a terminal device, comprising a memory, a processor and computer readable instructions stored in the memory and running on the processor, wherein the processor implements the steps of the capacity prediction method described above when executing the computer readable instructions.
By adopting the technical scheme, the invention has the following beneficial effects:
when the capacity is predicted, two prediction processes are provided according to whether the detected capacity is abnormally changed. When the detected capacity is not abnormally changed, capacity prediction is carried out according to a mean value method; when the abnormal change of the capacity is detected, the time range of the abnormal change of the capacity needs to be judged, the abnormal capacity in the time range is smoothed, and finally the capacity is predicted according to an average method. Therefore, the invention can accurately predict the capacity change and effectively control the operation and maintenance cost.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart illustrating a capacity prediction method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of the second embodiment of the present invention after the capacity is abnormally changed at a certain time;
FIG. 3 is a schematic diagram of a capacity anomaly part with peak value removed according to a second embodiment of the present invention;
FIG. 4 is a graph illustrating a linear regression of capacity versus de-peaking data as provided by example two of the present invention;
FIG. 5 is a schematic diagram of the filled volume after performing a stationarity check according to a second embodiment of the present invention;
fig. 6 is a block diagram of a computer processor according to a third embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
Example one
Referring to fig. 1, the present embodiment provides a capacity prediction method, including the following steps:
s1, detecting whether the capacity is abnormally changed:
if yes, go to step S2;
if the detection result is no, executing step S4;
s2, judging the time range of the capacity abnormal change;
s3, smoothing the abnormal capacity in the time range;
and S4, capacity prediction is carried out according to the mean value method.
It can be seen that, in the present embodiment, when capacity is predicted, two prediction processes are provided according to whether the detected capacity is abnormally changed. When the detected capacity is not abnormally changed, capacity prediction is carried out according to a mean value method; when the abnormal change of the capacity is detected, the time range of the abnormal change of the capacity needs to be judged, the abnormal capacity in the time range is smoothed, and finally the capacity is predicted according to an average method. Therefore, the invention can accurately predict the capacity change and effectively control the operation and maintenance cost.
In this embodiment, preferably, the step S1 of the capacity prediction method includes:
s11, calculating the first order difference of the capacity at each sequence moment;
defining: { atIs the time series of volumes, { btIs the first order differential time sequence of the capacity, and t is atA time period of };
then, the first order difference of the capacity at each sequence instant satisfies the following relationship:
bi＝ai-ai-1
in the formula, aiIs { atValue at sequence instant i, biIs { btThe value at sequence instant i, i being the sequence instant in { t };
s12, calculation of btMean μ and standard deviation σ over a time period { t };
the calculation formula of the mean value μ is as follows:
Figure BDA0002855039690000071
where n is the length of the time period t, biIs { btThe value at sequence instant i;
the calculation formula of the standard deviation σ is as follows:
Figure BDA0002855039690000072
where n is the length of the time period t, biIs { btThe value at sequence instant i; μ is { b }tMean over a period of time { t };
s13, comparison biJudging whether the capacity is abnormally changed at the sequence moment i or not according to the relation with (mu-f sigma, mu + f sigma), wherein f is a predefined safety coefficient;
if it is
Figure BDA0002855039690000073
Then determine { atWhen an abnormal change occurs, step S2 is executed;
if b isiE (μ -f σ, μ + f σ), then { a is determinedtNo abnormal change occurs, step S4 is executed.
Preferably, the value of the safety coefficient f is in a direct proportion relation with the confidence coefficient;
preferably, the safety factor f is less than or equal to 3.
Specifically, f is a variable, and the value can be changed with the required confidence. Suppose { btSatisfying a normal distribution, f can be taken to be 1.96 when the confidence is 95%, 2.58 when the confidence is 99%, and so on. As the confidence increases, the value of f also becomes larger.
Preferably, we do not take a very high confidence level here, let f be 3, i.e. if the deviation exceeds 3 standard deviations, it can be considered that the capacity has changed abnormally.
In this embodiment, preferably, the step S2 of the capacity prediction method includes:
s21, according to the judgment result of the step S13, all the sections (mu-f) not in the sectionB of σ, μ + f σ)iExtracting;
s22, according to the extracted biAnd determining a time region of the abnormal capacity change.
In this embodiment, preferably, the step S3 of the capacity prediction method includes:
s31, carrying out trend removing operation on the abnormal capacity part;
s32, filling the capacity missing part after the trend removing operation;
definition, { ktIs { a }tTime series of missing part volumes after detrending operations; { ytIs { a }tTime series of remaining fraction of capacity after detrending operation, { x }tIs { y }tTime period of { x } { ntThe length of the time period is m;
then, establish { ytAnd { x }tThe regression equation of (1):
yi＝a+bxi
in the formula, yiIs { ytValue at sequence instant i, xiIs { xtThe value at sequence time i, i being the sequence time;
the calculation formula of the constant term a and the slope term b in the regression equation is as follows:
Figure BDA0002855039690000081
Figure BDA0002855039690000082
Figure BDA0002855039690000083
Figure BDA0002855039690000084
in the formula, yiIs { ytValue at sequence instant i, xiIs { xtThe value at sequence instant i, i being the sequence instant, m being { x }tLength of time period of { t }, n is the length of time period of { t };
according to the calculated constant term a and the slope term b, the capacity deficiency value time sequence { k is processed according to the following formulatThe filling is carried out, and the filling is carried out,
y＝a+bKj
in the formula, j is an arbitrary integer from 1 to m-n, and y is a time-series value of the volume to be filled.
It can be seen that the effect of step S2 is to make the whole sequence smoother, so that the prediction will be more accurate without being affected by abnormal values.
In this embodiment, preferably, the step S4 of the capacity prediction method includes:
s41, performing stationarity test on the time sequence of the capacity by adopting a unit root detection method;
if the time series of the capacity is the unstable series, executing step S42;
if the time series of the capacity check result is a stationary sequence, executing step S43;
specifically, the time series { a ] is examined using ADF (enhanced Dixon Fuller's test) detectiontWhether there is a unit root.
If the time series { a }tIf the unit root exists in the range of the confidence interval, the checking result of the time sequence of the capacity is an unstable sequence, and then the step S42 is executed;
if the time series { a }tIf no unit root exists in the confidence interval range, the result of the time sequence of the capacity is a stable sequence, and then the step S43 is executed;
s42, processing the unstable sequence by adopting a difference or logarithm method and obtaining a new capacity time sequence, returning to the step S41 to carry out stability test on the new capacity time sequence until the test result of the new capacity time sequence is a stable sequence;
for example: the unstable sequence is processed by adopting a difference method, and the following formula is mainly adopted:
bi＝ai-ai-1wherein, i is 1,2,3, …, n
For example: the unstable sequence is processed by adopting a difference method, and the following formula is mainly adopted:
ci＝log(ai) Wherein, i is 1,2,3, …, n
Wherein, if the sequence grows linearly, a difference method can be adopted, and if the sequence grows exponentially, a logarithm method can be adopted.
This process is repeated, without stopping the test of step 1 until the sequence is stationary, and the next step is followed, at which time the stationary sequence { d } is obtainedt}。
S43, adopting a moving average method or an exponential decay average method to predict the stable sequence to obtain a time sequence of the capacity of the next sequence moment, and defining the stable sequence as { d }tD is the time sequence of the capacity of the next sequence timet+1；
For stationary sequences { dtD predictiont+1The moving average method and the exponential decay average method are mainly adopted.
For example: p-order moving average method: dt+1＝(dt+dt-1+…+dt-p+1)/p；
Wherein the value of p depends on dtThe length of time.
For example: exponential decay averaging method: introduction of auxiliary sequences vtMake a calculation, assume { d }tThe length of the said is n, then there is
v1＝0
vt+1＝βvt+(1-β)dtWherein t is 1,2,3, … n
dt+1＝vt+1
t＝n+1
Wherein the value of beta can be changed, the larger the value is, the faster the sequence is attenuated, and the value is not 0.9.
S44, reducing d by adopting an anti-differential or anti-logarithmic methodt+1To obtain a time series of predicted capacities at+1。
After the prediction is completed, the pair d is neededt+1Is reduced to obtain a reduced alphat+1In agreement with the two methods of sequence smoothing, the reduction is also divided into two methods, anti-differential and anti-log.
For example: the contrast division method comprises the following steps:
Figure BDA0002855039690000101
for example: an inverse logarithmic method:
Figure BDA0002855039690000102
in conclusion, when the method is used for predicting the capacity, two prediction processes are provided according to whether the detected capacity is abnormally changed. When the detected capacity is not abnormally changed, capacity prediction is carried out according to a mean value method; when the abnormal change of the capacity is detected, the time range of the abnormal change of the capacity needs to be judged, the abnormal capacity in the time range is smoothed, and finally the capacity is predicted according to an average method. Therefore, the method can accurately predict the capacity change and effectively control the operation and maintenance cost.
Example two
With reference to fig. 2 to fig. 5, a specific prediction method provided in this embodiment two on the basis of the above embodiment one takes an instantaneous load increase as an example, and normally, the usage rate of the server disk is stabilized at about 10%, but the load suddenly increases, which causes a peak.
As shown in fig. 2, the capacity anomaly detection module starts to work, accurately identifies the time zone in which the anomaly change occurs, and successfully removes the corresponding peak value.
As shown in fig. 3, a period of time during which an abnormal change in capacity occurs is identified, and a decresting operation is performed during the period of time.
As shown in fig. 4 and 5, linear regression was performed on the de-peaked data to determine the filling value of the missing portion, and filling was successful. And then, performing stability test on the filled data sequence, and finding that the sequence passes the stability test. Finally, a prediction module is introduced for prediction, and the prediction result is 9.95%; if the abnormal detection module is not introduced to directly carry out prediction, the obtained prediction result is 10.50%. Therefore, the result of introducing the capacity abnormity detection module is accurate.
EXAMPLE III
With reference to fig. 6, a third embodiment provides a computer processor based on the first embodiment, which includes:
a capacity anomaly detection module 1, which is used for detecting whether the capacity is abnormally changed;
a capacity abnormal time judgment module 2, configured to judge a time range of occurrence of a capacity abnormal change when the capacity abnormal detection module 1 detects that the capacity abnormal change occurs;
a capacity exception smoothing module 3, configured to smooth the exception capacity in the time range;
and the capacity prediction module 4 is used for carrying out capacity prediction according to a mean value method.
When the computer processor of the embodiment predicts the capacity, two prediction processes are provided according to whether the detected capacity is abnormally changed. When the detected capacity is not abnormally changed, capacity prediction is carried out according to a mean value method; when the abnormal change of the capacity is detected, the time range of the abnormal change of the capacity needs to be judged, the abnormal capacity in the time range is smoothed, and finally the capacity is predicted according to an average method. Therefore, the computer processor can accurately predict the capacity change and effectively control the operation and maintenance cost.
Example four
Fourth embodiment provides a terminal device based on the first embodiment or the third embodiment, where the terminal device includes a memory, a processor, and computer readable instructions stored in the memory and executed on the processor, and the processor implements the steps of the capacity prediction method according to the first embodiment when executing the computer readable instructions. The capacity prediction method is described in detail in the first embodiment, and is not described herein again.
When the terminal device of the embodiment predicts the capacity, two prediction processes are provided according to whether the detected capacity is abnormally changed. When the detected capacity is not abnormally changed, capacity prediction is carried out according to a mean value method; when the abnormal change of the capacity is detected, the time range of the abnormal change of the capacity needs to be judged, the abnormal capacity in the time range is smoothed, and finally the capacity is predicted according to an average method. Therefore, the terminal equipment can accurately predict the capacity change and effectively control the operation and maintenance cost.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (8)

1. A capacity prediction method, comprising the steps of:
s1, detecting whether the capacity is abnormally changed:
if yes, go to step S2;
if the detection result is no, executing step S4;
s2, judging the time range of the capacity abnormal change;
s3, smoothing the abnormal capacity in the time range;
and S4, capacity prediction is carried out according to the mean value method.
2. The capacity prediction method of claim 1, wherein step S1 comprises:
s11, calculating the first order difference of the capacity at each sequence moment;
defining: { atIs the time series of volumes, { btIs the first order differential time sequence of the capacity, and t is atA time period of };
then, the first order difference of the capacity at each sequence instant satisfies the following relationship:
bi＝ai-ai-1
in the formula, aiIs { atValue at sequence instant i, biIs { btThe value at sequence instant i, i being the sequence instant in { t };
s12, calculation of btMean μ and standard deviation σ over a time period { t };
the calculation formula of the mean value μ is as follows:
Figure FDA0002855039680000011
where n is the length of the time period t, biIs { btThe value at sequence instant i;
the calculation formula of the standard deviation σ is as follows:
Figure FDA0002855039680000012
where n is the length of the time period t, biIs { btThe value at sequence instant i; μ is { b }tMean over a period of time { t };
s13, comparison biJudging whether the capacity is abnormally changed at the sequence moment i or not according to the relation with (mu-f sigma, mu + f sigma), wherein f is a predefined safety coefficient;
if it is
Figure FDA0002855039680000021
Then determine { atWhen an abnormal change occurs, step S2 is executed;
if b isi∈(μ-fσ，μ+fσ), then { a) is determinedtNo abnormal change occurs, step S4 is executed.
3. The capacity prediction method of claim 2,
the value of the safety factor f is in a direct proportion relation with the confidence coefficient, and the safety factor f is less than or equal to 3.
4. The capacity prediction method of claim 2, wherein step S2 comprises:
s21, according to the judgment result of the step S13, all b not in the section (mu-f sigma, mu + f sigma) is addediExtracting;
s22, according to the extracted biAnd determining a time region of the abnormal capacity change.
5. The capacity prediction method of claim 4, wherein step S3 comprises:
s31, carrying out trend removing operation on the abnormal capacity part;
s32, filling the capacity missing part after the trend removing operation;
definition, { ktIs { a }tTime series of missing part volumes after detrending operations; { ytIs { a }tTime series of remaining fraction of capacity after detrending operation, { x }tIs { y }tTime period of { x } { ntThe length of the time period is m;
then, establish { ytAnd { x }tThe regression equation of (1):
yi＝a+bxi
in the formula, yiIs { ytValue at sequence instant i, xiIs { xtThe value at sequence time i, i being the sequence time;
the calculation formula of the constant term a and the slope term b in the regression equation is as follows:
Figure FDA0002855039680000022
Figure FDA0002855039680000023
Figure FDA0002855039680000024
Figure FDA0002855039680000031
in the formula, yiIs { ytValue at sequence instant i, xiIs { xtThe value at sequence instant i, i being the sequence instant, m being { x }tLength of time period of { t }, n is the length of time period of { t };
according to the calculated constant term a and the slope term b, the capacity deficiency value time sequence { k is processed according to the following formulatThe filling is carried out, and the filling is carried out,
y＝a+bKj
in the formula, j is an arbitrary integer from 1 to m-n, and y is a time-series value of the volume to be filled.
6. The capacity prediction method of claim 5, wherein step S4 comprises:
s41, performing stationarity test on the time sequence of the capacity by adopting a unit root detection method;
if the time series of the capacity is the unstable series, executing step S42;
if the time series of the capacity check result is a stationary sequence, executing step S43;
s42, processing the unstable sequence by adopting a difference or logarithm method and obtaining a new capacity time sequence, returning to the step S41 to carry out stability test on the new capacity time sequence until the test result of the new capacity time sequence is a stable sequence;
s43, adopting a moving average method or an exponential decay average method to predict the stable sequence to obtain a time sequence of the capacity of the next sequence moment, and defining the stable sequence as { d }tD is the time sequence of the capacity of the next sequence timet+1；
S44, reducing d by adopting an anti-differential or anti-logarithmic methodt+1To obtain a time series of predicted capacities at+1。
7. A computer processor, comprising:
the capacity abnormity detection module is used for detecting whether the capacity is abnormally changed;
the capacity abnormal time judging module is used for judging the time range of the capacity abnormal change when the capacity abnormal detection module detects that the capacity is abnormally changed;
the capacity exception smoothing processing module is used for smoothing the exception capacity in the time range;
and the capacity prediction module is used for predicting the capacity according to the mean value method.
8. A terminal device comprising a memory, a processor and computer readable instructions stored in the memory and run on the processor, characterized in that the processor, when executing the computer readable instructions, implements the steps of the capacity prediction method according to any one of claims 1 to 6.
CN202011542335.8A 2020-12-23 2020-12-23 Capacity prediction method, computer processor and terminal equipment Active CN112580880B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011542335.8A CN112580880B (en) 2020-12-23 2020-12-23 Capacity prediction method, computer processor and terminal equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011542335.8A CN112580880B (en) 2020-12-23 2020-12-23 Capacity prediction method, computer processor and terminal equipment

Publications (2)

Publication Number Publication Date
CN112580880A true CN112580880A (en) 2021-03-30
CN112580880B CN112580880B (en) 2023-12-19

Family

ID=75139186

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011542335.8A Active CN112580880B (en) 2020-12-23 2020-12-23 Capacity prediction method, computer processor and terminal equipment

Country Status (1)

Country Link
CN (1) CN112580880B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113157204A (en) * 2021-01-29 2021-07-23 杭州优云软件有限公司 Disk capacity prediction method for identifying manual cleaning behavior based on second-order difference method

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070055477A1 (en) * 2005-09-02 2007-03-08 Microsoft Corporation Web data outlier detection and mitigation
CN103984938A (en) * 2014-05-30 2014-08-13 中国科学院遥感与数字地球研究所 Remote sensing time series abnormity detection method
CN104181883A (en) * 2014-08-08 2014-12-03 青岛高校信息产业有限公司 Method for processing abnormal data of real-time data acquisition system in real time
KR20160026492A (en) * 2014-09-01 2016-03-09 목포대학교산학협력단 Anomaly detection method using confidence interval estimation based on time series analysis
US20170018033A1 (en) * 2015-07-15 2017-01-19 Foundation Of Soongsil University Industry Cooperation Stock fluctuatiion prediction method and server
CN108173686A (en) * 2017-12-26 2018-06-15 北京工业大学 It is a kind of that stream Forecasting Methodology is asked based on the cloud data center of ARIMA and wavelet transformation
CN108563739A (en) * 2018-04-11 2018-09-21 平安科技（深圳）有限公司 Weather data acquisition methods and device, computer installation and readable storage medium storing program for executing
CN109993370A (en) * 2019-04-10 2019-07-09 国网浙江省电力有限公司 A kind of electric power sale day cash flow projections method based on nonstationary time series

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070055477A1 (en) * 2005-09-02 2007-03-08 Microsoft Corporation Web data outlier detection and mitigation
CN103984938A (en) * 2014-05-30 2014-08-13 中国科学院遥感与数字地球研究所 Remote sensing time series abnormity detection method
CN104181883A (en) * 2014-08-08 2014-12-03 青岛高校信息产业有限公司 Method for processing abnormal data of real-time data acquisition system in real time
KR20160026492A (en) * 2014-09-01 2016-03-09 목포대학교산학협력단 Anomaly detection method using confidence interval estimation based on time series analysis
US20170018033A1 (en) * 2015-07-15 2017-01-19 Foundation Of Soongsil University Industry Cooperation Stock fluctuatiion prediction method and server
CN108173686A (en) * 2017-12-26 2018-06-15 北京工业大学 It is a kind of that stream Forecasting Methodology is asked based on the cloud data center of ARIMA and wavelet transformation
CN108563739A (en) * 2018-04-11 2018-09-21 平安科技（深圳）有限公司 Weather data acquisition methods and device, computer installation and readable storage medium storing program for executing
CN109993370A (en) * 2019-04-10 2019-07-09 国网浙江省电力有限公司 A kind of electric power sale day cash flow projections method based on nonstationary time series

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113157204A (en) * 2021-01-29 2021-07-23 杭州优云软件有限公司 Disk capacity prediction method for identifying manual cleaning behavior based on second-order difference method

Also Published As

Publication number Publication date
CN112580880B (en) 2023-12-19

Similar Documents

Publication Publication Date Title
CN113407371B (en) Data anomaly monitoring method, device, computer equipment and storage medium
CN112685273A (en) Anomaly detection method and device, computer equipment and storage medium
CN112257755A (en) Method and device for analyzing operating state of spacecraft
US20040172579A1 (en) System and method for memory leak detection
US20210048811A1 (en) Model generation device for life prediction, model generation method for life prediction, and recording medium storing model generation program for life prediction
CN113127305A (en) Abnormality detection method and apparatus
CN114978956B (en) Method and device for detecting abnormal mutation points of performance of intelligent city network equipment
US12118396B2 (en) Computing resource autoscaling based on predicted metric behavior
CN112580880A (en) Capacity prediction method, computer processor and terminal equipment
CN111858031B (en) Cluster distributed resource scheduling method, device, equipment and storage medium
CN111797889A (en) Single variable alarm system performance evaluation method and system based on piecewise linear representation
CN114491383A (en) Abnormal data processing method and system for bridge monitoring
CN112506752A (en) Operation and maintenance method, device and equipment based on time series data trend prediction
US8904338B2 (en) Predicting performance of a software project
CN111400141A (en) Abnormity detection method and device
Haq et al. New weighted adaptive CUSUM dispersion charts
CN118152124A (en) Data processing method and system based on cloud computing
CN110298767B (en) Thermal power plant time sequence variable abnormity monitoring method and system
US6671658B2 (en) Method for service level estimation in an operating computer system
CN113434823B (en) Data acquisition task abnormity early warning method and device, computer equipment and medium
CN112084648B (en) Method and device for predicting residual service life of equipment and electronic equipment
CN113553545B (en) Event detection method and system for small-current electrical appliance, equipment and storage medium
CN110795839A (en) Method for improving chemical big data modeling speed by utilizing grid mutual information to rapidly calculate
CN113901612A (en) Structural member degradation modeling and reliability pre-estimating method and system
CN114178326B (en) Control method and device of detection equipment and computer equipment

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
GR01 Patent grant
GR01 Patent grant