MOBAFS: A Multi Objective Bee Algorithm for Feature subset selection in Software Product Lines

TL;DR

This paper introduces MOBAFS, a multi-objective bee algorithm designed to efficiently select feature subsets in large-scale software product lines, outperforming existing methods in solution quality and diversity.

Contribution

The paper presents a novel multi-objective bee swarm optimization algorithm tailored for feature subset selection in large-scale software product lines, demonstrating superior performance over state-of-the-art methods.

Findings

MOBAFS outperforms SATIBEA in most solution quality indicators.

The method effectively handles large feature sets up to 6,888 features.

Results show improved diversity and solution quality in real-world cases.

Abstract

Software product line represents software engineering methods, tools and techniques for creating a group of related software systems from a shared set of software assets. Each product is a combination of multiple features. These features are known as software assets. So, the task of production can be mapped to a feature subset selection problem which is an NP-hard combinatorial optimization problem. This issue is much significant when the number of features in a software product line is huge. In this paper, a new method based on Multi Objective Bee Swarm Optimization algorithm (called MOBAFS) is presented. The MOBAFS is a population based optimization algorithm which is inspired by foraging behavior of honey bees. The is used to solve a SBSE problem. This technique is evaluated on five large scale real world software product lines in the range of 1,244 to 6,888 features. The proposed method is compared with the state-of-the-art, SATIBEA. According to results of three solution quality indicators and two diversity metrics, the proposed method, in most cases, surpasses the other algorithm.