GPU Accelerated Genetic Algorithm with Sequence-based Clustering for Ordered Problems

The island model allows genetic algorithms to effectively maintain diversity through migration between multiple independent populations. Due to its flexibility and modularity, it is commonly employed in distributed and parallel implementations, particularly in recent trends in leveraging the massively parallel cores in GPUs. However, the efficiency and effectiveness of the island model can be considered as its ability to manage its global and local search while minimising the overlap of islands searching in the same area of the solution space. This paper introduces a GPU accelerated island-model genetic algorithm that conducts global search by organising its populations into islands according to the similarity in genotype sequences. Local search is managed through adaptive mechanisms designed to maintain population diversity. The characteristics of the proposed genetic algorithm are investigated with encouraging results demonstrating its robustness and scalability when solving ordered optimisation problems.

[1]  Edmund K. Burke,et al.  The Multi-Funnel Structure of TSP Fitness Landscapes: A Visual Exploration , 2015, Artificial Evolution.

[2]  K. Dejong,et al.  An analysis of the behavior of a class of genetic adaptive systems , 1975 .

[3]  Jirí Jaros,et al.  Multi-GPU island-based genetic algorithm for solving the knapsack problem , 2012, 2012 IEEE Congress on Evolutionary Computation.

[4]  Md. Saiful Islam,et al.  LCS Based Diversity Maintenance in Adaptive Genetic Algorithms , 2018, AusDM.

[5]  Gabriela Ochoa,et al.  Comparing communities of optima with funnels in combinatorial fitness landscapes , 2017, GECCO.

[6]  Qingfu Zhang,et al.  Distributed evolutionary algorithms and their models: A survey of the state-of-the-art , 2015, Appl. Soft Comput..

[7]  Huiqing Wang,et al.  A Genetic Spectral Clustering Algorithm , 2011 .

[8]  Chu-Hsing Lin,et al.  Parallel genetic algorithms on the graphics processing units using island model and simulated annealing , 2017 .

[9]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[10]  Darrell Whitley,et al.  The Island Model Genetic Algorithm: On Separability, Population Size and Convergence , 2015, CIT 2015.

[11]  Fearghal Morgan,et al.  Maintaining Healthy Population Diversity Using Adaptive Crossover, Mutation, and Selection , 2011, IEEE Transactions on Evolutionary Computation.

[12]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[13]  Rasmus K. Ursem,et al.  Multinational GAs: Multimodal Optimization Techniques in Dynamic Environments , 2000, GECCO.

[14]  Irene Moser,et al.  A Systematic Literature Review of Adaptive Parameter Control Methods for Evolutionary Algorithms , 2016, ACM Comput. Surv..

[15]  Mitsuo Gen,et al.  Accelerating genetic algorithms with GPU computing: A selective overview , 2019, Comput. Ind. Eng..

[16]  Jean Perron,et al.  A Selection Process for Genetic Algorithm Using Clustering Analysis , 2017, Algorithms.

[17]  Marco Laumanns,et al.  SPEA2: Improving the strength pareto evolutionary algorithm , 2001 .

[18]  Gabriela Ochoa,et al.  Mapping the global structure of TSP fitness landscapes , 2017, J. Heuristics.

[19]  Md. Saiful Islam,et al.  AMGA: An Adaptive and Modular Genetic Algorithm for the Traveling Salesman Problem , 2018, ISDA.

[20]  Paul J. Kennedy,et al.  Dynamic island model based on spectral clustering in genetic algorithm , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[21]  Kenneth Alan De Jong,et al.  An analysis of the behavior of a class of genetic adaptive systems. , 1975 .

[22]  El-Ghazali Talbi,et al.  GPU-based island model for evolutionary algorithms , 2010, GECCO '10.

[23]  Jonatan Gómez Perdomo,et al.  Self-adaptation of genetic operators through genetic programming techniques , 2017, GECCO.

[24]  Peter C. Nelson,et al.  An explorative and exploitative mutation scheme , 2010, IEEE Congress on Evolutionary Computation.

[25]  Franz Rothlauf,et al.  Communities of Local Optima as Funnels in Fitness Landscapes , 2016, GECCO.

[26]  Patrick Siarry,et al.  A survey on optimization metaheuristics , 2013, Inf. Sci..

[27]  Gabriela Ochoa,et al.  Deconstructing the Big Valley Search Space Hypothesis , 2016, EvoCOP.

[28]  Chu-Hsing Lin,et al.  On the Accelerated Convergence of Genetic Algorithm Using GPU Parallel Operations , 2015, Int. J. Softw. Innov..

[29]  Md. Saiful Islam,et al.  A Distributed Genetic Algorithm with Adaptive Diversity Maintenance for Ordered Problems , 2019, 2019 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT).

[30]  Yuanan Liu,et al.  Balanced-evolution genetic algorithm for combinatorial optimization problems: the general outline and implementation of balanced-evolution strategy based on linear diversity index , 2018, Natural Computing.