Optimal Cloud Service Pricing And Multi-server System Configuration For Profit Maximization In Cloud Computing

As an effective and efficient way to provide computing resources and services to customers on demand,cloud computing has become more and more popular.Moreover,as a business computing model,understanding the economics of cloud computing becomes critically important.From the perspective of cloud service provider,profit is the most concerned aspect and mainly determined by service charges and business costs under given market demand.To maximize the profit,service provider need to understand both constructs of service charges and business costs,and how they are determined by users demand distribution,the characteristics of the applications and the configuration of a multi-server system.This paper aims to solve the profit maximize problem which refers to optiml cloud service pricing and optimal multi-server configuration We modeled the profit maximize problem as follows.First,we proposed a pricing model which can be used to model users demand distribution based on users perceived value.Second,based on the delay sensitivity of users service requests,a MR(Monetary Reward)model is presented.At last,we proposed a services charge penalty model for the lower service quality.The multi-server system is treated as an M/M/m queuing model,and two power consumption mode are considered,namely,idle-speed mode and constant-speed mode.Moreover,this paper proposed a Dynamic Adaption Loop Control system(DALCS)model.The DALCS model can dynamically adapt to the change of market conditions.In the study of the research mentioned above,the profit maximize problem takes the following factors into account:the amounts of service,the sensitivity of a service,the workload of an application environment,the configuration of a multi-server system,the service-level agreement(SLA),the quality of service(QoS),the satisfaction of a consumer,the penalty of a low-quality service,the cost of renting of a multi-server system,the cost of energy consumption and the users dyamic demand distribution in market environments.The experimental results showed that the proposed pricing model meets users demand distnbution The optimal service price,optimal amounts and speed of multi-server system have obtained.Under various simulation conditions,the max profit in a unit time is higher than the existed research OMCPM and UPMR.