Reliability modeling using Particle Swarm Optimization (original) (raw)
Related papers
Improving software reliability growth model selection ranking using particle swarm optimization
Journal of theoretical and applied information technology, 2017
Reliability of software always related to software failures and a number of software reliability growth models (SRGMs) have been proposed past few decades to predict software reliability. Different characteristics of SRGM leading to the study and practices of SRGM selection for different domains. Appropriate model must be chosen for suitable domain in order to predict the occurrence of the software failures accurately then help to estimate the overall cost of the project and delivery time. In this paper, particle swarm optimization (PSO) method is used to optimize a parameter estimation and distance based approach (DBA) is used to produce SRGM model selection ranking. The study concluded that the use of PSO for optimizing the SRGM's parameter has provided more accurate reliability prediction and improved model selection rankings. The model selection ranking methodology can facilitate a software developer to concentrate and analyze in making a decision to select suitable SRGM during testing phases.
Reliability Growth Modeling for Software Fault Detection Using Particle Swarm Optimization
2006 IEEE International Conference on Evolutionary Computation, 2006
Modeling the software testing process to obtain the predicted faults (failures) depends mainly on representing the relationship between execution time (or calendar time) and the failure count or accumulated faults. A number of unknown function parameters such as the mean failure function μ(t; β) and the failure intensity function λ(t; β) are estimated using either least-square or maximum likelihood estimation techniques. Unfortunately, the model parameters are normally in nonlinear relationships. This makes traditional parameter estimation techniques suffer many problems in finding the optimal parameters to tune the model for a better prediction. In this paper, we explore our preliminary idea in using Particle Swarm Optimization (PSO) technique to help in solving the reliability growth modeling problem. The proposed approach will be used to estimate the parameters of the well known reliability growth models such as the exponential model, power model and S-Shaped models. The results are promising.
Software Reliability Using Modified Particle Swarm Optimization
This paper present the Modified approaches of Particle Swarm Optimization (PSO) with Genetic Algorithm (GA). PSO and GA are Population based heuristic search technique which can be used tosolve the optimization problems modeled on the concept of Evolutionary Approach. In standard PSO, the non-oscillatory route can quickly cause a particle to stagnate and also it may prematurely converge on suboptimal solutions that are not even guaranteed to be local optimum. In this paper the modification strategies are proposed in PSO using GA. Experiment results are examined with benchmark functions and results show that the proposed modified PSO models outperform the standard PSO.
IEEE/CAA Journal of Automatica Sinica, 2019
This paper proposes an artificial neural network (ANN) based software reliability model trained by novel particle swarm optimization (PSO) algorithm for enhanced forecasting of the reliability of software. The proposed ANN is developed considering the fault generation phenomenon during software testing with the fault complexity of different levels. We demonstrate the proposed model considering three types of faults residing in the software. We propose a neighborhood based fuzzy PSO algorithm for competent learning of the proposed ANN using software failure data. Fitting and prediction performances of the neighborhood fuzzy PSO based proposed neural network model are compared with the standard PSO based proposed neural network model and existing ANN based software reliability models in the literature through three real software failure data sets. We also compare the performance of the proposed PSO algorithm with the standard PSO algorithm through learning of the proposed ANN. Statistical analysis shows that the neighborhood fuzzy PSO based proposed neural network model has comparatively better fitting and predictive ability than the standard PSO based proposed neural network model and other ANN based software reliability models. Faster release of software is achievable by applying the proposed PSO based neural network model during the testing period.
Performance Evaluation of Software Reliability Growth Models Using Optimization Techniques
Residual faults may degrade the performance of a software system. Recognizing and eliminating the remaining errors in software is a challenging task. The main objective is to analyse the SRGMs performance which helps in selecting a suitable software reliability growth model (SRGM) to forecast the reliability of computer product. This paper mainly focuses on performance evaluation of various SRGMs (i.e. Two-Dimensional S-shaped model, Yamada Rayleigh model, Huang Logistic model) using various modified versions of evolutionary algorithms namely Modified Particle Swarm Optimization (MPSO), Improved Artificial Bee Colony (IABC) algorithm, and Modified Cuckoo Search (MCS) algorithm. The model parameters are estimated using Logistic Exponential Testing Effort Function (LETEF). The experimental results are evaluated using RMSE criterion. To predict the reliability of a computer product many SRGMs were proposed in the literature. But, the traditional methods are not sufficient alone to enhance the reliability. Hence, Evolutionary algorithms are combined with SRGMs to improve the performance of an SRGM with test effort. The resultant improved SRGM model helpful in recognition of residual faults and reliability enhancement. This research is useful for test engineers and software managers in making decisions like when should stop testing, software release policies, and software cost estimation.
A Review on Parameter Estimation Techniques of Software Reliability Growth Models
International Journal of Computer Applications Technology and Research, 2014
Software reliability is considered as a quantifiable metric, which is defined as the probability of a software to operate without failure for a specified period of time in a specific environment. Various software reliability growth models have been proposed to predict the reliability of a software. These models help vendors to predict the behaviour of the software before shipment. The reliability is predicted by estimating the parameters of the software reliability growth models. But the model parameters are generally in nonlinear relationships which creates many problems in finding the optimal parameters using traditional techniques like Maximum Likelihood and least Square Estimation. Various stochastic search algorithms have been introduced which have made the task of parameter estimation, more reliable and computationally easier. Parameter estimation of NHPP based reliability models, using MLE and using an evolutionary search algorithm called Particle Swarm Optimization, has been explored in the paper.
Software quality prediction using random particle swarm optimization (PSO)
2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT), 2016
In this paper we have considered java based modules as a dataset for software quality prediction. The properties used are class, object, inheritance and dynamic behavior. The data modularity considered for this work is 1-10 and 11-20. First the data is arranged in the group and then it is tested based on chi-square test. Then we have calculated F-measure (FM), Power (PO) and Odd Ratio (OR) and find the parametric quality of software metrics. Then we have applied random particle swarm optimization for testing the optimized value and the obtained results found are improved.
2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT), 2016
This paper provides mathematical implications of software quality prediction using different software metrics and the optimized values are obtained by particle swarm optimization (PSO). Then the main focus of this research work is to find the final optimum score based on the previous software metrics used. Then we apply PSO for checking the optimized value based on the results obtained by the Fmeasure(FM), Odd ratio(OR) and Power(PO). We have applied random particle so that fixed biasness is removed through this algorithm. The algorithm used in our approach is shown below. The results are convincing and uniform in different iteration.
The Use of Cuckoo Search in Estimating the Parameters of Software Reliability Growth Models
This work aims to investigate the reliability of software products as an important attribute of computer programs; it helps to decide the degree of trustworthiness a program has in accomplishing its specific functions. This is done using the Software Reliability Growth Models (SRGMs) through the estimation of their parameters. The parameters are estimated in this work based on the available failure data and with the search techniques of Swarm Intelligence, namely, the Cuckoo Search (CS) due to its efficiency, effectiveness and robustness. A number of SRGMs is studied, and the results are compared to Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO) and extended ACO. Results show that CS outperformed both PSO and ACO in finding better parameters tested using identical datasets. It was sometimes outperformed by the extended ACO. Also in this work, the percentages of training data to testing data are investigated to show their impact on the results. https://sites.google.com/site/ijcsis/
Software reliability engineering has recently turned out to be an interesting research topic in the field of software engineering. For the purpose of reliability calculation of software, various software reliability models have been designed based on the application of software in particular fields. The ability of the particular model in estimating the failure rate, reliability, and cost of the software are the major requirement in reliability modeling since any sort of failure or fault in the software can make the entire system unreliable to perform the desired operation. This paper proposes an efficient software reliability growth model (SRGM) model selection for estimating the reliability of the software. The reliability model selection criteria are generally based on the improved computational time and better failure rates. The selection of the model is done by utilizing optimization techniques. Here we have used modified cuckoo search optimization and modified ABC in order to find the effectiveness of the reliability model. Using these optimization algorithms, we evaluate various measures of the reliability models and are compared with that of other models. Here two different optimization approaches are used since we can efficiently find the best model using these algorithms.