Characteristics of genetic algorithm

Genetic algorithm is a general algorithm to solve search problems, which can be used in various general problems. The * * * characteristics of the search algorithm are:

① First, a set of candidate solutions is formed.

② Calculate the fitness of these candidate solutions according to some adaptation conditions.

③ According to the fitness, some candidate solutions are reserved and some candidate solutions are abandoned.

④ Perform some operations on the reserved candidate solutions to generate new candidate solutions.

In genetic algorithm, the above features are combined in a special way: parallel search based on genome, selection operation with guessing nature, exchange operation and mutation operation. This special combination distinguishes genetic algorithm from other search algorithms.

Genetic algorithm also has the following characteristics:

(1) Genetic algorithm starts from the string set of problem solutions, not from a single solution. This is a great difference between genetic algorithm and traditional optimization algorithm. The traditional optimization algorithm iteratively finds the optimal solution from a single initial value; It is easy to fall into the local optimal solution. Genetic algorithm starts from the set of character strings, which has a large coverage and is beneficial to global optimization.

(2) Genetic algorithm deals with multiple individuals in the population at the same time, that is, it evaluates multiple solutions in the search space, which reduces the risk of falling into the local optimal solution, and the algorithm itself is easy to achieve parallelism.

(3) Genetic algorithm basically does not need the knowledge of search space or other auxiliary information, only uses fitness function value to evaluate individuals, and then carries out genetic operation. The fitness function is not limited by continuously differentiable, and its definition domain can be set arbitrarily. This feature greatly expands the application scope of genetic algorithm.

(4) Genetic algorithm does not use deterministic rules, but uses probability transfer rules to guide its search direction.

(5) Have the habit of self-organization, self-adaptation and self-learning. When the genetic algorithm uses the information obtained in the evolution process to organize its own search, individuals with high fitness have higher survival probability and obtain more adaptive gene structure.

(6) In addition, the algorithm itself can also use dynamic adaptive technology to automatically adjust the control parameters and coding accuracy of the algorithm during the evolution process, such as using fuzzy adaptive method.