Parameters Tuning of Adaptive Firefly Algorithm based Strategy for t-way Testing

The adaptive firefly algorithm (AFA) is developed based on an elitism operator. Elitism operators can perform the function of updating the effectiveness of diversification in a search algorithm. In this study, a strategy was proposed to upgrade the FA concerning static issues. Most traditionally, for evolutionary algorithms, elitism suggests that the best solution found is utilized to work for the next generation. Elitism involves the replication of a small set of the fittest candidate solutions, which remain unaltered, into succeeding generations. The condition can radically impact execution time by ensuring that the El waste no time on re-finding newly-disposed partial solutions. Candidates who stay protected and unmodified via elitism all meet the requirements for parent selection in terms of rearing the remainder of the succeeding generation. This study used different tuning parameters, such as the number of fireflies, iterations and switching probability. To ensure that AFA could perform for t-way testing as useful as other strategies to generate the best performance. Considering the standard covering array (N, 2, ) it demonstrates the tuning parameters for AFA to improve elitism. In this paper, the Findings show that AFA, as well as t-way testing, can deliver the minimum requirements and sufficient results