Abstract

Software projects often suffer from unplanned overtime due to uncertainty and risk incurred due to changing requirement and attempt to meet up with time-to-market of the software product. This causes stress to developers and can result in poor quality. This paper presents a memetic algorithmic approach for solving the overtime-planning problem in software development projects. The problem is formulated as a three-objective optimization problem aimed at minimizing overtime hours, project makespan and cost. The formulation captures the dynamics of error generation and propagation due to overtime using simulation. Multi-Objective Shuffled Frog-Leaping Algorithm (MOSFLA) specifically designed for overtime planning is applied to solve the formulated problem. Empirical evaluation experiments on six real-life software project datasets were carried out using three widely used multi-objective quality indicators. Results showed that MOSFLA significantly outperformed the existing traditional overtime management strategies in software engineering projects in all quality indicators with 0.0118, 0.3893 and 0.0102 values for Contribution (IC), Hypervolume (IHV) and Generational Distance (IGD) respectively. The proposed approach also produced significantly better IHV and IGD results than the state of the art approach (NSGA-IIV ) in 100% of the project instances. However, the approach could only outperform NSGA-IIV in approximately 67% of projects instances with respect to IC. 

Authors (4)