Optimization with the use of the genetic algorithm method and parallel computing

2013;
: pp. 24-27
1
Poznań University of Technology

The work presents the description of a method for performing optimized calculations with the use of the genetic algorithm method performed on computers paralleled in a cluster. It defines the scope of electromagnetic calculations which must be performed in order to determine the objective function. It also provides sample factors describing the quality of paralleling the calculation process.

  1. K. Bednarek and L. Kasprzyk, “Speeding up of electromagnetic and optimization calculations by the use of the parallel algorithms”, Przegląd Elektrotechniczny, vol. 85 , no. 12, pp. 65 – 68, 2009.
  2. J. Jajczyk, “Optimization of the geometry of high currency busducts with solid insulation with the use of the modified genetic algorithm method”, PhD thesis, Poznan Univ. of Technology, Poland, 2008.
  3. J. A. Ramirez, R. R. Saldanha, R. H. C. Takahashi and J. A. Vasconcelos, “Improvements in Genetic Algorithms”, IEEE Transactions on Magnetics, vol. 37, no. 5, pp. 3414 – 3417, 2001.
  4. K. Skowronek and G. Trzmiel, “The method for identification of fotocell in real time”, Przegląd Elektrotechniczny, vol. 83, no. 11, pp.108–110, 2007.
  5. R. Wyrzykowski, PC computer clusters and multicore architectures: structure and use. Warszawa, Poland: Exit, 2009.
  6. D. B. Fogel, Evolutionary Computation: Toward a New Philosophy of Machine Intelligence. New Jersey, USA: IEEE Press/Wiley-Interscience, 2006.
  7. D. E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning. Massachusetts, USA: Addison-Wesley Publishing Company, 1989.
  8. G. Luque and E. Alba, Parallel Genetic Algorithms Theory and Real Word Applications. Berlin, Germany: Springer 2011.