A Firefly Approach for Prioritizing Functional and Nonfunctional Requirements

Abstract

Abstract:The prioritization of requirements is an important task in software development to implement requirements based on budget, time, customer expectations and practical constraints. An Interactive Genetic Algorithm (IGA) has been used to prioritize requirements by satisfying constraints. IGA sometimes provides a poor ranking due to population divergence. This is resolved in this paper by utilizing Firefly algorithm. The methods for prioritizing both functional and non functional requirements together are very less and have several drawbacks like of considering a small number of non functional requirements and applying less ranking weight. The firefly algorithm provides random prioritization initially, then improves the prioritization iteratively by minimizing disagreement between priorities and constraints while maximizing agreement between priority and customer satisfaction. The sum of disagreement is considered as light intensity of firefly. The population of firefly generates an ordered list of functional and nonfunctional requirements. The fitness value (intensity) is found for all fireflies then each firefly updates its position towards the best search of a firefly until all fireflies obtain same fitness value. The experimental result proves that the firefly based prioritization outperforms than Genetic Algorithm based prioritization.