کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
511442 865849 2007 15 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
AORCEA – An adaptive operator rate controlled evolutionary algorithm
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر نرم افزارهای علوم کامپیوتر
پیش نمایش صفحه اول مقاله
AORCEA – An adaptive operator rate controlled evolutionary algorithm
چکیده انگلیسی

When applying evolutionary algorithms to optimization problems many different strategy parameters have to be set to define the behavior of the evolutionary algorithm itself. To a certain extent these strategy parameter values determine whether the algorithm is capable of finding a near-optimum solution or not. In particular the choice of the different genetic operators and their relative rates is most often based on experience. Furthermore, the operator rates are defined before starting the optimization runs and remain unchanged until the stopping criterion is reached. Controlling the parameter values during the run has the potential of adjusting the algorithm to the problem while solving the problem. This paper investigates an adaptive strategy controlling the rates of arbitrary chosen genetic operators. The control mechanism is based on the state of the optimization by evaluating a success and a diversity measure for each operator. More efficient operators are favored in order to find better solutions with less evaluations. The algorithm is tested with constrained and unconstrained numerical examples and a concrete structural optimization problem is treated.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Computers & Structures - Volume 85, Issues 19–20, October 2007, Pages 1547–1561
نویسندگان
, , ,