Application of Improved Genetic Algorithm in Vehicle Networked Cloud Data Platform

Under the car networking user group, the traditional cloud computing data scheduling mostly adopts the algorithm of generating initial data by randomization and the fitness function of single indicator. This can not meet the diverse needs of front-end users and the effective use of background resources, resulting in low user satisfaction and inefficient operation of the algorithm. In order to solve this problem, this paper proposes an improved genetic algorithm model that uses population matching function to initialize population and user QoS model to construct fitness function of genetic algorithm. In this paper, the balance algorithm of the front-end user and back-end server resources is designed creatively, so that the optimal solution can meet the needs of the front and rear end. The experimental results show that the improved algorithm is superior to the traditional genetic algorithm and min-min algorithm in the implementation efficiency, system load balancing and user satisfaction of the application layer of car networking, which is an efficient task scheduling algorithm.