On the Asymptotic Behavior of Adaptive Testing Strategy for Software Reliability Assessment

In software reliability assessment, one problem of interest is how to minimize the variance of reliability estimator, which is often considered as an optimization goal. The basic idea is that an estimator with lower variance makes the estimates more predictable and accurate. Adaptive Testing (AT) is...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on software engineering 2014-04, Vol.40 (4), p.396-412
Main Authors: Lv, Junpeng, Yin, Bei-Bei, Cai, Kai-Yuan
Format: Article
Language:English
Subjects:
Adaptive testing
Aircraft
Assessments
Asymptotic methods
Asymptotic properties
Effectiveness studies
Estimating techniques
Estimators
Global Positioning System
operational profile
Optimization
Optimization techniques
Reliability theory
Sensitivity analysis
Simulation
Software
Software reliability
Strategy
Testing
testing strategy
Variance
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In software reliability assessment, one problem of interest is how to minimize the variance of reliability estimator, which is often considered as an optimization goal. The basic idea is that an estimator with lower variance makes the estimates more predictable and accurate. Adaptive Testing (AT) is an online testing strategy, which can be adopted to minimize the variance of software reliability estimator. In order to reduce the computational overhead of decision-making, the implemented AT strategy in practice deviates from its theoretical design that guarantees AT's local optimality. This work aims to investigate the asymptotic behavior of AT to improve its global performance without losing the local optimality. To this end, a new AT strategy named Adaptive Testing with Gradient Descent method (AT-GD) is proposed. Theoretical analysis indicates that AT-GD, a locally optimal testing strategy, converges to the globally optimal solution as the assessment process proceeds. Simulation and experiments are set up to validate AT-GD's effectiveness and efficiency. Besides, sensitivity analysis of AT-GD is also conducted in this study.
ISSN:0098-5589
1939-3520
DOI:10.1109/TSE.2014.2310194