• DocumentCode
    3349631
  • Title

    Implement of evolable hardware based improved genetic algorithm

  • Author

    Aifeng Ren ; Wei Zhao ; Shuo Tang ; Xin Tong ; Ming Luo

  • Author_Institution
    Sch. of Electron. Eng., Xidian Univ., Xi´an, China
  • Volume
    4
  • fYear
    2011
  • fDate
    26-28 July 2011
  • Firstpage
    2112
  • Lastpage
    2115
  • Abstract
    Evolvable Hardware (EHW) refers to hardware that can change its architecture and behavior dynamically and autonomously by interacting with its environment. The paper deals with an EHW completely developed on FPGA (Field Programmed Gate Array), with emphasis on the chromosome coding for hardware circuit and operation plat form of GA (Genetic Algorithm). A LUT-based VRC (virtual reconfigurable circuit) implementation of EHW is proposed in this article with the aim to find a general model fitter for evolving large scale circuit system. And a row-column dual decode architecture is adapt to speed up configuration. Moreover, its performance is illustrated with several concrete designs. All modules compilation and simulation are preformed by Altera Quartus II 10.0 and tested on DE2-115 Development Board. Finally, this article puts forward some questions which remain to be solved in the future design of EHW.
  • Keywords
    decoding; encoding; field programmable gate arrays; genetic algorithms; reconfigurable architectures; Altera Quartus II 10.0; DE2-115 development board; FPGA; LUT-based VRC; chromosome coding; evolvable hardware; field programmed gate array; genetic algorithm; hardware circuit; large scale circuit system; row-column dual decode architecture; virtual reconfigurable circuit; Biological cells; Field programmable gate arrays; Genetic algorithms; Hardware; Microprocessors; Table lookup; Chromosome Coding; Evolvable Hardware; Genetic Algorithm; Nios II;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Natural Computation (ICNC), 2011 Seventh International Conference on
  • Conference_Location
    Shanghai
  • ISSN
    2157-9555
  • Print_ISBN
    978-1-4244-9950-2
  • Type

    conf

  • DOI
    10.1109/ICNC.2011.6022550
  • Filename
    6022550