1st International ICST Workshop on Knowledge Discovery and Data Mining

Research Article

Solving Constrained Optimization via a Modified Genetic Particle Swarm Optimization

  • @INPROCEEDINGS{10.4108/wkdd.2008.2663,
        author={Liu Zhiming and Wang Cheng and Li Jiang},
        title={Solving Constrained Optimization via a Modified Genetic Particle Swarm Optimization},
        proceedings={1st International ICST Workshop on Knowledge Discovery and Data Mining},
        publisher={ACM},
        proceedings_a={WKDD},
        year={2010},
        month={5},
        keywords={Particle swarm optimization genetic algorithm constrained optimization.},
        doi={10.4108/wkdd.2008.2663}
    }
    
  • Liu Zhiming
    Wang Cheng
    Li Jiang
    Year: 2010
    Solving Constrained Optimization via a Modified Genetic Particle Swarm Optimization
    WKDD
    ACM
    DOI: 10.4108/wkdd.2008.2663
Liu Zhiming1,2, Wang Cheng1, Li Jiang1,*
  • 1: Hubei Key Laboratory of Digital Valley Science and Technology, Huazhong University of Science & Technology.
  • 2: Hubei University of Education, Wuhan, Hubei 430074, China.
*Contact email: Leejan4ever@gmail.com

Abstract

The genetic particle swarm optimization (GPSO) was derived from the original particle swarm optimization (PSO), which is incorporated with the genetic reproduction mechanisms, namely crossover and mutation. Based on which a modified genetic particle swarm optimization (MGPSO) was introduced to solve constrained optimization problems. In which the differential evolution (DE) was incorporated into GPSO to enhance search performance. At each generation GPSO and DE generated a position for each particle, respectively, and the better one was accepted to be a new position for the particle. To compare and ranking the particles, the lexicographic order ranking was introduced. Moreover, DE was incorporated to the original PSO with the same method, which was used to be compared with MGSPO. MGPSO were experimented with wellknown benchmark functions. By comparison with original PSO algorithms and the evolution strategy, the simulation results have shown its robust and consistent effectiveness.