VIRUS BASED OPTIMIZATION ALGORITHMS

Abstract

ABSTRACT Software cost estimation is one of the most important activities for software project management and all the companies, today, are focusing on incorporating new techniques to minimize any risk. Among these, Constructive Cost Model (COCOMO) is the most widely used and accepted model due to its applicability in diverse stages of software Engineering. Traditional COCOMO, however, often lacks the precision and accuracy as the estimations are largely based on the parameters such as size of the project, cost drivers, coefficients etc and a small miscalculation can lead to vast difference in the estimated effort. Hence, scientists have been focusing on optimizing the COCOMO model using various meta-heuristic algorithms. In this paper, a novel meta-heuristic algorithm, Virus Optimization Algorithm (VOA), has been used to optimize the COCOMO model in order to minimize the error in the calculations and aid in proper budgeting for software projects. The performance of the proposed algorithm was investigated by comparing it to three other well-known software cost estimation models. The results showed that proposed work outperformed other algorithms in minimizing the Mean Magnitude of Relative Error while optimizing the COCOMO II model. Index Terms - VOA algorithm, Software Cost Estimation, COCOMO