Techniques for tuning systems generate configurations that are used to test the systems to determine optimal configurations for the systems. The configurations for a system are generated to allow for effective testing of the system while remaining within budgetary and/or resource constraints. The co
Techniques for tuning systems generate configurations that are used to test the systems to determine optimal configurations for the systems. The configurations for a system are generated to allow for effective testing of the system while remaining within budgetary and/or resource constraints. The configurations may be selected to satisfy one or more conditions on their distributions to ensure that a satisfactory set of configurations are tested. Machine learning techniques may be used to create models of systems and those models can be used to determine optimal configurations.
대표청구항▼
1. A computer-implemented method of determining system configurations, comprising: determining, by a computer system, a set of configurations for a system;measuring performance of the system for members of the determined set of configurations;creating, based at least in part on the measured performa
1. A computer-implemented method of determining system configurations, comprising: determining, by a computer system, a set of configurations for a system;measuring performance of the system for members of the determined set of configurations;creating, based at least in part on the measured performance, a model of the system;receiving, from a user, one or more user-specified objective functions, based at least in part on the model of the system;identifying one or more configurable parameters related to the system;identifying a relationship between the one or more configurable parameters;identifying at least one variable constraint related to the system based at least in part on the identified relationship;determining a valid set of values to be assigned to the one or more configurable parameters and the at least one variable constraint based at least in part on the identified relationship, wherein the value of the at least one variable constraint maps to the valid set of values assigned to the one or more configurable parameters;generating an optimal configuration of the system with respect to the one or more user-specified objective functions based at least in part on the model and the valid set of values assigned to the one or more configurable parameters and the at least one variable constraint; andproviding the generated optimal configuration for tuning the system. 2. The computer-implemented method of claim 1, further comprising tuning the system according to the optimal configuration. 3. The computer-implemented method of claim 2, further comprising: measuring one or more performance characteristics of the tuned system over a period of time;calculating, for the one or more performance characteristics, one or more predicted performance characteristics for the period of time; andproviding a display that compares the measured one or more performance characteristics with the calculated one or more predicted performance characteristics. 4. The computer-implemented method of claim 1, wherein determining the set of configurations includes: testing at least a first set of configurations for the system to determine a set of configuration constraints; andselecting the set of configurations consistent with the determined set of configuration constraints. 5. The computer-implemented method of claim 4, wherein selecting the set of configurations includes selecting the set of configurations to have a distribution that optimizes one or more distribution metrics. 6. The computer-implemented method of claim 1, wherein measuring performance of the system for each configuration includes: configuring the system with the configuration;simulating the configured system; andmeasuring one or more performance characteristics of the system. 7. A computing system for determining configurations for a system under test, comprising: one or more processors; andmemory including executable instructions that, when executed by the one or more processors, cause the computing system to implement at least:a configuration selector configured to select a set of configurations for the system under test;an application simulator configured to simulate the system under test under the selected set of configurations and provide, based at least in part on simulating the system under test, performance data for the system under test;a model creator configured to create, based at least in part on the provided performance data, a model of the system under test; anda model optimizer configured to:receive, from a user, one or more user-specified objective functions, based at least in part on the model of the system;identify one or more configurable parameters related to the system;identify a relationship between the one or more configurable parameters;identify at least one variable constraint related to the system based at least in part on the identified relationship;determine a valid set of values to be assigned to the one or more configurable parameters and the at least one variable constraint based at least in part on the identified relationship, wherein the value of the at least one variable constraint maps to the valid set of values assigned to the one or more configurable parameters; anddetermine an optimal configuration for the system under test that produces an optimal performance of the system with respect to the one or more user-specified objective functions based at least in part on the model and the valid set of values assigned to the one or more configurable parameters and the at least one variable constraint. 8. The computing system of claim 7, wherein the configuration selector includes a configuration validator configured to determine whether configurations are valid and wherein the configuration selector avoids selecting invalid configurations. 9. The computing system of claim 7, wherein the configuration selector includes a classification trainer configured to learn constraints for configurations and wherein the configuration selector selects the set of configurations consistent with the learned constraints. 10. The computing system of claim 7, wherein the configuration selector includes a configuration generator configured to generate valid configurations within a set of constraints and wherein the configuration selector selects the set of configurations from the generated valid configurations. 11. The computing system of claim 7, wherein the system under test is an application on a host. 12. The computing system of claim 7, wherein the configuration selector is configured to select the set of configurations in a manner optimizing one or more configuration distribution metrics. 13. One or more non-transitory computer-readable storage media having collectively stored thereon instructions executable by one or more processors to cause a computer system to at least: determine a set of configurations for the system;measure performance of the system for members of the determined set of configurations;create, based at least in part on the measured performance, a model of the system;receive, from a user, one or more user-specified objective functions, based at least in part on the model of the system;identify one or more configurable parameters related to the system;identify a relationship between the one or more configurable parameters;identify at least one variable constraint related to the system based at least in part on the identified relationship;determine a valid set of values to be assigned to the one or more configurable parameters and the at least one variable constraint based at least in part on the identified relationship, wherein the value of the at least one variable constraint maps to the valid set of values assigned to the one or more configurable parameters;generate an optimal configuration of the system with respect to the one or more user-specified objective functions based at least in part on the model and the valid set of values assigned to the one or more configurable parameters and the at least one variable constraint; andprovide the generated optimal configuration for tuning the system. 14. The one or more non-transitory computer-readable storage media of claim 13, wherein determining the set of configurations includes: testing at least a first set of configurations for the system to determine a set of configuration constraints; andselecting the set of configurations consistent with the determined set of configuration constraints. 15. The one or more non-transitory computer-readable storage media of claim 14, wherein determining the set of constraints includes obtaining a data set that indicates validity of each of the tested first set of configurations and wherein the set of configuration constraints is based at least in part on the obtained data set. 16. The one or more non-transitory computer-readable storage media of claim 14, wherein selecting the set of configurations includes selecting the set of configurations to have a distribution that optimizes one or more distribution metrics. 17. The one or more non-transitory computer-readable storage media of claim 13, wherein measuring performance of the system for each configuration includes: configuring the system with the configuration;simulating the configured system; andmeasuring one or more performance characteristics of the system. 18. The one or more non-transitory computer-readable storage media of claim 17, wherein simulating the configured system includes causing virtual users of the system to interact with the system. 19. The one or more non-transitory computer-readable storage media of claim 13, wherein the set of configurations is a proper subset of a set of possible configurations for the system. 20. The one or more non-transitory computer-readable storage media of claim 13, wherein each configuration comprises a plurality of configurable parameters of the system.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (26)
Chaudhuri, Surajit; Narasayya, Vivek R.; Symala, Manoj A., Application and database context correlation for database application developers.
Dolby Nigel I. (Ham Lake MN) Nagle Timothy E. (Bloomington MN) Goessling Thomas R. (Burnsville MN), Generalized configurator using a declaratively constructed two-level bi-partite graph as a knowledge representation.
Mehta,Ashish; Wojsznis,Peter; Wojsznis,Wilhelm K.; Blevins,Terrence L.; Thiele,Dirk; Ottenbacher,Ron; Nixon,Mark, Integrated model predictive control and optimization within a process control system.
Joseph C. Davis ; Karthik Vasanth ; Sharad Saxena ; Purnendu K. Mozumder ; Suraj Rao ; Chenjing L. Fernando ; Richard G. Burch, Method and system for using response-surface methodologies to determine optimal tuning parameters for complex simulators.
Diao, Yixin; Dyko, Denise Y.; Eskesen, Frank N.; Hellerstein, Joseph L.; Keller, Alexander; Spainhower, Lisa F., Methods and systems for model-based management using abstract models.
Keeton,Kimberly; Merchant,Arif; Wilkes,John, System and method for interposition-based selective simulation of faults for access requests to a data storage system.
Aravamudan, Murali; Ramakrishnan, Kajamalai G.; Barve, Rakesh; Venkataraman, Sashikumar; Rajasekharan, Ajit, User interface methods and systems for selecting and presenting content based on relationships between the user and other members of an organization.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.