Artificial intelligence education system based on feedback-adjusted differential evolution algorithm

Abstract

Abstract In order to build a high-quality artificial intelligence teaching system, based on the feedback adjustment differential evolution algorithm, this paper constructs an artificial intelligence teaching model based on machine learning, which aims to minimize the total cost of normalized network resources. Moreover, this paper abstracts the SFC mapping problem into an integer linear programming problem, which simplifies the SFC mapping solution process, and proposes a business-aware greedy search algorithm. At the same time, this paper takes into account factors such as the betweenness centrality of data center nodes in DC-EON and the maximum overlap between SFCs to complete VNF deployment, and this paper considers the bandwidth request of the virtual link, the route length and the betweenness centrality of the link to realize the link mapping. In addition, in order to improve the effectiveness of the algorithm solution, this paper designs a feedback-adjusted differential evolution operator to optimize the individuals in the population. Finally, this paper designs experiments to study the performance of the algorithm and the model. From the experimental results, it can be seen that the algorithm and model proposed in this paper basically meet expectations.