CN111242163B - Method, system and equipment for predicting performance of storage equipment - Google Patents
Method, system and equipment for predicting performance of storage equipment Download PDFInfo
- Publication number
- CN111242163B CN111242163B CN201911384106.5A CN201911384106A CN111242163B CN 111242163 B CN111242163 B CN 111242163B CN 201911384106 A CN201911384106 A CN 201911384106A CN 111242163 B CN111242163 B CN 111242163B
- Authority
- CN
- China
- Prior art keywords
- performance
- storage device
- iterative algorithm
- test
- predicting
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 58
- 238000012360 testing method Methods 0.000 claims abstract description 57
- 238000012549 training Methods 0.000 claims description 36
- 238000011056 performance test Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 238000013499 data model Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 abstract description 3
- 238000012545 processing Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2273—Test methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
According to the method, the system and the equipment for predicting the performance of the storage equipment, provided by the invention, the performance of the storage equipment is predicted through the AdaBoost iterative algorithm model, various data samples obtained when the storage equipment is developed and tested can be effectively utilized, the AdaBoost iterative algorithm model obtained after machine learning can obtain a more optimal configuration scheme for a user to use the storage equipment, the workload of developing and testing personnel for optimizing the storage equipment is reduced, and the method, the system and the equipment have strong practicability.
Description
Technical Field
The invention relates to the technical field of storage device testing, in particular to a method, a system and a device for predicting the performance of storage devices.
Background
With the rapid development of scientific computing and various network applications, the amount of information generated by human beings is more and more, and the storage of data is more and more concerned by people, so that the position of a storage component in the whole computer system is more and more important, and the storage is shifted to a disk array from a single disk and a single tape, and further the storage network is developed to be popular at present. The demand for large-scale data application is continuously emerging, mass data and application thereof become a new development direction, data storage has a great influence on the work and life of people, and naturally and more attention needs to be paid to the improvement of various performances of used storage equipment.
The performance of a single storage device is greatly different in input and output performance for different management software layer configurations on the premise that the hardware configuration is not changed, and how to judge the performance of the configured storage device under the fixed hardware environment condition is a problem which is focused on by a customer when the storage device is used and is also a target to be achieved by the storage device during performance test.
In general, the performance high-low data indicator of interest for a storage device is IOPS (I/O per second), i.e., the maximum number of I/os per second. Under the condition that hardware is unchanged, the performance value of the storage device is related to parameter configurations such as the number of selected links, the RAID level, the number of disks contained in the RAID, the number of created LUNs, the number of concurrences and the like, in the process of optimizing the performance of the storage device, each parameter adjustment influences the performance, the optimal storage performance configuration can be selected only by repeatedly debugging and combining experience under the general condition, and no direct theoretical basis or scheme can be referred to.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a method, a system and a device for predicting performance of a storage device, in which an AdaBoost iterative algorithm model is used to predict the performance of the storage device, various configuration parameters and data are used for machine learning during performance testing of the storage device to obtain an intelligent prediction model, and the quality of a parameter configuration scheme is determined for the storage device in the scenes of user use, performance testing, etc.
An AdaBoost (Adaptive Boosting) iterative algorithm model is a lifting algorithm based on a statistical learning theory, and the core idea is to train different classifiers, namely weak classifiers, aiming at the same training set, then assemble the weak classifiers to construct a stronger final classifier, namely a decision classifier, thereby achieving the purpose of obtaining a good statistical rule under the condition of dispersive statistical sample size.
In order to achieve the purpose, the invention is realized by the following technical scheme: a method for predicting the performance of a storage device comprises the following steps:
s1: building a storage equipment environment and collecting test data;
s2: constructing collected test data into a data sample characteristic space vector according to a test data representation method required by building an AdaBoost iterative algorithm model;
s3: building an AdaBoost iterative algorithm model and a data sample input and output interface;
s4: inputting performance test results of the storage equipment with different configurations in different environments into the AdaBoost iterative algorithm model, and training the AdaBoost iterative algorithm;
s5: testing an AdaBoost iterative algorithm model, judging whether the accuracy reaches a preset value, if so, successfully training and turning to the next step;
s6: and inputting the configuration information of the storage equipment to be tested into the AdaBoost iterative algorithm model to obtain a performance prediction conclusion.
Further, the test data includes: the RAID level of the storage device, the number of disks contained in the RAID, the number of output links, the number of LUNs created per RAID, the number of concurrency of testing performance, and performance test results.
Further, the step S2 includes:
the RAID levels of the storage device include RAID0, RAID10, RAID5, and RAID6, and the four RAID levels are respectively represented by x1 {1,2,3,4 };
the RAID of the storage device comprises the disk number represented by x2 ═ {1,2,3 … … 24}, wherein the maximum element 24 represents the maximum supported 24 disk number of the current corresponding storage product;
the output link number of the storage device is represented by x3 ═ {1,2,3 … … 8}, wherein the maximum element 8 represents that the current corresponding storage product supports 8 links at maximum;
the division of the LUNs under the RAID of the storage device is divisible into a plurality of LUNs according to scenes, and is represented by x4 ═ {1,2,3 … … 10}, wherein the largest element 10 represents the 10 LUNs with the largest current test performance division;
the concurrency number of the test performance of the storage device is represented by x5 ═ {1,2,3 … … 64} according to an actual scene, wherein a maximum element 64 represents that the maximum concurrency number of the actual test scene is 64;
the performance test results of the memory device test are denoted by y.
Further, the step S3 includes:
according to results obtained from different performance test scenes, a data sample feature space training data model of the AdaBoost iterative algorithm is established as follows:
T＝{(X1,Y1),(X2,Y2),…,(XN,YN)}
wherein:
n ═ 1,2, … …, indicating the number of performance tests;
Xii is 1,2, … … N, and represents a feature vector of the i-th different configuration combination, i.e., a 5-dimensional feature vector consisting of configurations x1, x2, x3, x4, and x 5;
Yi1 { +1, -1}, i { +1, 2, … … N, which means the ith time represented byFeature vector XiMarking corresponding test result Y, defining Y when performance test result Y is less than 1000i-1 indicates low performance; y is greater than or equal to 1000 according to performance test resultiHigh performance is indicated by + 1.
Further, the step S4 further includes:
expressing the characteristic space vector T as a final result to be obtained by a graph and an AdaBoost iterative algorithm model and displaying the final result;
solving a final classifier function F (X) in an iterative process, and predicting the performance of the storage equipment by substituting storage configuration XiAnd F (X) obtaining the high-low classification of the predicted performance value.
Further, the iterative algorithm for solving the final classifier function f (x) includes the following steps:
input training data set T { (X)1,Y1),(X2,Y2),…,(XN,YN) }, iteration times M;
the weight distribution of the initialized training samples is as follows:
D1＝(w1,1,w1,2,…w1,i),
for M ═ 1,2,3, …, M, each iteration includes:
using a weight distribution DmThe training data set is learned to obtain a weak classifier Gm(X)；
Calculation of Gm(X) classification error rate on training data set:
calculating Gm(X) specific gravity in strong classifier:
updating the weight distribution of the training data set:
a final classifier function is obtained:
correspondingly, the invention also discloses a system for predicting the performance of the storage device, which comprises the following steps:
the data preparation unit is used for building a storage equipment environment and collecting test data;
the vector construction unit is used for constructing collected test data into a data sample characteristic space vector according to a test data representation method required by building an AdaBoost iterative algorithm model;
the model building unit is used for building an AdaBoost iterative algorithm model and a data sample input/output interface;
the algorithm training unit is used for inputting performance test results of the storage equipment with different configurations in different environments into the AdaBoost iterative algorithm model and training the AdaBoost iterative algorithm;
the test unit is used for testing the AdaBoost iterative algorithm model and judging whether the accuracy rate reaches a preset value, if so, the training is successful and the next step is carried out;
and the prediction unit is used for inputting the configuration information of the storage equipment to be tested into the AdaBoost iterative algorithm model to obtain a performance prediction conclusion.
Correspondingly, the invention also discloses a device for predicting the performance of the storage device, which comprises:
a memory for storing a computer program;
a processor for implementing the method steps of predicting the performance of a storage device as described in any one of the above when executing the computer program.
Correspondingly, the invention also discloses a readable storage medium, wherein a computer program is stored on the readable storage medium, and when the computer program is executed by a processor, the computer program realizes the steps of the prediction method of the storage device performance.
Compared with the prior art, the invention has the beneficial effects that: the invention provides a method, a system and a device for predicting the performance of a storage device, which can predict the performance of the storage device through an AdaBoost iterative algorithm model, effectively utilize various data samples obtained during the development and test of the storage device, obtain the AdaBoost iterative algorithm model after machine learning, obtain a more optimal configuration scheme for a user to use the storage device, reduce the workload of developing and testing personnel to optimize the storage device, and have strong practicability.
The method is convenient to operate, does not need complex processing and human intervention, only needs to continuously input data samples, is complete in model automatic learning, and is strong in operability.
Therefore, compared with the prior art, the invention has prominent substantive features and remarkable progress, and the beneficial effects of the implementation are also obvious.
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, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a system block diagram of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made with reference to the accompanying drawings.
A method for predicting the performance of a storage device as shown in fig. 1 comprises the following steps:
s1: and building a storage equipment environment and collecting test data.
The test data includes: the RAID level of the storage device, the number of disks contained in the RAID, the number of output links, the number of LUNs created per RAID, the number of concurrency of testing performance, and performance test results.
S2: and constructing the collected test data into a data sample characteristic space vector according to a test data representation method required by building an AdaBoost iterative algorithm model.
And performing performance test on each storage device to obtain performance data under different configurations, wherein the representation methods of different configurations, performance results and data samples are as follows:
1. RAID level: the RAID levels stored include RAID0, RAID10, RAID5, and RAID6, and data x1 denotes RAID levels in 4 as {1,2,3,4}, respectively.
2. RAID contains the number of disks: the RAID includes a number of disks which may affect performance, where the number of disks is represented by x2 ═ {1,2,3 … … 24}, where the largest element 24 represents the maximum number of 24 disks supported by the current corresponding company storage product.
3. Number of output links stored: the output link is represented by x3 ═ {1,2,3 … … 8} according to the storage product characteristics, where the largest element 8 represents the maximum 8 links supported by the current corresponding company storage product.
4. Number of LUNs created per RAID: the division of LUNs under RAID can be divided into a plurality of LUNs according to the scenario, and x4 ═ {1,2,3 … … 10} represents that the largest element 10 represents the maximum 10 LUNs of the current test performance.
5. Number of concurrences for testing performance: the concurrency number is expressed by x5 ═ {1,2,3 … … 64} according to the actual scene, wherein the maximum element 64 represents that the actual test scene maximum concurrency number is 64.
6. And (3) performance test results: the IOPS results tested under different configurations are denoted by y.
S3: and (4) building an AdaBoost iterative algorithm model and a data sample input and output interface.
According to results obtained from different performance test scenes, a data sample characteristic space training data model is established as follows:
T＝{(X1,Y1),(X2,Y2),…,(XN,YN)}
wherein:
n ═ 1,2, … …, indicating the number of performance tests;
Xiand i is 1,2, … … N, and represents a feature vector of the i-th different arrangement combination, i.e., a 5-dimensional feature vector consisting of arrangements x1, x2, x3, x4, and x 5. Such as X1The configuration storage RAID0, 2 disks, 3 links, 4 LUNs, and 5 are indicated (1,2,3,4, 5).
Yi{ +1, -1}, i { +1, 2, … … N, which represents the ith order of the feature vector XiMarking corresponding test result Y, and defining Y when IOPS performance result Y is less than 1000i-1 indicates low performance; when IOPS performance result Y is more than or equal to 1000, YiHigh performance is indicated by + 1.
S4: and inputting the performance test results of the storage equipment with different configurations in different environments into the AdaBoost iterative algorithm model, and training the AdaBoost iterative algorithm.
The method also comprises the following steps: representing the characteristic space vector T as a graph and displaying a final result obtained by an AdaBoost iterative algorithm model, wherein the iterative process is to solve a final classifier function F (X) for describing a classified area, and then only substitute the storage configuration X when predicting the performance of the storage equipmentiAnd F (X), directly obtaining the high-low classification of the predicted performance value.
The iterative algorithm for solving the final classifier function F (X) comprises the following steps:
input training data set T { (X)1,Y1),(X2,Y2),…,(XN,YN) }, iteration times M;
the weight distribution of the initialized training samples is as follows:
D1＝(w1,1,w1,2,…w1,i),
for M ═ 1,2,3, …, M, each iteration includes:
using a weight distribution DmLearning the training data set to obtain a weak classifier Gm(X)；
Calculation of Gm(X) classification error rate on training data set:
calculation of Gm(X) specific gravity in strong classifier:
updating the weight distribution of the training data set:
a final classifier function is obtained:
s5: and testing the AdaBoost iterative algorithm model, judging whether the accuracy reaches a preset value, if so, successfully training and turning to the next step.
S6: and inputting the configuration information of the storage equipment to be tested into the AdaBoost iterative algorithm model to obtain a performance prediction conclusion.
On the basis of the prediction method of the performance of the storage device, the process of predicting the performance of the storage device by using the AdaBoost iterative algorithm model is further explained in detail:
(1) the storage device is mainly focused on the IOPS, different configuration schemes have the effect that the performance of the storage device is affected by the number of configured links, the RAID level, the number of disks contained in the RAID, the number of created LUNs, the number of concurrencies and other condition parameters under the condition that hardware is not changed, various condition parameters are required to be repeatedly combined for debugging in order to determine a performance result during actual use or test, the result can be determined by combining certain experience, time and labor are wasted, and errors cannot be guaranteed.
(2) By using the AdaBoost iterative algorithm model, data obtained by matching different conditions during testing can be effectively utilized, and the data are used as data samples and input into the model for algorithm training.
(3) After algorithm training is completed, expected accuracy is achieved through testing, and then when the storage device is used, the configured performance result is determined under different demand scenes, actual testing is not needed, and only configuration information is input into a model, so that performance expected conclusions of different combination and collocation can be obtained.
Correspondingly, as shown in fig. 2, the present invention also discloses a system for predicting the performance of a storage device, which includes:
and the data preparation unit is used for building a storage equipment environment and collecting test data.
And the vector construction unit is used for constructing the collected test data into a data sample characteristic space vector according to a test data representation method required by building an AdaBoost iterative algorithm model.
And the model building unit is used for building an AdaBoost iterative algorithm model and a data sample input and output interface.
And the algorithm training unit is used for inputting the performance test results of the storage equipment with different configurations in different environments into the AdaBoost iterative algorithm model and training the AdaBoost iterative algorithm.
And the testing unit is used for testing the AdaBoost iterative algorithm model and judging whether the accuracy reaches a preset value, if so, the training is successful and the next step is carried out.
And the prediction unit is used for inputting the configuration information of the storage equipment to be tested into the AdaBoost iterative algorithm model to obtain a performance prediction conclusion.
Correspondingly, the invention also discloses a device for predicting the performance of the storage device, which comprises:
a memory for storing a computer program;
a processor for implementing the method steps of predicting the performance of a storage device as described in any one of the above when executing the computer program.
Correspondingly, the invention also discloses a readable storage medium, wherein a computer program is stored on the readable storage medium, and when the computer program is executed by a processor, the computer program realizes the steps of the prediction method of the storage device performance.
Those skilled in the art will readily appreciate that the techniques of the embodiments of the present invention may be implemented as software plus a required general purpose hardware platform. Based on such understanding, the technical solutions in the embodiments of the present invention may be embodied in the form of a software product, where the computer software product is stored in a storage medium, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like, and the storage medium can store program codes, and includes instructions for enabling a computer terminal (which may be a personal computer, a server, or a second terminal, a network terminal, and the like) to perform all or part of the steps of the method in the embodiments of the present invention. The same and similar parts among the various embodiments in this specification may be referred to each other. Especially, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant points can be referred to the description in the method embodiment.
In the embodiments provided by the present invention, it should be understood that the disclosed system, system and method can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, systems or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one unit.
Similarly, each processing unit in the embodiments of the present invention may be integrated into one functional module, or each processing unit may exist physically, or two or more processing units are integrated into one functional module.
The invention is further described with reference to the accompanying drawings and specific embodiments. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and these equivalents also fall within the scope of the present application.
Claims (9)
1. A method for predicting performance of a storage device, comprising the steps of:
s1: building a storage equipment environment and collecting test data;
s2: constructing collected test data into a data sample characteristic space vector according to a test data representation method required by building an AdaBoost iterative algorithm model;
s3: building an AdaBoost iterative algorithm model and a data sample input and output interface;
s4: inputting performance test results of the storage equipment with different configurations in different environments into the AdaBoost iterative algorithm model, and training the AdaBoost iterative algorithm;
s5: testing an AdaBoost iterative algorithm model, judging whether the accuracy reaches a preset value, if so, successfully training and turning to the next step;
s6: and inputting the configuration information of the storage equipment to be tested into the AdaBoost iterative algorithm model to obtain a performance prediction conclusion.
2. The method of predicting the performance of a storage device according to claim 1, wherein the test data comprises: the RAID level of the storage device, the number of disks contained in the RAID, the number of output links, the number of LUNs created per RAID, the number of concurrency of testing performance, and performance test results.
3. The method for predicting the performance of the storage device according to claim 2, wherein the step S2 comprises:
the RAID levels of the storage device include RAID0, RAID10, RAID5, RAID6, and x1 ═ 1,2,3,4 represents the four RAID levels, respectively;
the RAID of the storage device comprises the disk number represented by x2 ═ {1,2,3 … … 24}, wherein the maximum element 24 represents the maximum supported 24 disk number of the current corresponding storage product;
the output link number of the storage device is represented by x3 ═ {1,2,3 … … 8}, wherein the largest element 8 represents that the current corresponding storage product supports 8 links at most;
the division of the LUNs under the RAID of the storage device is divisible into a plurality of LUNs according to scenes, and is represented by x4 ═ {1,2,3 … … 10}, wherein the largest element 10 represents the 10 LUNs with the largest current test performance division;
the concurrency number of the test performance of the storage device is represented by x5 ═ {1,2,3 … … 64} according to an actual scene, wherein a maximum element 64 represents that the maximum concurrency number of the actual test scene is 64;
and y represents the performance test result of the storage device test.
4. The method for predicting the performance of the storage device according to claim 3, wherein the step S3 comprises:
according to results obtained from different performance test scenes, a data sample feature space training data model of the AdaBoost iterative algorithm is established as follows:
T＝{(X1,Y1),(X2,Y2),…,(XN,YN)}
wherein:
n ═ 1,2, … …, indicating the number of performance tests;
Xii is 1,2, … … N, and represents a feature vector of the i-th different configuration combination, i.e., a 5-dimensional feature vector consisting of configurations x1, x2, x3, x4, and x 5;
Yi{ +1, -1}, i { +1, 2, … … N, which represents the ith order of the feature vector XiMarking corresponding test result Y, defining Y when performance test Y is less than 1000i-1 indicates low performance; y is more than or equal to 1000 in performance testiHigh performance is indicated by + 1.
5. The method for predicting performance of storage device according to claim 4, wherein said step S4 further comprises:
expressing the characteristic space vector T as a final result to be obtained by a graph and an AdaBoost iterative algorithm model and displaying the final result;
solving a final classifier function F (X) in an iterative process, and predicting the performance of the storage equipment by substituting storage configuration XiAnd F (X) obtaining the high-low classification of the predicted performance value.
6. The method of predicting storage device performance of claim 5, wherein the iterative algorithm step of solving the final classifier function F (X) is as follows:
input training data set T { (X)1,Y1),(X2,Y2),…,(XN,YN) }, iteration times M;
the weight distribution of the initialized training samples is as follows:
for M ═ 1,2,3, …, M, each iteration includes:
using a weight distribution DmThe training data set is learned to obtain a weak classifier Gm(X)；
Calculation of Gm(X) classification error rate on training data set:
calculation of Gm(X) specific gravity in strong classifier:
updating the weight distribution of the training data set:
a final classifier function is obtained:
7. a system for predicting storage device performance, comprising:
the data preparation unit is used for building a storage equipment environment and collecting test data;
the vector construction unit is used for constructing collected test data into a data sample characteristic space vector according to a test data representation method required by building an AdaBoost iterative algorithm model;
the model building unit is used for building an AdaBoost iterative algorithm model and a data sample input/output interface;
the algorithm training unit is used for inputting performance test results of the storage equipment with different configurations in different environments into the AdaBoost iterative algorithm model and training the AdaBoost iterative algorithm;
the testing unit is used for testing the AdaBoost iterative algorithm model and judging whether the accuracy reaches a preset value, if so, the training is successful and the next step is carried out;
and the prediction unit is used for inputting the configuration information of the storage equipment to be tested into the AdaBoost iterative algorithm model to obtain a performance prediction conclusion.
8. A device for predicting performance of a storage device, comprising:
a memory for storing a computer program;
a processor for implementing the method steps of predicting the performance of a storage device according to any one of claims 1 to 6 when executing said computer program.
9. A readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the method steps of predicting the performance of a storage device according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911384106.5A CN111242163B (en) | 2019-12-28 | 2019-12-28 | Method, system and equipment for predicting performance of storage equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911384106.5A CN111242163B (en) | 2019-12-28 | 2019-12-28 | Method, system and equipment for predicting performance of storage equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111242163A CN111242163A (en) | 2020-06-05 |
| CN111242163B true CN111242163B (en) | 2022-05-31 |
Family
ID=70872325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911384106.5A Active CN111242163B (en) | 2019-12-28 | 2019-12-28 | Method, system and equipment for predicting performance of storage equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111242163B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107730059A (en) * | 2017-11-29 | 2018-02-23 | 成都思晗科技股份有限公司 | The method of transformer station's electricity trend prediction analysis based on machine learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7676445B2 (en) * | 2003-08-20 | 2010-03-09 | International Business Machines Corporation | Apparatus, system and method for developing failure prediction software |
-
2019
- 2019-12-28 CN CN201911384106.5A patent/CN111242163B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107730059A (en) * | 2017-11-29 | 2018-02-23 | 成都思晗科技股份有限公司 | The method of transformer station's electricity trend prediction analysis based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111242163A (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106020715B (en) | Storage pool capacity management | |
| TWI433035B (en) | Scaling instruction intervals to identify collection points for representative instruction traces | |
| US8898096B2 (en) | Application configuration generation | |
| US8954309B2 (en) | Techniques for application tuning | |
| CN107220217A (en) | Characteristic coefficient training method and device that logic-based is returned | |
| CN111008693B (en) | Network model construction method, system and medium based on data compression | |
| CN110751326B (en) | Photovoltaic day-ahead power prediction method and device and storage medium | |
| CN107766573B (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium based on data processing | |
| Dong et al. | Adaptive neural network-based approximation to accelerate eulerian fluid simulation | |
| CN110210625A (en) | Modeling method, device, computer equipment and storage medium based on transfer learning | |
| WO2022088632A1 (en) | User data monitoring and analysis method, apparatus, device, and medium | |
| CN114862656A (en) | Method for acquiring training cost of distributed deep learning model based on multiple GPUs | |
| CN113610069B (en) | Knowledge distillation-based target detection model training method | |
| CN109711707B (en) | Comprehensive state evaluation method for ship power device | |
| CN104077303A (en) | Method and device for displaying data | |
| US20140365637A1 (en) | Methods and systems for reducing metrics used to monitor resources | |
| CN109800138B (en) | CPU testing method, electronic device and storage medium | |
| CN114297008A (en) | Cloud host performance prediction method and device, terminal and storage medium | |
| JP2023007366A (en) | Molecular structure acquiring method, apparatus, electronic device, and storage medium | |
| CN111242163B (en) | Method, system and equipment for predicting performance of storage equipment | |
| CN113010687B (en) | Exercise label prediction method and device, storage medium and computer equipment | |
| CN115185804A (en) | Server performance prediction method, system, terminal and storage medium | |
| CN111352812A (en) | Method and system for predicting performance of storage device based on naive Bayes machine learning model | |
| CN114266414A (en) | Loan amount prediction method, loan amount prediction device, loan amount prediction electronic device, and loan amount prediction medium | |
| CN108229572B (en) | Parameter optimization method and computing 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 |