Differential evolution using homeostasis adaption based mutation operator and its application for software cost estimation

Among meta-heuristic algorithms, differential evolution (DE) is one of the most powerful nature-inspired algorithm used to solve the complex problems in various application areas. In DE algorithm at higher generations, there is an increase in the computational cost because existing mutation operator may not provide more diversity. In this paper, a new variant of DE has been proposed by incorporating the homeostasis adaption based mutation operator (HABMO), which maintains the diversity when it stuck to the local optimum problem. This operator with DE is applied for the cost estimation in software development, where proposed optimization technique is used with constructive cost model (COCOMO) for optimizing the tuning parameters. The main objective of this work is accurate prediction and minimization of the error like MMRE, MMER, MSE and RMSE in less number of iteration, for COCOMO model. Further, the proposed variant of DE has been compared with different versions of DE and it has been concluded that the proposed HABDE is able to improve the performance of DE algorithm. (c)& nbsp;2018 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

A new variant of differential evolution algorithm, which incorporates a homeostasis adaption based mutation operator, is proposed in this paper to improve the performance of DE algorithm for cost estimation in software development. The main objective of this algorithm is to accurately predict and minimize errors in fewer iterations to optimize tuning parameters.