Improving Software Effort Estimation Models Using Grey Wolf Optimization Algorithm

One of the Software Development Life Cycle phases is planning the software project. Estimating the software effort is another task in this project planning phase. Software effort estimation is the method of determining how many workers are required to create a software project. Many researchers have focused on this field to increase the precision of software effort estimation and used both algorithmic and non-algorithmic techniques. The most widely used method is the Constructive Cost Model (COCOMO). However, the COCOMO model has a limitation related to the precision of the software effort estimation. Meta-heuristic algorithms are preferred with parameter optimization because they can provide nearly optimal solutions at a reasonable cost. This study aims to enhance the precision of effort estimation by modifying the three COCOMO-based models' coefficients and assess the efficiency of Grey Wolf Optimization (GWO) in finding the optimal value of effort estimation through applying four other algorithms, including Zebra Optimization (ZOA), Moth-Flame Optimization (MFO), Prairie Dog Optimization (PDO), and White Shark Optimization (WSO) with NASA18 dataset. These models include the basic COCOMO model, and another two models were also suggested in the published research as a modification of the basic COCOMO model. The six most used software effort estimation metrics are used to assess the performance of the proposed models. The results show high accuracy and significant error minimization of the GWO over other algorithms involving ZOA, MFO, PDO, WSO, and other existing models.