CN102184746A - Storage performance testing system and method based on particle swarm optimization parameter - Google Patents
Storage performance testing system and method based on particle swarm optimization parameter Download PDFInfo
- Publication number
- CN102184746A CN102184746A CN 201010619704 CN201010619704A CN102184746A CN 102184746 A CN102184746 A CN 102184746A CN 201010619704 CN201010619704 CN 201010619704 CN 201010619704 A CN201010619704 A CN 201010619704A CN 102184746 A CN102184746 A CN 102184746A
- Authority
- CN
- China
- Prior art keywords
- test
- module
- parameter
- particle
- testing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention provides a storage performance testing system based on a particle swarm optimization parameter. The system comprises a testing management module, a data acquisition module, a particle swarm establishment module, a parameter optimization adjustment module, a load testing module, a test data analysis module and a test result output module. The problems that the optimal value of the testing parameter is obtained by manually setting a testing parameter and manually analyzing testing results, and low testing efficiency and low accuracy exist during optimal value searching under a condition of a plurality of testing parameters are solved. The storage performance testing system and method based on the particle swarm optimization parameter can be used for quickly acquiring the optimal testing parameter of storage performance of a file system, and are specially suitable for the problem on the optimal value of the testing system in the condition of a plurality of testing parameters.
Description
Technical field
The present invention relates to a kind of memory property measuring technology, specifically a kind of memory property test macro and method based on the particle cluster algorithm parameters optimization.
Background technology
Along with the development of computing machine and information network, the especially large-scale distributed file system of distributed file system has obtained using widely.In order better to understand the advantage and the deficiency of different file system, obtain weighing the index of its performance by test.Present existing testing software and testing tool, all can effectively record the memory property of file system as IOZone, IOMeter etc., but all need artificially to be provided with fixing test parameter, if test the optimal value of a certain performance, can only be provided with repeatedly and test manual analysis test result then.Though some testing software can carry out automatic test, support to be provided with repeatedly a plurality of parameters of test, can't in test process, adjust test parameter flexibly and obtain optimum test result.
As disclosing a kind of storage server integrated test system for performance among the Chinese patent literature CN1588892A, comprise the test and management module and the load generation module that are arranged on the client computer, wherein the test and management module is responsible for being provided with test parameter, send test command to the load generation module, collect the test result data of load generation module, and will export control test overall process after the test result data sorting-out in statistics; The load generation module is used to create the I/O flowing of access, under the test and management module controls, transmits the I/O request message to storage server, and receives the response message that storage server returns.In this technical scheme, test parameter is set, sends test command, collects test result by the test and management module, the load generation module is carried out test, but obtain certain optimal performance index of system if desired, need a plurality of values be set to this parameter tests respectively, then test result is carried out manual analysis again, just can obtain optimum test parameter and test result.When system under test (SUT) has a plurality of test parameter, if all can there be very big influence in a plurality of test parameters to test result, the method that parameter and analytical test result seek the optimal value of test parameter and test result manually is set exists testing efficiency low, the problem that accuracy is not high, thereby influenced test result, improved testing cost.
Particle cluster algorithm also claims particle swarm optimization algorithm (Partical Swarm Optimization), is abbreviated as PSO, is a kind of new evolution algorithm that development in recent years is got up, and it takes a hint from the predation of simulation flock of birds, is used to solve optimization problem.Particle cluster algorithm belongs to a kind of of evolution algorithm, it is from RANDOM SOLUTION, seeks optimum solution by iteration, the quality of separating by fitness evaluation, to be particle follow optimum particle in solution space searches for, it by follow current search to optimal value seek global optimum.In particle cluster algorithm, separating of each optimization problem all is a bird in the search volume, and we are referred to as " particle ".All particles all have an adaptive value by the decision of optimised function, and each particle also has a speed to determine direction and the distance that they circle in the air, and particles are just followed current optimal particle and searched in solution space then.Particle cluster algorithm is initialized as a group random particles, finds optimum solution by iteration then.In iteration each time, particle upgrades oneself by following the tracks of two " extreme values ", and first is exactly the optimum solution that particle itself is found, and this is separated and is called individual extreme value pBest, another extreme value is the optimum solution that whole population is found at present, and this extreme value is global extremum gBest.This algorithm has realizes advantages such as easy, that precision is high, convergence is fast having superiority in solving practical problems.Particle cluster algorithm has been widely used in function optimization at present, neural metwork training, the application of fuzzy system control and other genetic algorithms.But, when particle cluster algorithm uses, need choose and set up the population model in conjunction with concrete condition, problem how to use particle cluster algorithm to solve in the practical application also is one of difficult problem that exists in the prior art.
Summary of the invention
For this reason, technical matters to be solved by this invention need in the prior art to be manually to be provided with the optimal value that test parameter, analytical test result obtain test parameter and test result, seeking optimal value under the situation of a plurality of test parameters exists testing efficiency low, the problem that accuracy is not high, thus propose a kind ofly can obtain the optimum test parameter of outfile system memory property and the memory property test macro and the method based on the particle cluster algorithm parameters optimization of test result fast and accurately.
For solving the problems of the technologies described above, a kind of memory property test macro of the present invention based on the particle cluster algorithm parameters optimization, comprise that test and management module, data acquisition module, population set up module, parameter optimization adjusting module, load testing module, test data analysis module, test result output module
The test and management module: the administration interface for the user provides man-machine interaction starts or stops test, imports a plurality of test parameters by described administration interface user;
Data acquisition module: gather, write down and put in order the described a plurality of test parameters of user, check whether described a plurality of test parameter is available, whether meet input rule by described test and management module input;
Population is set up module: analyze a plurality of test parameters of the input of described data acquisition module, be that particle makes up a population model with described a plurality of test parameters, and carry out initialization;
The parameter optimization adjusting module: obtain the state of each particle in the current population model earlier, then according to the optimal value that obtains in the described test data analysis module, according to particle swarm optimization algorithm, the parameter value of each particle when determining next time to test;
The load testing module: carry out test, the parameter value according to determining in the described parameter optimization adjusting module calls test procedure file system is tested, and outputs test result after test is finished;
Test data analysis module: the test result that receives described load testing module output, be analyzed with test result before, obtain result's optimal value, determine global optimum and local optimum, and the particle state in the record population model at this moment;
Test result output module: the net result after intermediate result that produces in the output test process and test are finished.
Also comprise the log information module, be used for the error message that recording system information and test process produce.
Described test and management module is provided with information in user's real time inspection test process, check test result, check the interface of log information.
A kind of storing performance testing method that uses described memory property test macro based on the particle cluster algorithm parameters optimization comprises the steps:
(1) obtains the test parameter of user's input by the test and management module, and described test parameter is passed to data acquisition module analyze and detect;
(2) set up module by population and utilize the result after the described data acquisition module block analysis to set up the population model, and carry out initialization in conjunction with particle swarm optimization algorithm;
(3) set up the state that init state in the module obtains each particle of population by the parameter optimization adjusting module according to population, determine the parameter value of testing;
(4) by the load testing module according to the parameter value of determining in the described parameter optimization adjusting module, call test procedure file system tested, output test result after test is finished;
(5) receive the test result that described load testing module is exported by the test data analysis module, be analyzed with test result before, obtain result's optimal value, if there is not test result before, think that then this test result is an optimal value, record particle state at this moment;
(6) the parameter optimization adjusting module is according to the data that write down in the test data analysis module in the described step (5), judge whether end condition is satisfied, if satisfy end condition then change step (7), if do not satisfy end condition, according to the optimal value that obtains in the test data analysis module in the described step (5), according to particle swarm optimization algorithm, the parameter value of each particle forwards step (4) to when determining to test next time;
(7) by intermediate result that produces and the net result of testing after finishing in the test result output module output test process.
In described step (6), the cycle index of end condition for setting.
In described step (6), end condition be the optimal value that tests out in the described step (5) and last time optimal value error less than error criterion.
Described error criterion is 2%-10%.
Also comprise the error message that produces by in log information module records system information and the test process in the described step.
The user by the information in the test and management module real time inspection test process, check test result, check log information.
In described step (5), described optimal value comprises global optimum and local optimum.
Technique scheme of the present invention has the following advantages compared to existing technology,
(1) the memory property test macro of particle cluster algorithm parameters optimization of the present invention, comprise the test and management module, data acquisition module, population is set up module, the parameter optimization adjusting module, the load testing module, the test data analysis module, test result output module, the user is by test and management module input test parameter, described test parameter is set up module by population and is set up the population model in conjunction with particle swarm optimization algorithm after the data acquisition module check and analysis, call parameters is optimized and revised module the population Model parameter is optimized adjustment then, call the performance of storage system test procedure by the load testing module according to the particle state in the population model again and carry out test, after test is finished the result is exported to described test data analysis module, described test data analysis module is analyzed test result, if do not satisfy end condition, then test parameter is optimized the adjustment back and begins to proceed test from parameter adjustment module according to test result, if satisfy termination condition, then stop test.In this technical scheme, particle swarm optimization algorithm is combined with the file system performance test, in the test process of file system, utilize particle swarm optimization algorithm to adjust parameter configuration automatically, analysis by test result between centering comes a plurality of parameters of test next time are optimized configuration, efficiently solve the problem of test macro best performance value under a plurality of test parameter situations, adopt this technical scheme on the basis of traditional measuring technology and instrument, to significantly improve testing efficiency, test process does not need manual intervention, eliminated the personal error in the test process, particularly under the situation of a plurality of parameters that influence test result, use particle swarm optimization algorithm can quick and precisely test out the optimum performance of system, help to save testing cost, improve reliability of testing result.
(2) the memory property test macro of particle cluster algorithm parameters optimization of the present invention, also comprise the log information module, be used for the error message that recording system information and test process produce, made things convenient for later searching and checking, condition is provided for pinpointing the problems and dealing with problems.
(3) the memory property test macro of particle cluster algorithm parameters optimization of the present invention, described test and management module is provided with information in user's real time inspection test process, check test result, check the interface of log information, for providing, the user checks the interface, convenient for users to use and safeguard, for the user provides friendly and practical interface.
(4) storing performance testing method based on the particle cluster algorithm parameters optimization of the present invention, realized the memory property test of parameter automatic optimization, compare with traditional test, parameter is carried out the adjustment of dynamic flexible, promoted testing efficiency greatly by particle swarm optimization algorithm.
(5) storing performance testing method based on the particle cluster algorithm parameters optimization of the present invention, end condition can be provided with as required, and end condition can be set to given cycle index, obtains optimal value by repeatedly circulating; End condition also can be set to the optimal value that tests out in the step (5) and last time optimal value error less than error criterion, if, then think and found optimal value, finish test less than the standard error that is provided with.End condition is provided with as required, has dirigibility and practicality.
(6) storing performance testing method based on the particle cluster algorithm parameters optimization of the present invention, described optimal value comprises global optimum and local optimum, optimize the population model by global optimum and local optimum, can better realize optimizing, obtain the best parameter setting.
Description of drawings
For the easier quilt of content of the present invention is clearly understood, below according to a particular embodiment of the invention and in conjunction with the accompanying drawings, the present invention is further detailed explanation, wherein
Fig. 1, Fig. 2 are the composition structural drawing of the memory property test macro based on the particle cluster algorithm parameters optimization of the present invention;
Fig. 3 is the process flow diagram of the storing performance testing method based on the particle cluster algorithm parameters optimization of the present invention;
Fig. 4 is to use the embodiment that tests bandwidth based on the storing performance testing method of particle cluster algorithm parameters optimization of the present invention;
Fig. 5 is to use test result of testing bandwidth based on the storing performance testing method of particle cluster algorithm parameters optimization of the present invention.
Embodiment
Provided a kind of memory property test macro of the present invention as shown in Figure 1 based on the particle cluster algorithm parameters optimization, comprise that test and management module, data acquisition module, population set up module, parameter optimization adjusting module, load testing module, test data analysis module, test result output module, wherein: the test and management module starts or stops test, imports a plurality of test parameters by described administration interface user for the administration interface that the user provides man-machine interaction; Data acquisition module is responsible for gathering, writing down and put in order the described a plurality of test parameters of user by described test and management module input, checks whether described a plurality of test parameter is available, whether meets input rule; Population is set up a plurality of test parameters of the input of the described data acquisition module of module analysis, is that particle makes up a population model with described a plurality of test parameters, and carries out initialization; The parameter optimization adjusting module is used for obtaining the state of each particle in the current population model, then according to the optimal value that obtains in the described test data analysis module, and according to particle swarm optimization algorithm, the parameter value of each particle when determining next time to test; The load testing module is responsible for carrying out test, and the parameter value according to determining in the described parameter optimization adjusting module calls test procedure file system is tested, and outputs test result after test is finished; The test data analysis module receives the test result of described load testing module output, be analyzed with test result before, obtain result's optimal value, determine global optimum and local optimum, and the particle state in the record population model at this moment; Test result output module is used for exporting test process intermediate result that produces and the net result of testing after finishing.
The method of testing of the memory property test macro correspondence based on the particle cluster algorithm parameters optimization of the present invention is as follows, its flow process as shown in Figure 3:
(1) obtains the test parameter that the user imports by the test and management module, and described test parameter is passed to data acquisition module analyze and detect, described data acquisition module is checked whether the test parameter of described input is available, whether is met input rule, if meet the input standard, then carry out next step, do not meet the input requirement, then point out and wait for that the user re-enters test parameter;
(2) set up module by population and utilize the result after the described data acquisition module block analysis to set up the population model, and carry out initialization in conjunction with particle swarm optimization algorithm;
(3) set up the state that init state in the module obtains each particle of population by the parameter optimization adjusting module according to population, determine the parameter value of testing;
(4) by the load testing module according to the parameter value of determining in the described parameter optimization adjusting module, call test procedure file system tested, output test result after test is finished;
(5) receive the test result that described load testing module is exported by the test data analysis module, be analyzed with test result before, obtain result's optimal value, described optimal value comprises global optimum and local optimum, if there is not test result before, think that then this test result is an optimal value, record particle state at this moment;
(6) the parameter optimization adjusting module is according to the data that write down in the test data analysis module in the described step (5), judge whether end condition is satisfied, if satisfy end condition then change step (7), if do not satisfy end condition, according to the optimal value that obtains in the test data analysis module in the described step (5), according to particle swarm optimization algorithm, the parameter value of each particle forwards step (4) to when determining to test next time;
(7) by intermediate result that produces and the net result of testing after finishing in the test result output module output test process, intermediate result is optimal value and its corresponding test parameter of each test result, final optimal value and its corresponding test parameter that net result obtains for test.
In the present embodiment, the end condition in the described step (6) be the optimal value A that tests out in the described step (5) and last time optimal value
Error less than error criterion, select 5% in this standard error, promptly
Between the 2%-10%.In addition, end condition herein also can be set to cycle index, after reaching certain cycle index, then finishes test, and the result who obtains in this process is a test result.
As embodiment that can conversion, the described in the above-described embodiments memory property test macro based on the particle cluster algorithm parameters optimization also comprises the log information module, be used for the error message that recording system information and test process produce, as shown in Figure 2, in addition, also be provided with information in user's real time inspection test process in described test and management module, check test result, check the interface of log information, for the user provides friendly use interface.
As Fig. 4, shown in Figure 5ly provided a test implementation example at bandwidth, adopt the gigabit Ethernet network, test parameter has test node quantity, data block size and transmission size etc., and test result is seen Fig. 5, the manual test method is pseudo-linear trend growth, but growth rate is slower; Test by using above-mentioned memory property test macro based on the particle cluster algorithm parameters optimization, test result is in rising trend substantially, just reach maximum aggregate bandwidth value the 14th iteration, tend to be steady thereafter, test result all is better than the manual test result in 16 tests.Testing time is few, can rapidly and efficiently find optimal value, compares with classic method, has not only improved testing efficiency, and has improved the accuracy of test.
Obviously, the foregoing description only is for example clearly is described, and is not the qualification to embodiment.For those of ordinary skill in the field, can also make other changes in different forms on the basis of the above description.Here need not also can't give exhaustive to all embodiments.And conspicuous variation of being extended out thus or change still are among the protection domain of the invention.
Claims (10)
1. memory property test macro based on the particle cluster algorithm parameters optimization, it is characterized in that: comprise that test and management module, data acquisition module, population set up module, parameter optimization adjusting module, load testing module, test data analysis module, test result output module
The test and management module: the administration interface for the user provides man-machine interaction starts or stops test, imports a plurality of test parameters by described administration interface user;
Data acquisition module: gather, write down and put in order the described a plurality of test parameters of user, check whether described a plurality of test parameter is available, whether meet input rule by described test and management module input;
Population is set up module: analyze a plurality of test parameters of the input of described data acquisition module, be that particle makes up a population model with described a plurality of test parameters, and carry out initialization;
The parameter optimization adjusting module: obtain the state of each particle in the current population model earlier, then according to the optimal value that obtains in the described test data analysis module, according to particle swarm optimization algorithm, the parameter value of each particle when determining next time to test;
The load testing module: carry out test, the parameter value according to determining in the described parameter optimization adjusting module calls test procedure file system is tested, and outputs test result after test is finished;
Test data analysis module: the test result that receives described load testing module output, be analyzed with test result before, obtain result's optimal value, determine global optimum and local optimum, and the particle state in the record population model at this moment;
Test result output module: the net result after intermediate result that produces in the output test process and test are finished.
2. the memory property test macro based on the particle cluster algorithm parameters optimization according to claim 1 is characterized in that: also comprise the log information module, be used for the error message that recording system information and test process produce.
3. the memory property test macro based on the particle cluster algorithm parameters optimization according to claim 1 and 2 is characterized in that: described test and management module is provided with information in user's real time inspection test process, check test result, check the interface of log information.
4. a storing performance testing method that uses the described memory property test macro based on the particle cluster algorithm parameters optimization of claim 1-3 is characterized in that, comprises the steps:
(1) obtains the test parameter of user's input by the test and management module, and described test parameter is passed to data acquisition module analyze and detect;
(2) set up module by population and utilize the result after the described data acquisition module block analysis to set up the population model, and carry out initialization in conjunction with particle swarm optimization algorithm;
(3) set up the state that init state in the module obtains each particle of population by the parameter optimization adjusting module according to population, determine the parameter value of testing;
(4) by the load testing module according to the parameter value of determining in the described parameter optimization adjusting module, call test procedure file system tested, output test result after test is finished;
(5) receive the test result that described load testing module is exported by the test data analysis module, be analyzed with test result before, obtain result's optimal value, if there is not test result before, think that then this test result is an optimal value, record particle state at this moment;
(6) the parameter optimization adjusting module is according to the data that write down in the test data analysis module in the described step (5), judge whether end condition is satisfied, if satisfy end condition then change step (7), if do not satisfy end condition, according to the optimal value that obtains in the test data analysis module in the described step (5), according to particle swarm optimization algorithm, the parameter value of each particle forwards step (4) to when determining to test next time;
(7) by intermediate result that produces and the net result of testing after finishing in the test result output module output test process.
5. storing performance testing method according to claim 4 is characterized in that: in described step (6), and the cycle index of end condition for setting.
6. storing performance testing method according to claim 4 is characterized in that: in described step (6), end condition be the optimal value that tests out in the described step (5) and last time optimal value error less than error criterion.
7. storing performance testing method according to claim 6 is characterized in that: described error criterion is 2%-10%.
8. according to claim 4 or 5 or 6 described storing performance testing methods, it is characterized in that: also comprise the error message that produces by in log information module records system information and the test process in the described step.
9. storing performance testing method according to claim 8 is characterized in that: the user by the information in the test and management module real time inspection test process, check test result, check log information.
10. according to claim 4 or 5 or 6 or 7 or 9 described storing performance testing methods, it is characterized in that: in described step (5), described optimal value comprises global optimum and local optimum.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010619704 CN102184746B (en) | 2010-12-31 | 2010-12-31 | Storage performance testing system and method based on particle swarm optimization parameter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010619704 CN102184746B (en) | 2010-12-31 | 2010-12-31 | Storage performance testing system and method based on particle swarm optimization parameter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102184746A true CN102184746A (en) | 2011-09-14 |
| CN102184746B CN102184746B (en) | 2013-03-20 |
Family
ID=44570908
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010619704 Expired - Fee Related CN102184746B (en) | 2010-12-31 | 2010-12-31 | Storage performance testing system and method based on particle swarm optimization parameter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102184746B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105893258A (en) * | 2016-03-31 | 2016-08-24 | 中电海康集团有限公司 | Performance optimizing method and tool based on artificial fish school algorithm |
| CN106649060A (en) * | 2015-11-02 | 2017-05-10 | 中国移动通信集团公司 | Equipment performance testing method and device |
| CN107884670A (en) * | 2017-12-28 | 2018-04-06 | 扬州华鼎电器有限公司 | The method of testing and its test system of a kind of single phase power transformer |
| CN108494602A (en) * | 2018-04-08 | 2018-09-04 | 上海鸿洛通信电子有限公司 | Method of adjustment, device and the intelligent terminal of OTA parameters |
| CN108877256A (en) * | 2018-06-27 | 2018-11-23 | 南京邮电大学 | Intersection based on wireless communication nearby disperses cooperative self-adapted cruise control method |
| CN109902069A (en) * | 2019-03-04 | 2019-06-18 | 重庆科技学院 | A kind of intelligent mathematical model stocking system and method |
| CN110326008A (en) * | 2017-04-26 | 2019-10-11 | 谷歌有限责任公司 | Machine learning is integrated into control system |
| CN114968828A (en) * | 2022-08-02 | 2022-08-30 | 树优(宁波)科技有限公司 | Performance test method, platform, equipment and storage medium for optimization algorithm |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1588892A (en) * | 2004-09-17 | 2005-03-02 | 华中科技大学 | Complex detecting system for storage server property |
| CN101090345A (en) * | 2007-07-20 | 2007-12-19 | 哈尔滨工程大学 | Performance test method for network storage system |
| CN101727394A (en) * | 2009-12-28 | 2010-06-09 | 成都市华为赛门铁克科技有限公司 | Method and device for testing performance of memory device |
-
2010
- 2010-12-31 CN CN 201010619704 patent/CN102184746B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1588892A (en) * | 2004-09-17 | 2005-03-02 | 华中科技大学 | Complex detecting system for storage server property |
| CN101090345A (en) * | 2007-07-20 | 2007-12-19 | 哈尔滨工程大学 | Performance test method for network storage system |
| CN101727394A (en) * | 2009-12-28 | 2010-06-09 | 成都市华为赛门铁克科技有限公司 | Method and device for testing performance of memory device |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649060A (en) * | 2015-11-02 | 2017-05-10 | 中国移动通信集团公司 | Equipment performance testing method and device |
| CN105893258A (en) * | 2016-03-31 | 2016-08-24 | 中电海康集团有限公司 | Performance optimizing method and tool based on artificial fish school algorithm |
| CN110326008A (en) * | 2017-04-26 | 2019-10-11 | 谷歌有限责任公司 | Machine learning is integrated into control system |
| US11809164B2 (en) | 2017-04-26 | 2023-11-07 | Google Llc | Integrating machine learning into control systems for industrial facilities |
| CN107884670A (en) * | 2017-12-28 | 2018-04-06 | 扬州华鼎电器有限公司 | The method of testing and its test system of a kind of single phase power transformer |
| CN107884670B (en) * | 2017-12-28 | 2023-11-03 | 扬州华鼎电器有限公司 | Testing method and testing system for single-phase power transformer |
| CN108494602A (en) * | 2018-04-08 | 2018-09-04 | 上海鸿洛通信电子有限公司 | Method of adjustment, device and the intelligent terminal of OTA parameters |
| CN108877256A (en) * | 2018-06-27 | 2018-11-23 | 南京邮电大学 | Intersection based on wireless communication nearby disperses cooperative self-adapted cruise control method |
| CN108877256B (en) * | 2018-06-27 | 2020-11-13 | 南京邮电大学 | Wireless communication-based method for controlling scattered cooperative self-adaptive cruise near intersection |
| CN109902069A (en) * | 2019-03-04 | 2019-06-18 | 重庆科技学院 | A kind of intelligent mathematical model stocking system and method |
| CN114968828A (en) * | 2022-08-02 | 2022-08-30 | 树优(宁波)科技有限公司 | Performance test method, platform, equipment and storage medium for optimization algorithm |
| CN114968828B (en) * | 2022-08-02 | 2022-11-04 | 树优(宁波)科技有限公司 | Performance test method, platform, equipment and storage medium for optimization algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102184746B (en) | 2013-03-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102184746B (en) | Storage performance testing system and method based on particle swarm optimization parameter | |
| CN101976221B (en) | Particle swarm taboo combination-based parallel test task dispatching method and platform | |
| CN108683560A (en) | A kind of performance benchmark test system and method for high amount of traffic processing frame | |
| CN107679146A (en) | The method of calibration and system of electric network data quality | |
| CN103294579A (en) | Method for testing high-performance computing cluster application performance | |
| CN106897833B (en) | New energy power distribution network reliability assessment method and device | |
| CN110727506B (en) | SPARK parameter automatic tuning method based on cost model | |
| CN110740079B (en) | Full link benchmark test system for distributed scheduling system | |
| CN101609416A (en) | Improve the method for performance tuning speed of distributed system | |
| CN109670714B (en) | Ship gas turbine comprehensive state evaluation method based on membership degree analysis | |
| CN102857560A (en) | Multi-service application orientated cloud storage data distribution method | |
| CN103617004A (en) | Tool and method for performing read-write tests on distributed file system | |
| CN113392029A (en) | Comprehensive performance testing device and method for different levels of container cloud platform | |
| CN112115029A (en) | Performance test method and device, computer equipment and computer readable storage medium | |
| CN108363660B (en) | Test program generation method and device | |
| CN109657197A (en) | A kind of pre-stack depth migration calculation method and system | |
| CN111767546B (en) | Deep learning-based input structure inference method and device | |
| CN111626896B (en) | Automatic acquisition and information management system for building engineering quality detection data | |
| CN102521135A (en) | Linear system test method and device | |
| CN113011559A (en) | Automatic machine learning method and system based on kubernets | |
| CN106484539A (en) | A kind of determination method of processor cache characteristic | |
| CN104714956A (en) | Comparison method and device for isomerism record sets | |
| Lu et al. | On the auto-tuning of elastic-search based on machine learning | |
| Liu et al. | Agent-based online quality measurement approach in cloud computing environment | |
| CN112784435B (en) | GPU real-time power modeling method based on performance event counting and temperature |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130320 Termination date: 20131231 |