PENGENDALIAN MUTATION RATE PADA ALGORITMA GENETIKA

Abstract

Genetic algorithm is heuristic searching algorithm which based on nature selection of mechanism and nature genetic. The
basic concept that inspires the genetic algorithm is that evolution theory. In the process of searching the best solution on
classic genetic algorithm often occurs optimum local. Optimum local is a common problem which is often occurs in genetic
algorithm, and one of the reasons is that because of the population diversity. If population diversity is too low is led to
optimum local, and if it is too high caused more times to look for the best solution. Mutation operator plays an important role
in the process of genetic algorithm to manage that population diversity and an important element of mutation operator is
mutation rate. On classic genetic algorithm that mutation rate is set in the beginning while the process of genetic algorithm
depends on how many generations are. Therefore is needed to control mutation rate in generation. Controlling mutation
operator, especially mutation rate based on Fuzzy Logic Controller (FLC) to manage population diversity, not too high or too
low, in order to get optimal result. Evaluation is done 10 times execution by comparing the performance of standard genetic
algorithm (GA), IAG and genetic algorithm based on Fuzzy Logic Controller (FLC) and experimental results show that there
is an improvement on genetic algorithm performance based on FLC.