Profit Maximization for Cloud Broker in Cloud Computing

Abstract

As cloud computing evolves, more and more applications are moving to the cloud. Cloud brokers are are like Middlemen between cloud service providers and cloud users. Thus, cloud brokers can significantly reduce the cost of consumers. In addition to reducing the cost per user, the cloud broker can also accommodate the price difference between on-demand virtual machines and dedicated virtual machines. The problem with the current system is that if many customers request a large amount of cloud services at once, the cloud service broker cannot purchase enough cloud services from CSP to meet the needs of all customers. Then there is a peak demand problem where the customer cannot complete the job. As a result, dynamic conditions not only lead to financial problems, but can also negatively impact the customer experience. To solve this problem, the system focuses on guaranteed quality of service for all requests, reduces waste of resources, increases security and maximizes revenue. All jobs are scheduled by the job scheduler and assigned to different VMs in a centralized way. Many factors such as market demand, application volume, SLA, service rental cost, etc. are taken into account to formulate an optimal configuration problem of profit maximization.