Abstract —A genetic algorithm (GA) has several genetic operators that can be modified to improve the performance of particular implementations. These operators include parent selection, crossover and mutation. Selection is one of the important operations in the GA process. There are several ways for selection. This paper presents the comparison of GA performance in solving travelling salesman problem (TSP) using different parent selection strategy. Several TSP instances were tested and the results show that tournament selection strategy outperformed proportional roulette wheel and rank- based roulette wheel selections, achieving best solution quality with low computing times. Results also reveal that tournament and proportional roulette wheel can be superior to the rank- based roulette wheel selection for smaller problems only and become susceptible to premature convergence as problem size increases. Index Terms— Genetic algorithm, Selection, Travelling salesman problem, Optimization I. INTRODUCTION asic genetic algorithm (GA) is generally composed of two processes. The first process is selection of individuals for the production of the next generation and the second process is manipulation of the selected individuals to form the next generation by crossover and mutation techniques. The selection mechanism determines which individuals are chosen for mating (reproduction) and how many offspring each selected individual produces. The main principle of selection strategy is “the better is an individual; the higher is its chance of being parent.” Generally, crossover and mutation explore the search space, whereas selection reduces the search area within the population by discarding poor solutions. However, worst individuals should not be discarded and they have some chances to be selected because it may lead to useful genetic material. A good search technique must find a good trade-off between exploration and exploitation in order to find a global optimum [1]. Hence, it is important to find a balance between exploration (i.e. poor solutions must have chance to go to the next generation) and exploitation (i.e. good solutions go to the next generation more frequently than poor solutions) within the mechanism of the selection. Manuscript received March 6, 2011; revised March 21, 2011. This work was supported by the University Malaysia Pahang (UMP) in collaboration with Dublin City University, Ireland. Noraini Mohd Razali is with School of Mechanical & Manufacturing Engineering, Dublin City University, Ireland (e-mail: norainimbr@ump.edu.my). John Geraghty is with Enterprise Research Process Centre, Dublin City University, Ireland (e- mail: john.geraghty@dcu.ie). The different selection strategy used in the GA process will significantly affect the performance of the algorithm differently. This study is intended to examine the performance of GA when using different selection strategy specifically in solving the travelling salesman problem (TSP). TSP is a classical example of a NP-hard combinatorial optimization problem. Many production and scheduling problems can be reduced to a simple concept that there is a salesman who must travel from city to city, visiting each city exactly once and returning to the home city [2]. It is possible for the salesman to select the orders of the cities visited so that the total distances travelled in his tour is as small as possible which will apparently save him time and money [2]. Although TSP is conceptually simple, it is difficult to obtain an optimal solution. The main difficulty of this problem is the enormous number of possible tours; (n- 1)!/2 for symmetric n cities tour. As the number of cities in the problem increases, the numbers of permutations of valid tours are also increase. It is this factorial growth that makes the task of solving the TSP immense even for modest n sized problems. The remainder of this paper is organized as follows: Section II presents a brief summary of the previous works on selection strategy. Section III contains an overview of the genetic algorithm for TSP, while Section IV describes into more detail on selection strategy that used in the experiments. Section V tests the performance of GA and discusses the experimental results. The conclusions are summarized in Section VI. II. PREVIOUS WORK ON SELECTION STRATEGY Several researchers have studied the performance of GA using different selection strategy; yet almost none of them tested on TSP problem. The performance of GA is usually evaluated in terms of convergence rate and the number of generations to reach the optimal solution. Jadaan et al. [3] for example compared the results of GA between proportional roulette wheel and rank-based roulette wheel selection method using several mathematical fitness functions and found that rank-based outperformed proportional in number of generations to come out with the optimal solution. He observed that rank-based is steadier, faster, certainty and more robust towards the optimum solutions than proportional roulette wheel. On the other hand, Zhong et al. [4] compared proportional roulette wheel with tournament selection, with tournament size equal 6 at seven general test functions and concluded algorithm with the tournament selection is more efficient in convergence Genetic Algorithm Performance with Different Selection Strategies in Solving TSP Noraini Mohd Razali, John Geraghty B Proceedings of the World Congress on Engineering 2011 Vol II WCE 2011, July 6 - 8, 2011, London, U.K. ISBN: 978-988-19251-4-5 ISSN: 2078-0958 (Print); ISSN: 2078-0966 (Online) WCE 2011