Optimization of Cluster Transportation Task Scheduling Based on Reinforced Genetic Algorithm

In the current highly intelligent environment, how to optimize the material distribution route with more intelligent and effective methods before the task starts to be executed to achieve better task allocation has become the key to reduce one's own cost and improve the rate of return, and it is also a major challenge. In order to solve this problem well, this paper proposes a reinforced genetic algorithm (RGA) which combines Levy flight and Q-learning reinforcement learning method to optimize the task scheduling scheme in the process of material distribution. The variant of the multi-traveling salesman problem is used as a model to test the performance of the algorithm. According to the experimental results, by introducing Q-learning to dynamically adjust the crossover and mutation probability, and introducing Levy flight strategy for auxiliary optimization, the proposed method can get the optimal solution more easily. Therefore, the proposed algorithm has excellent optimization ability and stability, and it is easier to get a reasonable task scheduling method when applied, and it can effectively reduce the distribution cost.