Improved Genetic Algorithm Based Design for Controlling Big Data Discrimination Paths

An improved genetic algorithm is proposed to address the problems of slow population evolution, low convergence speed, and long optimal paths that occur when the traditional genetic algorithm solves the path planning problem under the sampling point model of big data discrimination control path. In the improved genetic algorithm, in order to improve the quality of the initial population of the big data discrimination control path, the initialization method based on panel data is used to generate the initial population; the population quality of the improved big data discrimination control path is significantly improved under the sampling point panel data model; in order to solve the problem of the lack of directionality of the traditional genetic algorithm in selecting mutation nodes of the big data discrimination control path, and the mutation effect is not In order to solve the problem that the traditional genetic algorithm lacks direction when selecting the mutation nodes of the big data discrimination control path, and the mutation effect is not controllable, which even leads to the degradation of the quality of the obtained path, a big data discrimination control path goal-oriented mutation operator is proposed. It makes the selection of mutation nodes of big data discrimination control path more directional, and the quality of the obtained big data discrimination control path is better, thus improving the convergence speed of the algorithm.