scholarly journals A Demonstration of Modern Bayesian Methods for Assessing System Reliability with Multilevel Data and for Allocating Resources

2009 ◽  
Vol 2009 ◽  
pp. 1-10 ◽  
Author(s):  
Todd L. Graves ◽  
Michael S. Hamada
Keyword(s):  
Resource Allocation ◽  
Genetic Algorithms ◽  
Computational Methods ◽  
Test Data ◽  
Bayesian Methods ◽  
System Reliability ◽  
Information Sources ◽  
Expert Knowledge ◽  
Multilevel Data

Good estimates of the reliability of a system make use of test data and expert knowledge at all available levels. Furthermore, by integrating all these information sources, one can determine how best to allocate scarce testing resources to reduce uncertainty. Both of these goals are facilitated by modern Bayesian computational methods. We demonstrate these tools using examples that were previously solvable only through the use of ingenious approximations, and employ genetic algorithms to guide resource allocation.

scholarly journals A Recommender for Resource Allocation in Compute Clouds Using Genetic Algorithms and SVR

2019 ◽  
Author(s):  
Thiago Nelson Faria Dos Reis ◽  
Mário Antonio Meireles Teixeira ◽  
João Dallyson Sousa De Almeida ◽  
Anselmo Cardoso De Paiva
Keyword(s):  
Resource Allocation ◽  
Cloud Computing ◽  
Genetic Algorithms ◽  
Support Vector Regression ◽  
Support Vector

Alocação de recursos em Cloud Computing tem sido feito de forma reativa, dificultando garantias de serviço e gerando carga desnecessária de recursos ociosos. Para mitigar esses problemas, este trabalho propõe e avalia uma abordagem de alocação de recursos preditiva, implementado como um recomendador de configuração, com base em Support Vector Regression (SVR) e Algoritmos Genéticos (AG). Esta combinação é utilizada para estimar tempo de execução do aplicativo e recomenda uma configuração viável e válida de recursos na nuvem, sobre o tempo de execução e custos monetários. Como estudo de caso, as aplicações de aprendizagem de máquina com base na ferramenta Weka são escolhidos. Os resultados mostram que os tempos previstos foram muito perto dos reais, conseguindo uma estimativa eficiente de tempo e custo e sua consequente redução.

scholarly journals Software Test Data Generation based on Path Testing using Genetic Algorithms

2020 ◽  
Vol 8 (6) ◽  
pp. 4466-4473
Keyword(s):  
Genetic Algorithms ◽  
Test Data ◽  
Iterative Algorithms ◽  
Continuous Functions ◽  
Software Test ◽  
Test Cases ◽  
Test Data Generation ◽  
Data Generation ◽  
Optimal Solutions ◽  
Automated Test

Test data generation is the task of constructing test cases for predicting the acceptability of novel or updated software. Test data could be the original test suite taken from previous run or imitation data generated afresh specifically for this purpose. The simplest way of generating test data is done randomly but such test cases may not be competent enough in detecting all defects and bugs. In contrast, test cases can also be generated automatically and this has a number of advantages over the conventional manual method. Genetic Algorithms, one of the automation techniques, are iterative algorithms and apply basic operations repeatedly in greed for optimal solutions or in this case, test data. By finding out the most error-prone path using such test cases one can reduce the software development cost and improve the testing efficiency. During the evolution process such algorithms pass on the better traits to the next generations and when applied to generations of software test data they produce test cases that are closer to optimal solutions. Most of the automated test data generators developed so far work well only for continuous functions. In this study, we have used Genetic Algorithms to develop a tool and named it TG-GA (Test Data Generation using Genetic Algorithms) that searches for test data in a discontinuous space. The goal of the work is to analyze the effectiveness of Genetic Algorithms in automated test data generation and to compare its performance over random sampling particularly for discontinuous spaces.

AUTOMATIC PRODUCTION OF TEST DATA WITH A MULTIPLE BATCH-OPTIMISTIC METHOD

2009 ◽  
Vol 18 (01) ◽  
pp. 61-80 ◽  
Author(s):  
ANASTASIS A. SOFOKLEOUS ◽  
ANDREAS S. ANDREOU
Keyword(s):  
Genetic Algorithms ◽  
Software Testing ◽  
Test Data ◽  
Automatic Testing ◽  
Test Data Generation ◽  
Data Generation ◽  
Generation System ◽  
Automatic Production ◽  
Coverage Criterion ◽  
Testing Coverage

Recent research on software testing focuses on integrating techniques, such as computational intelligence, with special purpose software tools so as to minimize human effort, reduce costs and automate the testing process. This work proposes a complete software testing framework that utilizes a series of specially designed genetic algorithms to generate automatically test data with reference to the edge/condition testing coverage criterion. The framework utilizes a program analyzer, which examines the program's source code and builds dynamically program models for automatic testing, and a test data generation system that utilizes genetic algorithms to search the input space and determine a near to optimum set of test cases with respect to the testing coverage criterion. The performance of the framework is evaluated on a pool of programs consisting of both standard and random-generated programs. Finally, the proposed test data generation system is compared against other similar approaches and the results are discussed.

Components Map Generation of Gas Turbine Engine Using Genetic Algorithms and Engine Performance Deck Data

2006 ◽  
Vol 129 (2) ◽  
pp. 312-317 ◽  
Author(s):  
Changduk Kong ◽  
Jayoung Ki
Keyword(s):  
Experimental Data ◽  
Genetic Algorithms ◽  
Gas Turbine ◽  
Test Data ◽  
Engine Performance ◽  
Scaling Method ◽  
Turbine Engine ◽  
Scaling Methods ◽  
Map Generation ◽  
Component Map

In order to estimate the gas turbine engine performance precisely, the component maps containing their own performance characteristics should be used. Because the components map is an engine manufacturer’s propriety obtained from many experimental tests with high cost, they are not provided to the customer generally. Some scaling methods for gas turbine component maps using experimental data or data partially given by engine manufacturers had been proposed in a previous study. Among them the map generation method using experimental data and genetic algorithms had showed the possibility of composing the component maps from some random test data. However not only does this method need more experimental data to obtain more realistic component maps but it also requires some more calculation time to treat the additional random test data by the component map generation program. Moreover some unnecessary test data may introduced to generate inaccuracy in component maps. The map generation method called the system identification method using partially given data from the engine manufacturer (Kong and Ki, 2003, ASME J. Eng. Gas Turbines Power, 125, 958–979) can improve the traditional scaling methods by multiplying the scaling factors at design point to off-design point data of the original performance maps, but some reference map data at off-design points should be needed. In this study a component map generation method, which may identify the component map conversely from some calculation results of a performance deck provided by the engine manufacturer using the genetic algorithms, was newly proposed to overcome the previous difficulties. As a demonstration example for this study, the PW206C turbo shaft engine for the tilt rotor type smart unmanned aerial vehicle which has been developed by Korea Aerospace Research Institute was used. In order to verify the proposed method, steady-state performance analysis results using the newly generated component maps were compared with them performed by the Estimated Engine Performance Program deck provided by the engine manufacturer. The performance results using the identified maps were also compared with them using the traditional scaling method. In this investigation, it was found that the newly proposed map generation method would be more effective than the traditional scaling method and the methods explained above.

Sign in / Sign up

Export Citation Format

Share Document