Indonesian Journal of Electrical Engineering and Computer Science Vol. 28, No. 1, October 2022, pp. 306~314 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v28.i1.pp306-314  306 Journal homepage: http://ijeecs.iaescore.com A dynamic approach for parameter tuning in genetic algorithm using crossover and mutation ratios Mrinmoyee Chattoraj, Udaya Rani Vinayakamurthy School of Computing and Information Technology, REVA University, Bengaluru, India Article Info ABSTRACT Article history: Received Feb 25, 2022 Revised Jun 20, 2022 Accepted Jul 14, 2022 Genetic algorithm uses the natural selection process for any search process. It is an optimization process where integration among different vital parameters like crossover and mutation plays a major role. The parameters have an impact on the algorithm by their probabilities. In this paper we would review the different strategies used for the selection of crossover and mutation ratios and suggest a dynamic approach for modifying the ratios during runtime. We start with a mutation ratio 0% and crossover ratio 100% where the mutation ratio slowly increases and the crossover ratio decreases (MICD). The final mutation ratio will be 0% and crossover ratio will be 100% at the end of the search process. We also do the reverse process of considering the mutation ratio to be maximum and crossover ratio to be minimum and slowly decrease the mutation ratio and increase the crossover ratio (MDCI). We compare the proposed method with two pre-existing parameter tuning methods and found that this dynamic approach of incrementing the mutation and decrementing the crossover value was more effective when the size of the population was large. Keywords: Crossover ratio Genetic algorithm Mutation ratio Parameter control Parameter selection This is an open access article under the CC BY-SA license. Corresponding Author: Mrinmoyee Chattoraj School of Computing and Information Technology, REVA University Kattigenahalli Yelahanka, Bengaluru, India Email: mrinmoyee2005@gmail.com 1. INTRODUCTION Genetic algorithms are heuristics search algorithms which uses the technique of natural selection. It was developed by Holland in the year 1975 to solve optimization problems using evolutionary concepts of genetics [1]. Genetic algorithm is a nonlinear process which does not use any mathematical formula in order to reach the optimal solution but is an important tool to find out the optimal solution in the complex search spaces [2], [3]. Genetic algorithms are widely used by researchers in various fields such as computer network [4], image processing [5], machine learning [6]. In a traditional genetic algorithm, the process starts with a selection operator which chooses a set of individuals based on their fitness [7]. The offspring are produced from these individuals using the crossover and mutation operator and this process continues until a termination condition is reached [8]. The efficiency of the genetic algorithm is controlled basically by the size of the population, crossover and the mutation operator [9]. According to researchers it has been observed that the crossover and mutation operators plays a major role in increasing the performance of the genetic algorithms [10]. The selection and crossover operators help the genetic algorithm to converge to better solutions whereas the mutation operator helps to give the global optima by skipping the local search [11]. The values of these crossover and mutation parameter have an impact on the performance of the genetic algorithm i.e., crossover probability as 50% gives a different result when the crossover probability is changed to 100% [12], [13]. Similarly, the mutation probability also has an effect on the performance of