CN109240885A - A kind of method for monitoring performance, system and electronic equipment and storage medium - Google Patents
A kind of method for monitoring performance, system and electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109240885A CN109240885A CN201811004228.2A CN201811004228A CN109240885A CN 109240885 A CN109240885 A CN 109240885A CN 201811004228 A CN201811004228 A CN 201811004228A CN 109240885 A CN109240885 A CN 109240885A
- Authority
- CN
- China
- Prior art keywords
- performance
- training
- neural network
- monitoring
- input vector
- 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
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Alarm Systems (AREA)
Abstract
This application discloses a kind of method for monitoring performance, system and a kind of electronic equipment and computer readable storage mediums, this method comprises: acquisition monitors the performance index value of resource, and construct performance curve according to the performance index value；According in the performance curve all performance index values and the corresponding slope of the performance index value determine input vector；The input vector is inputted in the BP neural network that training is completed, obtains failure modes result.In the BP neural network of slope building input matrix training completion of the method for monitoring performance provided by the present application according to the current value and the performance indicator of each performance indicator on performance curve, failure modes are completed.Passage capacity slope of a curve represents the fluctuation of the performance indicator, realizes the alarm to performance indicator fluctuation, and combining each performance indicator by the BP neural network of multiple performance indicators training realizes no threshold alarm.
Description
Technical field
This application involves field of computer technology, more specifically to a kind of method for monitoring performance, system and a kind of electricity
Sub- equipment and a kind of computer readable storage medium.
Background technique
With the rapid development of Internet, data center carries the functions such as the acquisition, storage and analysis of various data, and
With the increase of business, business host will appear the increase and fluctuation of cpu busy percentage, memory usage, network flow, affect
The stable operation of business.Monitoring system in the prior art is alerted according only to the threshold value of index, can not be to performance indicator
Fluctuation and a comprehensive index alerted, it is impossible to meet customer demands.
Therefore, how to realize that carrying out alarm to the fluctuation and each performance indicator of synthesis of performance indicator is this field skill
Art personnel's technical issues that need to address.
Summary of the invention
The application be designed to provide a kind of method for monitoring performance, system and a kind of electronic equipment and a kind of computer can
Storage medium is read, realizes and the fluctuation and each performance indicator of synthesis of performance indicator is alerted.
To achieve the above object, this application provides a kind of method for monitoring performance, comprising:
The performance index value of acquisition monitoring resource, and performance curve is constructed according to the performance index value；
According in the performance curve all performance index values and the corresponding slope of the performance index value determine
Input vector；
The input vector is inputted in the BP neural network that training is completed, obtains failure modes result.
Wherein, performance curve is constructed according to the performance index value, comprising:
Intermediate curve is constructed according to the continuous performance index value, and the intermediate curve is smoothed and is returned
One change handles to obtain the performance curve.
Wherein, the input vector is specially that all performance index values in the performance curve and the performance refer to
The row vector or column vector of the corresponding slope composition of scale value.
Wherein, the performance index value include cpu busy percentage, memory usage, portal flow, in system load
Any one or appoint several combinations.
Wherein, further include；
Obtain training sample；It wherein, include training performance achievement data and the training quota number by the training sample
According to corresponding trained failure modes result；
Training input vector is determined according to the training performance achievement data, and utilizes the trained input vector and described
Training failure modes result training BP neural network, obtains the BP neural network of training completion.
Wherein, it using the trained input vector and the trained failure modes result training BP neural network, is instructed
Practice the BP neural network completed, comprising:
S201: the parameter of the BP neural network is initialized；Wherein, the parameter includes input layer number, hidden layer
Number of nodes, output layer number of nodes, it is each nerve between weight, hidden layer threshold value, output layer threshold value, learning rate, excitation function and
Maximum number of iterations；
S202: it is calculated according to the trained input vector, the excitation function, the weight and the hidden layer threshold value hidden
Input value containing layer；
S203: according to the hidden layer input value, the hidden layer threshold value, the output layer threshold value and the weight computing
The prediction output valve of the BP neural network；
S204: error is calculated according to the prediction output valve and the trained failure modes result, and according to the error
Update the weight, the hidden layer threshold value and the output layer threshold value；
S202-S204 is repeated, until the error reaches preset standard or the number of iterations reaches the maximum number of iterations
When, obtain the BP neural network of training completion.
To achieve the above object, this application provides a kind of performance monitoring systems, comprising:
Module is constructed, constructs performance song for acquiring the performance index value of monitoring resource, and according to the performance index value
Line；
Determining module, for according to all performance index values and the performance index value pair in the performance curve
The slope answered determines input vector；
Categorization module obtains failure modes knot for inputting the input vector in the BP neural network that training is completed
Fruit.
Wherein, further include；
Module is obtained, for obtaining training sample；It wherein, include training performance achievement data and institute by the training sample
State the corresponding trained failure modes result of training quota data；
Training module for determining training input vector according to the training performance achievement data, and utilizes the training
Input vector and the trained failure modes result training BP neural network, obtain the BP neural network of training completion.
To achieve the above object, this application provides a kind of electronic equipment, comprising:
Memory, for storing computer program；
Processor is realized when for executing the computer program such as the step of above-mentioned method for monitoring performance.
To achieve the above object, this application provides a kind of computer readable storage medium, the computer-readable storages
It is stored with computer program on medium, the step such as above-mentioned method for monitoring performance is realized when the computer program is executed by processor
Suddenly.
By above scheme it is found that a kind of method for monitoring performance provided by the present application, comprising: the performance of acquisition monitoring resource
Index value, and performance curve is constructed according to the performance index value；According to all performance indicators in the performance curve
Value and the corresponding slope of the performance index value determine input vector；The input vector is inputted into the BP nerve net that training is completed
In network, failure modes result is obtained.
Method for monitoring performance provided by the present application is according to the current value and the performance indicator of each performance indicator in performance song
In the BP neural network that slope building input matrix training on line is completed, failure modes are completed.Passage capacity slope of a curve
The fluctuation for representing the performance indicator realizes the alarm to performance indicator fluctuation, passes through the BP of multiple performance indicators training
Neural network, which combines each performance indicator, realizes no threshold alarm.Disclosed herein as well is a kind of performance monitoring system and one
Kind electronic equipment and a kind of computer readable storage medium, are equally able to achieve above-mentioned technical effect.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of flow chart of method for monitoring performance disclosed in the embodiment of the present application；
Fig. 2 is the flow chart of another kind method for monitoring performance disclosed in the embodiment of the present application；
Fig. 3 is a kind of topologies of BP neural network disclosed in the embodiment of the present application；
Fig. 4 is a kind of structure chart of performance monitoring system disclosed in the embodiment of the present application；
Fig. 5 is the structure chart of a kind of electronic equipment disclosed in the embodiment of the present application；
Fig. 6 is the structure chart of another kind electronic equipment disclosed in the embodiment of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
The embodiment of the present application discloses a kind of method for monitoring performance, realizes each to the fluctuation and synthesis of performance indicator
Performance indicator is alerted.
Referring to Fig. 1, a kind of flow chart of method for monitoring performance disclosed in the embodiment of the present application, as shown in Figure 1, comprising:
S101: the performance index value of acquisition monitoring resource, and performance curve is constructed according to the performance index value；
In specific implementation, the performance index value of continuous acquisition monitoring resource, and according to the continuous of each performance indicator item
Value constructs the performance curve of each performance indicator item.As a preferred implementation manner, according in the building of continuous performance index value
Half interval contour, and intermediate curve is smoothed and normalized obtains performance curve.Smoothing processing is i.e. in a time
It is averaged in section as current value, normalized is mapped to data within the scope of 0-1 and handles, more convenient and quick.
Performance index value herein may include cpu busy percentage, memory usage, portal flow, system load
Deng being not specifically limited herein.
S102: according to all performance index values and the corresponding slope of the performance index value in the performance curve
Determine input vector；
In specific implementation, the slope of each current value represents the fluctuation of the performance indicator in passage capacity curve, according to
All current values of performance indicator and all slopes are by preset sortord building input vector.As a kind of preferred implementation side
Formula, the input vector are specially that all performance index values in the performance curve and the performance index value are corresponding
The row vector or column vector of slope composition.The failure modes result obtained eventually by BP neural network can refer in conjunction with each performance
Target fluctuation, failure modes result is more accurate, subsequent to alert to the fluctuation of performance indicator.
S103: the input vector is inputted in the BP neural network that training is completed, obtains failure modes result.
Before this step, there are the training steps of BP neural network for default, specifically, obtaining training sample；According to described
Training performance achievement data determines training input vector, and utilizes the trained input vector and the trained failure modes result
Training BP neural network, obtains the BP neural network of training completion.It wherein, include training performance index number by the training sample
According to trained failure modes corresponding with the training quota data as a result, how specific for example train input vector and training failure
Classification results training BP neural network will describe in detail in next embodiment.
In specific implementation, it obtains after training the BP neural network completed, all properties index that previous step is obtained
In the BP neural network that corresponding input vector input training is completed, successively calculated, the prediction result of final output is then
As a result, the failure modes result combines each performance indicator, prediction result is more accurate, subsequent for the failure modes finally predicted
Each performance indicator can be integrated to be alerted.
Method for monitoring performance provided by the embodiments of the present application exists according to the current value and the performance indicator of each performance indicator
In the BP neural network that slope building input matrix training on performance curve is completed, failure modes are completed.Passage capacity curve
Slope represent the fluctuation of the performance indicator, realize the alarm to performance indicator fluctuation, instructed by multiple performance indicators
Experienced BP neural network, which combines each performance indicator, realizes no threshold alarm.
The training process of BP neural network is described in detail below, specific:
Referring to fig. 2, the flow chart of another kind method for monitoring performance disclosed in the embodiment of the present application, as shown in Figure 2, comprising:
S201: the parameter of the BP neural network is initialized；Wherein, the parameter includes input layer number, hidden layer
Number of nodes, output layer number of nodes, it is each nerve between weight, hidden layer threshold value, output layer threshold value, learning rate, excitation function and
Maximum number of iterations；
BP neural network is a kind of multilayer feedforward neural network, which is mainly characterized by signal to front transfer, error
Backpropagation.Into front transfer, input signal carries out layer-by-layer processing from input layer to hidden layer, until final output layer.
The state of neuron each time can all influence the state of neuron next time, if result that output layer calculates and phase
The output bias of prestige is larger, then enters backpropagation and be adjusted according to the error of prediction to the weight and threshold value of network, from
And the output valve of the prediction of BP neural network is made constantly to approach desired output valve.The topologies of BP neural network such as Fig. 3
It is shown.
In specific implementation, the initialization for carrying out network first, according to training input vector X trained failure corresponding with its
Classification results Y determines BP neural network input layer number n, node in hidden layer l, output layer number of nodes m, and initializes each
Weight W between a neuronjk、WijAnd hidden layer threshold value a, output layer threshold value b, setting learning rate, neuron excitation function and
Maximum number of iterations.
S202: it is calculated according to the trained input vector, the excitation function, the weight and the hidden layer threshold value hidden
Input value containing layer；
Wherein, hidden layer input value HjCalculation formula is as follows:
Wherein,
S203: according to the hidden layer input value, the hidden layer threshold value, the output layer threshold value and the weight computing
The prediction output valve of the BP neural network；
Wherein, output valve O is predictedkCalculation formula is as follows:
S204: error is calculated according to the prediction output valve and the trained failure modes result, and according to the error
Update the weight, the hidden layer threshold value and the output layer threshold value；
Wherein, error ekCalculation formula is as follows:
ek=Yk-Ok, k=1,2,3..., m；
Weight Wij、WjkMore new formula is as follows:
Wjk=Wjk+ηHjek；
Threshold value aj、bkMore new formula is as follows:
bk=bk+ek；
S205: judge whether the error reaches preset standard or whether the number of iterations reaches the maximum number of iterations；
If so, obtaining the BP neural network of training completion；If it is not, then reentering S202.
In specific implementation, when error is less than preset value or reaches maximum number of iterations, training is completed, and obtains having trained
At BP neural network.
A kind of performance monitoring system provided by the embodiments of the present application is introduced below, a kind of performance prison described below
Control system can be cross-referenced with a kind of above-described method for monitoring performance.
Referring to fig. 4, the structure chart of a kind of performance monitoring system provided by the embodiments of the present application, as shown in Figure 4, comprising:
Module 401 is constructed, constructs performance for acquiring the performance index value of monitoring resource, and according to the performance index value
Curve；
Determining module 402, for according in the performance curve all performance index values and the performance indicator
It is worth corresponding slope and determines input vector；
Categorization module 403 obtains failure modes for inputting the input vector in the BP neural network that training is completed
As a result.
Performance monitoring system provided by the embodiments of the present application exists according to the current value of each performance indicator and the performance indicator
In the BP neural network that slope building input matrix training on performance curve is completed, failure modes are completed.Passage capacity curve
Slope represent the fluctuation of the performance indicator, realize the alarm to performance indicator fluctuation, instructed by multiple performance indicators
Experienced BP neural network, which combines each performance indicator, realizes no threshold alarm.
On the basis of the above embodiments, the building module 401 includes: as a preferred implementation manner,
Acquisition unit, for acquiring the performance index value of monitoring resource；
Construction unit, for constructing intermediate curve according to the continuous performance index value, and to the intermediate curve into
Row smoothing processing and normalized obtain the performance curve.
On the basis of the above embodiments, the input vector is specially the performance as a preferred implementation manner,
The row vector or column vector of the corresponding slope composition of all performance index values and the performance index value in curve.
On the basis of the above embodiments, the performance index value includes that CPU is utilized as a preferred implementation manner,
Any one of rate, memory usage, portal flow, system load appoint several combinations.
On the basis of the above embodiments, further include as a preferred implementation manner,；
Module is obtained, for obtaining training sample；It wherein, include training performance achievement data and institute by the training sample
State the corresponding trained failure modes result of training quota data；
Training module for determining training input vector according to the training performance achievement data, and utilizes the training
Input vector and the trained failure modes result training BP neural network, obtain the BP neural network of training completion.
On the basis of the above embodiments, the training module includes: as a preferred implementation manner,
Determination unit, for determining training input vector according to the training performance achievement data；
Initialization unit, for initializing the parameter of the BP neural network；Wherein, the parameter includes input layer
Number, node in hidden layer, output layer number of nodes, it is each nerve between weight, hidden layer threshold value, output layer threshold value, learning rate, swash
Encourage function and maximum number of iterations；
First computing unit, for according to the trained input vector, the excitation function, the weight and described implicit
Layer threshold calculations hidden layer input value；
Second computing unit, for according to the hidden layer input value, the hidden layer threshold value, the output layer threshold value and
The prediction output valve of BP neural network described in the weight computing；
Updating unit is used for according to the prediction output valve and the trained failure modes result calculating error, and according to
Weight described in the error update, the hidden layer threshold value and the output layer threshold value；
Judging unit, for judging whether the error reaches preset standard or whether the number of iterations reaches the maximum and change
Generation number, if so, obtaining the BP neural network of training completion；If it is not, then restarting the work of first computing unit
Process.
Present invention also provides a kind of electronic equipment, referring to Fig. 5, the knot of a kind of electronic equipment provided by the embodiments of the present application
Composition, as shown in Figure 5, comprising:
Memory 100, for storing computer program；
Step provided by above-described embodiment may be implemented in processor 200 when for executing the computer program.
Specifically, memory 100 includes non-volatile memory medium, built-in storage.Non-volatile memory medium storage
There are operating system and computer-readable instruction, which is that the operating system and computer in non-volatile memory medium can
The operation of reading instruction provides environment.Processor 200 provides calculating and control ability for electronic equipment, executes the memory 100
When the computer program of middle preservation, the step of method for monitoring performance that any of the above-described embodiment provides may be implemented.
The embodiment of the present application is according to the current value of each performance indicator and slope structure of the performance indicator on performance curve
It builds in the BP neural network that input matrix training is completed, completes failure modes.Passage capacity slope of a curve represents the performance and refers to
Target fluctuation realizes the alarm to performance indicator fluctuation, and the BP neural network by the training of multiple performance indicators is comprehensive
Each performance indicator realizes no threshold alarm.
On the basis of the above embodiments, preferably, referring to Fig. 6, the electronic equipment further include:
Input interface 300 is connected with processor 200, for obtaining computer program, parameter and the instruction of external importing,
It saves through the control of processor 200 into memory 100.The input interface 300 can be connected with input unit, and it is manual to receive user
The parameter or instruction of input.The input unit can be the touch layer covered on display screen, be also possible to be arranged in terminal enclosure
Key, trace ball or Trackpad, be also possible to keyboard, Trackpad or mouse etc..Specifically, in the present embodiment, by defeated
The parameter etc. of the input BP neural network of incoming interface 300.
Display unit 400 is connected with processor 200, the data sent for video-stream processor 200.The display unit 400
It can be display screen, liquid crystal display or the electric ink display screen etc. in PC machine.It, can be with specifically, in the present embodiment
Failure modes result etc. is shown by display unit 400.
The network port 500 is connected with processor 200, for being communicatively coupled with external each terminal device.The communication link
The communication technology used by connecing can be cable communicating technology or wireless communication technique, and such as mobile high definition chained technology (MHL) leads to
It is blue with universal serial bus (USB), high-definition media interface (HDMI), adopting wireless fidelity technology (WiFi), Bluetooth Communication Technology, low-power consumption
The tooth communication technology, communication technology based on IEEE802.11s etc..Specifically, in the present embodiment, the network port can be passed through
500 import the BP neural network etc. that training is completed to processor 200.
Present invention also provides a kind of computer readable storage medium, the storage medium may include: USB flash disk, mobile hard disk,
Read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic
The various media that can store program code such as dish or CD.Computer program, the calculating are stored on the storage medium
Machine program realizes the step of method for monitoring performance that any of the above-described embodiment provides when being executed by processor.
Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are with other realities
The difference of example is applied, the same or similar parts in each embodiment may refer to each other.For system disclosed in embodiment
Speech, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part illustration
?.It should be pointed out that for those skilled in the art, under the premise of not departing from the application principle, also
Can to the application, some improvement and modification can also be carried out, these improvement and modification also fall into the protection scope of the claim of this application
It is interior.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
Claims (10)
1. a kind of method for monitoring performance characterized by comprising
The performance index value of acquisition monitoring resource, and performance curve is constructed according to the performance index value；
According in the performance curve all performance index values and the corresponding slope of the performance index value determine input
Vector；
The input vector is inputted in the BP neural network that training is completed, obtains failure modes result.
2. method for monitoring performance according to claim 1, which is characterized in that it is bent to construct performance according to the performance index value
Line, comprising:
Intermediate curve is constructed according to the continuous performance index value, and the intermediate curve is smoothed and is normalized
Processing obtains the performance curve.
3. method for monitoring performance according to claim 1, which is characterized in that the input vector is specially the performance curve
In all performance index values and the performance index value corresponding slope composition row vector or column vector.
4. method for monitoring performance according to claim 1, which is characterized in that the performance index value includes cpu busy percentage, interior
It deposits any one of utilization rate, portal flow, system load or appoints several combinations.
5. any one of -4 method for monitoring performance according to claim 1, which is characterized in that further include；
Obtain training sample；It wherein, include training performance achievement data and the training quota data pair by the training sample
The training failure modes result answered；
Training input vector is determined according to the training performance achievement data, and utilizes the trained input vector and the training
Failure modes result trains BP neural network, obtains the BP neural network of training completion.
6. method for monitoring performance according to claim 5, which is characterized in that utilize the trained input vector and the training
Failure modes result trains BP neural network, obtains the BP neural network of training completion, comprising:
S201: the parameter of the BP neural network is initialized；Wherein, the parameter includes input layer number, hidden layer node
Number, output layer number of nodes, it is each nerve between weight, hidden layer threshold value, output layer threshold value, learning rate, excitation function and maximum
The number of iterations；
S202: hidden layer is calculated according to the trained input vector, the excitation function, the weight and the hidden layer threshold value
Input value；
S203: according to the hidden layer input value, the hidden layer threshold value, the output layer threshold value and the weight computing
The prediction output valve of BP neural network；
S204: error is calculated according to the prediction output valve and the trained failure modes result, and according to the error update
The weight, the hidden layer threshold value and the output layer threshold value；
S202-S204 is repeated to obtain when the error reaches preset standard or the number of iterations reaches the maximum number of iterations
The BP neural network completed to training.
7. a kind of performance monitoring system characterized by comprising
Module is constructed, constructs performance curve for acquiring the performance index value of monitoring resource, and according to the performance index value；
Determining module, for according in the performance curve all performance index values and the performance index value it is corresponding
Slope determines input vector；
Categorization module obtains failure modes result for inputting the input vector in the BP neural network that training is completed.
8. performance monitoring system according to claim 7, which is characterized in that further include；
Module is obtained, for obtaining training sample；It wherein, include training performance achievement data and the instruction by the training sample
Practice the corresponding trained failure modes result of achievement data；
Training module for determining training input vector according to the training performance achievement data, and utilizes the training input
Training failure modes result training BP neural network, obtains the BP neural network of training completion described in vector sum.
9. a kind of electronic equipment characterized by comprising
Memory, for storing computer program；
Processor, realizing the method for monitoring performance as described in any one of claim 1 to 6 when for executing the computer program
Step.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the step of the method for monitoring performance as described in any one of claim 1 to 6 when the computer program is executed by processor
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811004228.2A CN109240885A (en) | 2018-08-30 | 2018-08-30 | A kind of method for monitoring performance, system and electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811004228.2A CN109240885A (en) | 2018-08-30 | 2018-08-30 | A kind of method for monitoring performance, system and electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109240885A true CN109240885A (en) | 2019-01-18 |
Family
ID=65069167
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811004228.2A Pending CN109240885A (en) | 2018-08-30 | 2018-08-30 | A kind of method for monitoring performance, system and electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109240885A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111832247A (en) * | 2020-06-24 | 2020-10-27 | 苏州浪潮智能科技有限公司 | Method and device for determining size of via hole anti-pad based on BP neural network |
| CN113496625A (en) * | 2021-08-11 | 2021-10-12 | 合肥工业大学 | Private parking space sharing method based on improved BP neural network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090094180A1 (en) * | 2007-10-04 | 2009-04-09 | Siemens Medical Solutions Usa, Inc. | Method of real-time crystal peak tracking for positron emission tomography (pet) avalanche-photodiodes (apd) detector |
| CN104316341A (en) * | 2014-11-17 | 2015-01-28 | 金陵科技学院 | Underground structure damage identification method based on BP neural network |
| CN107247653A (en) * | 2017-06-02 | 2017-10-13 | 郑州云海信息技术有限公司 | A kind of Fault Classification and device of data center's monitoring system |
-
2018
- 2018-08-30 CN CN201811004228.2A patent/CN109240885A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090094180A1 (en) * | 2007-10-04 | 2009-04-09 | Siemens Medical Solutions Usa, Inc. | Method of real-time crystal peak tracking for positron emission tomography (pet) avalanche-photodiodes (apd) detector |
| CN104316341A (en) * | 2014-11-17 | 2015-01-28 | 金陵科技学院 | Underground structure damage identification method based on BP neural network |
| CN107247653A (en) * | 2017-06-02 | 2017-10-13 | 郑州云海信息技术有限公司 | A kind of Fault Classification and device of data center's monitoring system |
Non-Patent Citations (1)
| Title |
|---|
| 孙红跃: "基于神经网络的建筑结构损伤识别方法", 《控制工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111832247A (en) * | 2020-06-24 | 2020-10-27 | 苏州浪潮智能科技有限公司 | Method and device for determining size of via hole anti-pad based on BP neural network |
| CN111832247B (en) * | 2020-06-24 | 2022-06-03 | 苏州浪潮智能科技有限公司 | Method and device for determining size of via hole anti-pad based on BP neural network |
| CN113496625A (en) * | 2021-08-11 | 2021-10-12 | 合肥工业大学 | Private parking space sharing method based on improved BP neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107526709A (en) | Handled using the tensor of low precision format | |
| CN107911491A (en) | Information recommendation method, device and storage medium, server and mobile terminal | |
| CN108431832A (en) | Neural network is expanded using external memory | |
| CN107766573B (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium based on data processing | |
| CN108537399A (en) | A kind of prediction technique and device of material requirement amount | |
| CN115796932B (en) | Project cost prediction method and device, electronic equipment and storage medium | |
| CN107273979A (en) | The method and system of machine learning prediction are performed based on service class | |
| CN109240885A (en) | A kind of method for monitoring performance, system and electronic equipment and storage medium | |
| CN109829763A (en) | Consuming capacity appraisal procedure and device, electronic equipment, storage medium | |
| CN116010226A (en) | Software system reliability simulation evaluation method and device and computer equipment | |
| Wang et al. | A new method of nonlinear causality detection: Reservoir computing Granger causality | |
| Almomani et al. | Selecting a good stochastic system for the large number of alternatives | |
| CN107463486A (en) | System performance analysis method, apparatus and server | |
| CN111047389A (en) | Monitoring recommendation analysis method, storage medium and system for AR shopping application | |
| CN108229572B (en) | Parameter optimization method and computing equipment | |
| CN116168403A (en) | Medical data classification model training method, classification method, device and related medium | |
| CN114757700A (en) | Article sales prediction model training method, article sales prediction method and apparatus | |
| Yu et al. | Model-robust design of conjoint choice experiments | |
| CN110163279A (en) | A kind of energy client segmentation method, apparatus and calculate equipment | |
| CN113095592A (en) | Method and system for performing predictions based on GNN and training method and system | |
| TWM644927U (en) | Inventory Management System | |
| CN117436974A (en) | Product recommendation method, device, computer equipment and storage medium | |
| CN116467521A (en) | Training method of account recommendation model, account recommendation method, device and equipment | |
| CN116680973A (en) | Battery heating time prediction method, system, vehicle and storage medium | |
| CN117196703A (en) | Resource distribution method, device, computer equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |