Implementation of hardware genetic algorithm | ||||
The International Conference on Electrical Engineering | ||||
Article 86, Volume 6, 6th International Conference on Electrical Engineering ICEENG 2008, May 2008, Page 1-14 PDF (887.87 K) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/iceeng.2008.34332 | ||||
View on SCiNiTO | ||||
Authors | ||||
Imbaby I. Mahmoud1; May Salama2; Asmaa Abdel Tawab1 | ||||
1Atomic Energy Auority, Cairo. | ||||
2Shobra Faculty of Engineering, Benha Univ. Cairo. | ||||
Abstract | ||||
Abstract: This work presents a hardware implementation of a Genetic Algorithm. Hardware Genetic Operators are implemented in FPGA. Fitness evaluation, which is problem dependent, is left for implementation as S/W module or problem specific hardware design. This allowed a re-configurable general-purpose design, which is customized by application specific population generation and fitness evaluation solution. A 16 site Random Number Generator module is implemented in VHDL based on Hybrid Cellular Automata (CA). Selection, Crossover, and Mutation Operators are implemented as systolic architecture. For preserving locality & modularity of systolic arrays we separate selection array implementation from the crossover and mutation operators. The chromosomes are fed serially to allow variable length chromosomes. The Genetic Engine is targeted a Xilinx Vertex XC2V2000-5 device using Xilinx Foundation Environment. The simulation is carried out using ModelSim. | ||||
Keywords | ||||
Genetic Algorithms; FPGA and VLSI design | ||||
Statistics Article View: 92 PDF Download: 118 |
||||