CN110245054A - Computer resource usage amount trend prediction analysis system and method - Google Patents
Computer resource usage amount trend prediction analysis system and method Download PDFInfo
- Publication number
- CN110245054A CN110245054A CN201810183873.9A CN201810183873A CN110245054A CN 110245054 A CN110245054 A CN 110245054A CN 201810183873 A CN201810183873 A CN 201810183873A CN 110245054 A CN110245054 A CN 110245054A
- Authority
- CN
- China
- Prior art keywords
- trend prediction
- usage amount
- prediction
- data
- trend
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/323—Visualisation of programs or trace data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3466—Performance evaluation by tracing or monitoring
- G06F11/3476—Data logging
Abstract
A kind of computer resource usage amount trend prediction analysis system a, comprising: data capture device captures an at least key index value for at least usage amount of a resource in an at least computer installation；One data analysis set-up is connected to data capture device, and receives, analyzes an at least key index value；One data exhibiting device, is connected to data analysis set-up, and the crucial pointer value of at least one after data analysis set-up is analyzed is shown with an image；And a trend prediction device, at least one crucial pointer value that analysis is shown with image, to generate a trend prediction figure；Wherein, trend prediction device is connected to data exhibiting device, and data exhibiting device shows trend prediction figure.Furthermore the present invention also provides a kind of computer resource usage amount trend prediction analysis method.
Description
Technical field
For the present invention about a kind of Computerized analysis system and its method, referring in particular to one kind can each resource in analytical calculation machine
Usage amount, and the usage amount of each resource is done into trend prediction analysis by the usage amount image conversion of each resource, and further
Computer resource usage amount trend prediction analysis system and method.
Background technique
Due to the progress of science and technology, scope applied by information engineering is also increasingly wider, and with the increasing of information engineering scale
Add, used in various science technology systems to software also become increasingly complex, in order to maintain the operation of system, more complicated software and
Engineering-environment more needs to use multiple stage computers to carry out operation.In this way, the central processing unit in multiple stage computers
The monitoring operation of the usage amount of multiple resources such as (Central Processing Unit, CPU), memory, disk becomes information
Very important thing in maintenance and operation engineering.Furthermore if can be predicted in the monitoring operation of multiple resources of multiple stage computers
When situations such as load surcharge or disk size are lower than safe range can occur for multiple resources, and multiple stage computers will be allowed to run
It is more smooth.
On the other hand, in various display subtypes, K line chart is a kind of very intuitive and can allow the open-and-shut figure of people
Table display mode.The producing method of K line chart is according to this four value institutes of share price " opening price, closing price, highest price, lowest price "
The figure drawn can observe to thorough the real variation in market in K line chart, both (or big it can be seen that share price
City) trend, while can also understand that the fluctuation situation of daily stock market's situation.
For these reasons, in the monitoring operation of the usage amount of multiple resources of multiple stage computers, if K line can be utilized
Figure shows the usage amount of each resource, and monitoring side can be allowed to observe that each resource exists in a manner of more intuitive and is open-and-shut
Prolonged use amount situation, and big data trend prediction analysis is done, to find whether each resource has hair in use ahead of time
It is raw abnormal.
Summary of the invention
To achieve the aforementioned purpose, the present invention provides a kind of computer resource usage amount trend prediction analysis system, comprising: one
Data capture device captures an at least key index value for at least usage amount of a resource in an at least computer installation；One
Data analysis set-up is connected to data capture device, and receives, analyzes an at least key index value；One data exhibiting device, even
It is connected to data analysis set-up, and at least key index value after data analysis set-up is analyzed is shown with an image；
And a trend prediction device, at least key index value shown with image is analyzed, to generate a trend prediction figure；Its
In, trend prediction device is connected to data exhibiting device, and data exhibiting device shows trend prediction figure.
Preferably, an at least key index value includes that the daily of an at least resource begins to use numerical quantity, every end of day to make
Numerical quantity is used using numerical quantity and daily minimum with numerical quantity, daily maximum.
Preferably, trend prediction device is analyzed by linear regression mode, to generate trend prediction figure.
Preferably, an at least key index value is an at least KPI value, image is K line chart.
Preferably, the usage amount of an at least resource includes at least utilization rate of a CPU, the utilization rate of an at least memory, extremely
The capacity of a few disk.
Furthermore the present invention also provides a kind of computer resource usage amount trend prediction analysis method, comprising the following steps: by
An at least key index value for at least usage amount of a resource in an at least computer installation is captured by a data capture device；
It is received by a data analysis set-up and analyzes an at least key index value；By a data exhibiting device by data analysis set-up
An at least key index value after analysis is shown with an image；And by a trend prediction device analysis with image into
An at least key index value for row display, and generate a trend prediction figure；Wherein, data exhibiting device shows trend prediction figure.
Preferably, in at least key index value shown by trend prediction device analysis with image and generating
In the step of gesture prognostic chart, trend prediction device further generates a prediction threshold values, when at least one prediction in trend prediction figure
When numerical value reaches prediction threshold values, at least one prediction numerical value for reaching prediction threshold values can be shown in trend prediction figure in the form of warning
On.
Preferably, trend prediction device analyzes at least key index value in image by machine learning mode, to produce
Raw prediction threshold values.
Preferably, an at least key index value includes that the daily of an at least resource begins to use numerical quantity, every end of day to make
Numerical quantity is used using numerical quantity and daily minimum with numerical quantity, daily maximum.
Preferably, trend prediction device is analyzed by linear regression mode, to generate trend prediction figure.
Detailed description of the invention
The architecture diagram of Fig. 1 computer resource usage amount trend prediction analysis system of an embodiment to illustrate the invention；
The trend schematic diagram of Fig. 2 usage amount of the disk size of an embodiment to illustrate the invention；
The trend schematic diagram of Fig. 3 usage amount of the disk size of another embodiment to illustrate the invention；
The trend schematic diagram of Fig. 4 usage amount of the disk size of another embodiment to illustrate the invention；
The trend schematic diagram of Fig. 5 usage amount of the disk size of another embodiment to illustrate the invention；
The trend schematic diagram of Fig. 6 usage amount of the disk size of another embodiment to illustrate the invention；
The trend schematic diagram of Fig. 7 usage amount of the disk size of another embodiment to illustrate the invention；
The average daily line trend schematic diagram of Fig. 8 usage amount of the disk size of an embodiment to illustrate the invention；And
The flow chart of Fig. 9 computer resource usage amount trend prediction analysis method of an embodiment to illustrate the invention.
Wherein, the reference numerals are as follows:
1 computer resource usage amount trend prediction analysis system
10 data capture devices
12 data analysis set-ups
14 data exhibiting devices
16 trend prediction devices
2 computer installations
20 CPU
22 memories
24 disks
S10-S16 step
Specific embodiment
Cooperate schema and appended drawing reference to do more detailed description to embodiments of the present invention below, makes to be familiar with this field
Technical staff can implement accordingly after studying this specification carefully.
Fig. 1 is an architecture diagram, to illustrate the computer resource usage amount trend prediction analysis system of one embodiment of the invention
System.Fig. 1 is please referred to, in an embodiment of the present invention, computer resource usage amount trend prediction analysis system 1 includes that a data are caught
Obtain equipment 10, a data analysis set-up 12, a data exhibiting device 14 and a trend prediction device 16.Data capture device 10
Capture an at least key index value for at least usage amount of a resource in an at least computer installation 2, wherein at least one money
Source is, for example, other computer hardwares such as CPU 20, memory 22, disk 24 in computer installation 2, and the usage amount of resource is for example
For the utilization rate of CPU 20, the utilization rate of memory 22, disk 24 capacity.Data analysis set-up 12 is connected to data capture device
10, and receive, analyze an at least key index value.Data exhibiting device 14 is connected to data analysis set-up 12, and data are divided
An at least key index value after analysis apparatus 12 is analyzed is shown with an image, wherein key index value is KPI value (Key
Performance Indicator, KPI), and the image is K line chart.Trend prediction device 16 can be analyzed to be shown with the image
An at least key index value, to generate a trend prediction figure.Wherein, trend prediction device 16 is connected to data exhibiting device
14, and data exhibiting device 14 can also show trend prediction figure caused by trend prediction device 16.
It should be noted that in an embodiment of the present invention, the CPU in 10 fechtable computer installation 2 of data capture device
20, memory 22 or disk 24 are in the key index value of four different periods.For example, 10 fechtable of data capture device is for example
Each resources such as CPU 20, memory 22 or disk 24 begin to use numerical quantity (open), every end of day usage amount numerical value daily
(close), daily maximum uses numerical quantity (low) using numerical quantity (high) and daily minimum.The daily amount of beginning to use number
First index value of the daily 00 point of generation in 00 minute of value, that is, each resource；Every end of day usage amount numerical value, that is, each resource is daily
The last one index value of 23 points of generations in 59 minutes；It is daily maximum using produced by each resource in numerical quantity i.e. one day 24 hours
Maximum Index numerical value；Daily minimum uses minimum index value caused by each resource in numerical quantity i.e. one day 24 hours.
The present invention can pass through each resource key index value caused by four periods, further by data analysis set-up 12
It receives, analyze the key index value that above-mentioned data capture device 10 is captured, and show by data exhibiting device 14 through number
The K line chart of the usage amount of each resource after being analyzed according to analytical equipment 12.In addition, shown by data exhibiting device 14
In K line chart, a day K line chart can be shown as unit of day, shown all K line charts as unit of week or shown as unit of the moon
Show a moon K line chart, each resource is monitored in a manner of more intuitive in the usage amount of specific time period.
Now by taking disk size as an example, to illustrate K line chart shown by data exhibiting device 14 of the invention.Fig. 2 is one
Schematic diagram, the trend of the usage amount of 24 capacity of disk to illustrate one embodiment of the invention.Fig. 1 and Fig. 2 is please referred to, data are worked as
It, can be by data exhibiting device after the residual capacity of the daily disk 24 of August to October is taken root (Root) by analytical equipment 12
14 show the August of such as Fig. 2 to the disk 24 between October residual capacity trend picture, wherein the remaining of disk 24 is held
The unit of amount is Gigabytes, GB.As seen from Figure 2, the residual capacity of disk 24 in 3 months time not too substantially
The increase and decrease situation of degree only has between August 20 days to August 27th and releases some capacity, but rear residual capacity also become stable,
Indicate the reduction of 24 capacity of stability contorting disk.It is to be understood that in the present invention, a user can be by click data exhibition
The K line chart numerical value of shown specific time period in existing device 14, to further appreciate that the usage amount situation of disk 24 in the period.
Fig. 3 is a schematic diagram, the trend of the usage amount of the disk size to illustrate another embodiment of the present invention.It please refers to
Fig. 1 and Fig. 3, in an alternative embodiment of the invention, when data analysis set-up 12 holds the residue of the daily disk 24 of August to October
After measuring log, the residual capacity of the August of such as Fig. 3 to the disk 24 between October can be shown by data exhibiting device 14
Trend picture, wherein the unit of the residual capacity of disk 24 is Gigabytes, GB.As seen from Figure 3, the remaining of disk 24 is held
Amount about reduces 40GB in 3 months, and is persistently to reduce in a stable manner, and representing disk 24 is to be in normal operating condition,
And the capacity about residue 100GB of current disk 24.It is to be understood that in the present invention, a user can be by click data exhibition
The K line chart numerical value of shown specific time period in existing device 14, to further appreciate that the usage amount situation of disk 24 in the period.
Fig. 4 is a schematic diagram, the trend of the usage amount of the disk size to illustrate yet another embodiment of the invention.It please refers to
Fig. 1 and Fig. 4, in yet another embodiment of the invention, when data analysis set-up 12 holds the residue of the daily disk 24 in May to October
After measuring log, the residual capacity in May of such as Fig. 4 to the disk 24 between October can be shown by data exhibiting device 14
Trend picture, wherein the unit of the residual capacity of disk 24 is Gigabytes, GB.As seen from Figure 4, the remaining of disk 24 is held
Measure May to there is the capacity for releasing about 50GB between June, represent May to disk 24 between June may carry out maintenance and will be unnecessary
Data delete.30GB is about reduced from June to every month between October later, and is persistently to reduce in a stable manner, represents magnetic
Disk 24 is in normal operating condition.It is to be understood that in the present invention, a user can be by click data display device 14
In shown specific time period K line chart numerical value, to further appreciate that the usage amount situation of disk 24 in the period.
Fig. 5 is a schematic diagram, the trend of the usage amount of the disk size to illustrate further embodiment of this invention.It please refers to
Fig. 1 and Fig. 5, in yet another embodiment of the invention, when data analysis set-up 12 holds the residue of the daily disk 24 in May to October
After amount is analyzed with variable (var) mode, May of such as Fig. 5 can be shown to the magnetic between October by data exhibiting device 14
Disk 24 with variable format come the trend picture of the residual capacity shown.As seen from Figure 5, the residual capacity May of disk 24 is to 8
The middle of the month is to continue to reduce, and representing disk 24 is in normal operating condition.Disk 24 is then to be tieed up in August later
Shield, and be then to be in stable state to disk in October 24 from August.It is to be understood that in the present invention, a user can be by
The K line chart numerical value of shown specific time period in click data display device 14, to further appreciate that disk 24 in the period
Usage amount situation.
Fig. 6 is a schematic diagram, the trend of the usage amount of the disk size to illustrate further embodiment of this invention.It please refers to
Fig. 1 and Fig. 6, in yet another embodiment of the invention, data analysis set-up 12 carries out the residual capacity of the disk 24 in May to October
Analysis, and drawn by the trend of residual capacity that data exhibiting device 14 shows May of such as Fig. 5 to the disk 24 between October
Face, wherein the unit of the residual capacity of disk 24 is Gigabytes, GB.As seen from Figure 5, the residual capacity of disk 24 is from 5
The moon about reduces 100GB to every month between October, and is persistently to reduce in a stable manner, and representing disk 24 is in normal use
State.It is to be understood that in the present invention, a user can be by specific time period shown in click data display device 14
K line chart numerical value, to further appreciate that the usage amount situation of disk 24 in the period.
Fig. 7 is a schematic diagram, the trend of the usage amount of the disk size to illustrate further embodiment of this invention.It please refers to
Fig. 1 and Fig. 7, in yet another embodiment of the invention, when data analysis set-up 12 holds the residue of the daily disk 24 in May to October
After amount is analyzed with variable (var) mode, May of such as Fig. 7 can be shown to the magnetic between October by data exhibiting device 14
Disk 24 with variable format come the trend picture of the residual capacity shown.As seen from Figure 7, the residual capacity May of disk 24 is to 7
The moon is to continue to reduce, and representing disk 24 is in normal operating condition.At July, disk 24 is then to be safeguarded later,
It and is then in stable state from disk in July to October 24.It is to be understood that in the present invention, a user can be by click
The K line chart numerical value of shown specific time period in data exhibiting device 14, to further appreciate that the use of disk 24 in the period
Amount situation.
It is to be understood that Fig. 2 has multiple advantages into Fig. 7 in such a way that K line chart is shown, and Fig. 2 to Fig. 7 is shown
Time section can adjust according to actual demand, such as using day, week, the moon as chronomere.For example, from the same day/when week/
The maximum amplitude of vibration amount of of that month K line chart, it will be appreciated that the stability and smoothness of analyzed resource；From same day/as week/this month K
Maximum reduction amount/maximum incrementss of line chart, then it will be seen that the maximum endurance of analyzed resource.
Further, when data analysis set-up 12 analyzes the residual capacity of disk 24 and shows by data exhibiting device 14
Out after the K line tendency chart of such as Fig. 2 to Fig. 7, trend prediction device 16 can thousands of/tens of thousands of a keys of the analysis chart 2 into Fig. 7 refer to
Scale value, to generate a trend prediction figure (not shown).Specifically, trend prediction device 16 can be automatically by thousands of/tens of thousands of
Key index value carries out big data analysis, such as selects each in thousands of/tens of thousands of a key index values median, and utilize
Linear regression (Linear regression) analysis mode finds out rule in thousands of/tens of thousands of a data points, and further by
Data exhibiting device 14 is to show a trend prediction figure, and the trend prediction figure can also be shown in the form of K line chart.So
One, the present invention can predict increase and decrease situation of the residual capacity of disk 24 in future by trend prediction device 16, with
Prevent the investigation of secret worry in advance.It is to be understood that in an embodiment of the present invention, trend prediction device 16 predicts 24 future of disk
Residual capacity trend, and in other embodiments of the present invention, CPU20 can be predicted in following use in trend prediction device 16
Rate, memory 22 the related resources such as following utilization rate behaviour in service.
Furthermore in an embodiment of the present invention, trend prediction device 16 can set a prediction threshold values, when trend prediction device
When prediction key index value in the 16 trend prediction figures shown by data exhibiting device 14 reaches the prediction threshold values, this becomes
The prediction key index value that the prediction threshold values is reached in gesture prognostic chart can be warned using different colors, with into one
Step reminds user, usage amount future of each resource in monitoring when, such as any day/any week/which can reach prediction the moon
Threshold values, and be ready ahead of time.
It is noted that in other embodiments of the present invention, trend prediction device 16 can have machine learning
The abilities such as (machine learning) and artificial intelligence, and the number greatly such as elastic search that arranges in pairs or groups, Hadoop, spark
According to analysis tool, in the accumulation by historical data, by a large amount of data (Volume), polynary data type data
(Variety) it does simultaneously and effectively shows (Velocity).A large amount of data are for example are as follows: the hundreds of thousands generated daily is to millions of
Pen data；Polynary data type data is for example are as follows: cpu load rate, memory usage amount, disk size, network flow etc.
Pointer；Show for example in real time are as follows: provide in real time, day line, contour, moon line etc. it is different show mode.For example, trend is pre-
Surveying device 16 can be by thousands of/tens of thousands of a key index values of the machine learning mode analysis chart 2 into Fig. 7, to generate the prediction
Threshold values, and the prediction threshold values can be dynamically adjusted according further to latest data.
Fig. 8 is a schematic diagram, the average daily line trend of the usage amount of the disk size to illustrate one embodiment of the invention.Please
Referring to Fig. 8, in an embodiment of the present invention, data analysis set-up 12 can show that at least one is average by data exhibiting device 14
Line.For example, data analysis set-up 12 using the key index value of the centre of a time section as standard value, with into one
Step shows a per day line by data exhibiting device 14, such as the key index value of every seven days centres is put down as trend
Mean value can show naturally all (nature week) average lines, if by every five days centres by data exhibiting device 14
Key index value as trend average value, then can be shown by data exhibiting device 14 work week (working week)
Average line.20 average daily lines, 30 average daily lines, 40 average daily lines and 60 average daily lines are shown in Fig. 8, so user can be allowed more intuitive
The how per day usage amount of ground understanding disk 24.
On the other hand, another advantage of computer resource usage amount trend prediction analysis system of the invention can be simultaneously to more
Each resource of platform computer installation carries out trend prediction analysis.For example, every computer installation has 1-N disk,
By taking 100 computer installations as an example, if every computer installation has 3-10 disk, 300-1000 disk, this hair are just had
Bright computer resource usage amount trend prediction analysis system can be made for each disk such as Fig. 2-disk shown in Fig. 7
Residual capacity tendency chart, in this way, user can by viewing Fig. 2-disk shown in Fig. 7 residual capacity tendency chart,
To understand the behaviour in service of each disk rapidly, and solve the problems, such as to encounter in real time.Furthermore example is saved as within if, every meter
Calculation machine device has 1 group of memory, by taking 100-1000 platform computer installation as an example, just has 100-1000 group memory and needs to manage,
If especially computer installation further includes virtual memory, the present invention also can be managed uniformly for virtual memory simultaneously, and be shown
Such as Fig. 2-tendency chart shown in Fig. 7 out to understand the behaviour in service of every group of memory rapidly, and solves the problems, such as to encounter in real time.
Fig. 9 is a flow chart, to illustrate the computer resource usage amount trend prediction analysis method of an embodiment.It please join
According to Fig. 9, computer resource usage amount trend prediction analysis method of the invention includes step S10-S16.Step S10 are as follows: by
One data capture device captures an at least key index value for at least usage amount of a resource in an at least computer installation；Step
Rapid S12 are as follows: received by a data analysis set-up and analyze an at least key index value；Step S14 are as follows: by a data exhibition
Existing device shows at least key index value after data analysis set-up analysis with an image；And step
S16 are as follows: by at least key index value that a trend prediction device analysis is shown with the image, and generate a trend
Prognostic chart.
Wherein, which can show the trend prediction figure；An at least key index value include this at least one
Resource begins to use numerical quantity, every end of day usage amount numerical value, daily maximum to make using numerical quantity and daily minimum daily
Use numerical quantity；The trend prediction device is analyzed by linear regression mode, to generate the trend prediction figure.
In addition, in at least key index value shown by the trend prediction device analysis with the image and producing
In the step S16 of the raw trend prediction figure, which further generates a prediction threshold values, when in the trend prediction figure
At least one prediction numerical value when reaching the prediction threshold values, at least one prediction numerical value for reaching the prediction threshold values can be in the form of warning
It is shown on the trend prediction figure.Furthermore in other embodiments of the present invention, which can be by machine learning side
Formula analyzes at least key index value in the image, to generate the prediction threshold values.
In conclusion the present invention successfully provides a kind of trend prediction of the usage amount of multiple resources of multiple stage computers
Analysis system and its method.The present invention shown using the form of K line chart each resource in the usage amount situation of a time section,
Can so allow monitoring side observed in a manner of more intuitive and is open-and-shut each resource in the usage amount situation of a time section,
And carry out big data trend prediction analysis through trend prediction device, with find ahead of time each resource future in use whether
It can be abnormal or when each resource future can encounter problem, to make strain ahead of time.
The foregoing is merely to explain presently preferred embodiments of the present invention, it is not intended to do any form to the present invention accordingly
On limitation, therefore, it is all have make any modification or change for the present invention under identical spirit, all should include
The invention is intended to the scopes of protection.
Claims (10)
1. a kind of computer resource usage amount trend prediction analysis system characterized by comprising
One data capture device captures an at least key index for at least usage amount of a resource in an at least computer installation
Value；
One data analysis set-up is connected to the data capture device, and receives, analyzes an at least key index value；
One data exhibiting device, is connected to the data analysis set-up, and by after data analysis set-up analysis this at least one
Crucial pointer value is shown with an image；And
One trend prediction device analyzes at least key index value shown with the image, to generate a trend prediction figure；
Wherein, which is connected to the data exhibiting device, and the data exhibiting device shows the trend prediction figure.
2. computer resource usage amount trend prediction analysis system as described in claim 1, which is characterized in that at least one pass
Key index value includes that the daily of an at least resource begins to use numerical quantity, every end of day usage amount numerical value, daily maximum use
Numerical quantity and daily minimum use numerical quantity.
3. computer resource usage amount trend prediction analysis system as described in claim 1, which is characterized in that the trend prediction
Device is analyzed by linear regression mode, to generate the trend prediction figure.
4. computer resource usage amount trend prediction analysis system as described in claim 1, which is characterized in that at least one pass
Key index value is an at least KPI value, which is K line chart.
5. computer resource usage amount trend prediction analysis system as described in claim 1, which is characterized in that at least one money
The usage amount in source include at least the utilization rate of a CPU, the utilization rate of an at least memory, an at least disk capacity.
6. a kind of computer resource usage amount trend prediction analysis method, which comprises the following steps:
At least one key of at least usage amount of a resource in an at least computer installation is captured by a data capture device
Index value；
It is received by a data analysis set-up and analyzes an at least key index value；
At least one crucial pointer value after data analysis set-up analysis is shown with an image by a data exhibiting device
Show；And
By at least key index value that a trend prediction device analysis is shown with the image, and generate a trend prediction
Figure；
Wherein, which shows the trend prediction figure.
7. computer resource usage amount trend prediction analysis method as claimed in claim 6, which is characterized in that become by this
In the step of gesture prediction meanss are analyzed at least key index value shown with the image and generate the trend prediction figure, this becomes
Gesture prediction meanss further generate a prediction threshold values, when at least one prediction numerical value in the trend prediction figure reaches the prediction threshold values
When, at least one prediction numerical value for reaching the prediction threshold values can be shown on the trend prediction figure in the form of warning.
8. computer resource usage amount trend prediction analysis method as claimed in claim 7, which is characterized in that the trend prediction
Device analyzes at least key index value in the image by machine learning mode, to generate the prediction threshold values.
9. computer resource usage amount trend prediction analysis method as claimed in claim 6, which is characterized in that at least one pass
Key index value includes that the daily of an at least resource begins to use numerical quantity, every end of day usage amount numerical value, daily maximum use
Numerical quantity and daily minimum use numerical quantity.
10. computer resource usage amount trend prediction analysis method as claimed in claim 6, which is characterized in that the trend is pre-
It surveys device to be analyzed by linear regression mode, to generate the trend prediction figure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810183873.9A CN110245054A (en) | 2018-03-07 | 2018-03-07 | Computer resource usage amount trend prediction analysis system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810183873.9A CN110245054A (en) | 2018-03-07 | 2018-03-07 | Computer resource usage amount trend prediction analysis system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110245054A true CN110245054A (en) | 2019-09-17 |
Family
ID=67876205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810183873.9A Pending CN110245054A (en) | 2018-03-07 | 2018-03-07 | Computer resource usage amount trend prediction analysis system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110245054A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060010101A1 (en) * | 2004-07-08 | 2006-01-12 | Yasuhiro Suzuki | System, method and program product for forecasting the demand on computer resources |
| US20090300173A1 (en) * | 2008-02-29 | 2009-12-03 | Alexander Bakman | Method, System and Apparatus for Managing, Modeling, Predicting, Allocating and Utilizing Resources and Bottlenecks in a Computer Network |
| JP2013175085A (en) * | 2012-02-27 | 2013-09-05 | Nec Corp | Apparatus, method and program for predicting resource capacity |
| CN106598805A (en) * | 2016-12-02 | 2017-04-26 | 太原师范学院 | Network-based computer hardware monitoring system |
-
2018
- 2018-03-07 CN CN201810183873.9A patent/CN110245054A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060010101A1 (en) * | 2004-07-08 | 2006-01-12 | Yasuhiro Suzuki | System, method and program product for forecasting the demand on computer resources |
| US20090300173A1 (en) * | 2008-02-29 | 2009-12-03 | Alexander Bakman | Method, System and Apparatus for Managing, Modeling, Predicting, Allocating and Utilizing Resources and Bottlenecks in a Computer Network |
| JP2013175085A (en) * | 2012-02-27 | 2013-09-05 | Nec Corp | Apparatus, method and program for predicting resource capacity |
| CN106598805A (en) * | 2016-12-02 | 2017-04-26 | 太原师范学院 | Network-based computer hardware monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11755452B2 (en) | Log data collection method based on log data generated by container in application container environment, log data collection device, storage medium, and log data collection system | |
| JP5324958B2 (en) | Method, program and apparatus for generating an integrated display of performance trends for multiple resources in a data processing system (integrated display of resource performance trends) | |
| US9753066B2 (en) | Methods and apparatus of analyzing electrical power grid data | |
| CN109684162B (en) | Equipment state prediction method, system, terminal and computer readable storage medium | |
| US9459980B1 (en) | Varying cluster sizes in a predictive test load while testing a productive system | |
| CN107704387B (en) | Method, device, electronic equipment and computer readable medium for system early warning | |
| WO2022088632A1 (en) | User data monitoring and analysis method, apparatus, device, and medium | |
| CN111638988A (en) | Cloud host fault intelligent prediction method based on deep learning | |
| CN114091783A (en) | Enterprise electricity utilization early warning method and device, computer equipment and storage medium | |
| CN108804037A (en) | The method and system of storage device History Performance Data are handled based on box figure | |
| US9501321B1 (en) | Weighted service requests throttling | |
| CN110347546B (en) | Dynamic adjustment method, device, medium and electronic equipment for monitoring task | |
| CN110245054A (en) | Computer resource usage amount trend prediction analysis system and method | |
| CN113641567B (en) | Database inspection method and device, electronic equipment and storage medium | |
| US9235424B1 (en) | Managing the performance of a data processing system through visualization of performance metrics data via a cognitive map | |
| US20230179501A1 (en) | Health index of a service | |
| Jiang et al. | Moneo: Monitoring fine-grained metrics nonintrusively in AI infrastructure | |
| US10353928B2 (en) | Real-time clustering using multiple representatives from a cluster | |
| Povoa et al. | A model for estimating energy consumption based on resources utilization | |
| US20120265723A1 (en) | Determining when to create a prediction based on deltas of metric values | |
| CN111628901A (en) | Index abnormality detection method and related device | |
| CN113220967B (en) | Ecological health degree measuring method and device for Internet environment and electronic equipment | |
| CN108664326A (en) | Information processing equipment and information processing system | |
| US20230004938A1 (en) | Detecting Inactive Projects Based On Usage Signals And Machine Learning | |
| WO2023185358A1 (en) | Kernel density estimation-based virtual machine running state detection method and apparatus |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190917 |