An approach to the MOGAS initialization problem using an algorithm based on path relinking

This paper describes an approach to the initialization of Multi-Objective Genetic Algorithms (MOGA). The proposed approach inserts in the initial population some solutions that are already in the Pareto optimal front or near it. These are extreme solutions, and a set of conveniently spaced solutions in the Pareto optimal front, obtained by exact algorithms or heuristics over a mono-objective formulation of the problem. To complete the initial population, the algorithm constructs a path connecting these solutions using an algorithm based on PathRelinking. The performance of this boot approach is compared against the random initialization, the insertion of optimal or sub-optimal solutions without the use of the PathRelinking, and some initialization heuristics that are problem-specific. The results of the empirical comparison provide clear evidence that supports the conclusion that the proposed approach is better than the others in terms of overall effectiveness.

[1]  Enrique Alba,et al.  MOCell: A cellular genetic algorithm for multiobjective optimization , 2009, Int. J. Intell. Syst..

[2]  K. Miettinen,et al.  Quasi-random initial population for genetic algorithms , 2004 .

[3]  Lothar Thiele,et al.  Comparison of Multiobjective Evolutionary Algorithms: Empirical Results , 2000, Evolutionary Computation.

[4]  Yuanyuan Zhang,et al.  The multi-objective next release problem , 2007, GECCO '07.

[5]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[6]  El-Ghazali Talbi,et al.  Path Relinking in Pareto Multi-objective Genetic Algorithms , 2005, EMO.

[7]  Ronald L. Iman,et al.  A FORTRAN-77 PROGRAM AND USER'S GUIDE FOR THE GENERATION OF LATIN HYPERCUBE AND RANDOM SAMPLES FOR USE WITH COMPUTER MODELS , 1984 .

[8]  Padraig Cunningham,et al.  Using Case Retrieval to Seed Genetic Algorithms , 2001, Int. J. Comput. Intell. Appl..

[9]  Dipankar Dasgupta,et al.  On the use of informed initialization and extreme solutions sub-population in multi-objective evolutionary algorithms , 2009, 2009 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making(MCDM).

[10]  Anna Syberfeldt,et al.  Using Heuristic Search for Initiating the Genetic Population in Simulation-Based Optimization of Vehicle Routing Problems , 2009 .

[11]  DebK.,et al.  A fast and elitist multiobjective genetic algorithm , 2002 .

[12]  Bryant A. Julstrom.  Naive and heuristic permutation-coded genetic algorithms for the quadratic knapsack problem , 2012, GECCO '12.

[13]  Graham Kendall,et al.  Diversity in genetic programming: an analysis of measures and correlation with fitness , 2004, IEEE Transactions on Evolutionary Computation.

[14]  Yan Fu,et al.  The Effect of Initial Population Sampling on the Convergence of Multi-Objective Genetic Algorithms , 2009 .

[15]  Hisao Ishibuchi,et al.  Effects of Including Single-Objective Optimal Solutions in an Initial Population on Evolutionary Multiobjective Optimization , 2009, 2009 International Conference of Soft Computing and Pattern Recognition.