Software Cost Estimation by Optimizing COCOMO Model Using Hybrid BATGSA Algorithm
Deepak Nandal, Om Prakash Sangwan · International journal of intelligent engineering and systems · 2018
This paper estimates the effort for software by optimizing the COnstructive COst MOdel (COCOMO) model parameters using hybrid BATGSA (Bat inspired Gravitational Search Algorithm) algorithm.The performance of the COCOMO model completely depends upon its parameters which can be optimized by using meta-heuristic algorithms.This paper uses hybrid BATGSA algorithm which hybrids the improved bat algorithm with the gravitation search algorithm (GSA) to optimize the COCOMO model.The bat algorithm demonstrates the hunting and routing behavior of the bat which is improved by using a random walk in the exploration phase.The exploration phase is further improved by using GSA as gravitation force affects the velocity of the bat.The algorithm has been analyzed on four NASA datasets downloaded from promise repository.The comparison of the algorithm has been made with existing three states of art techniques i.e.COCOMO model, BAT algorithm, Improved BAT(IBAT) algorithm by using normalized error as a parameter.The reduction in error ranges from 2% to 10% on different dataset as compared other state of art algorithms proves the significance of proposed algorithm.