A comprehensive fuzz‐rule‐based self‐adaptive genetic algorithm

The purpose of this paper is to present a comprehensive self‐adaptive genetic algorithm (GA) based on fuzzy mechanism, aiming to improve both the optimizing capability and the convergence speed.

Many key factors that affect the performance of GAs are identified and analyzed, and their influences on the optimizing capability and the convergence speed are further elaborated, which prove to be very difficult to be described with explicit mathematical formulas. Therefore, a set of fuzzy rules are used to model these complicated relationships, in order to effectively guide the online self‐adaptive adjustments, such as changing the crossover and mutation probabilities, and thus to improve the optimizing capability and convergence speed.

Simulation results illustrates that, compared with a normal GA and another self‐adaptive GA based on explicit mathematical modeling of the key factors, the new GA is more advanced in terms of the optimizing capability and the convergence speed.

This paper develops a fuzzy‐rule‐based approach to describe the relationships between multiple GA parameters and online states, and the approach is useful in the design of a comprehensive self‐adaptive GA.