Research On Cloud Service Request Scheduling Based On User Consumption Characteristics

With the great development of new technologies including big data,5G,and edge computing,various industries have more urgent needs for digital transformation.Cloud services are spreading from the Internet industry to government,manufacturing,finance,retail,transportation,education and other fields.In the face of severe competition in the cloud service market,for cloud service providers whose goal is to make profits,the key issue that needs to be solved is how to design effective scheduling algorithms to maximize cloud service profits.Existing research on profit optimization of cloud services generally only discusses the level of cloud service operators,while ignoring the analysis of the level of cloud users.Therefore,although current research may expand the profit of cloud services temporarily,in the long run,these technologies may lead to a poor user experience due to a lack of understanding of users' consumption habits,and ultimately lead to user loss and lower profits.Therefore,in order to solve the above problems,this paper first subdivides users according to their historical consumption behavior,establishes user personalized pricing strategy combined with user evaluation model,and then proposes a scheduling algorithm based on genetic algorithm to improve cloud service profit.The main contributions of this article are as follows:1.This paper uses the RFM model to analyze the historical consumption behavior of cloud users,and proposes two methods to extract user consumption characteristics.This article is based on the RFM model to count the user's consumption indicators,and then divides the user value and extracts the user's consumption characteristics through the index segmentation method and the clustering method respectively.2.In this paper,combined with the user service evaluation model,a personalized pricing strategy is established.This paper uses statistical methods to estimate the evaluation scores of users with different consumption characteristics for a variety of service price-quality combinations,and then develops a personalized service request pricing strategy for cloud users based on the evaluation prediction model.3.This paper proposes a scheduling optimization algorithm based on improved genetic algorithm.This paper firstly defines the cloud service profit optimization problem formally,then introduces the genetic algorithm and the LSF algorithm,and then designs a service request scheduling mechanism based on the improved genetic algorithm to maximize profits while ensuring user evaluation scores.The experimental results show that the scheduling algorithm proposed in this paper has achieved a great enhancement in profit optimization in contrast with the other three scheduling schemes,.