Abstract:
Background and Objective: Pricing in cloud computing environments assumes the same type of users and this constrains the performance and utilization of computing systems since requests are processed upon arrival even if they are delay-tolerant. The objective of this study was to model a pricing scheme in which cloud users who are not willing to tolerate any delay in the completion of their requests are charged using a standard pricing model in the cloud market and those cloud users who are willing to tolerate delay are charged lower prices at the expense of delaying packet completion time. Materials and Methods: To overcome the above challenge, this study proposed a pricing scheme that charges different prices for different users depending on the time sensitivity of the request. The proposed pricing scheme is modeled using a multiserver system which is treated as an M/Mi/m queueing system, where M stands for Markovian and represents arrivals that follow a Poisson distribution; Mi stands for Markovian service time that follows an exponential distribution with multiservers, m represents the number of servers. The performance of the differentiated pricing scheme was compared to the pricing scheme with no differentiation using MATLAB. Results: Numerical results show that the derived models can provide price differentiation resulting into delay tolerant packets paying less while the delay sensitive packets result in paying more. The price differentiation was more pronounced at high load and high arrival rate values. It was further observed that increase in load and arrival rate increased revenue. For low load and low arrival rate values price differentiation had little effect on revenue. Additionally, it is observed that the more the servers, the more the revenue generated. Conclusion: It was concluded that the proposed scheme provided differentiated pricing in which real time packets result in paying more with less delay and non real time packets result in paying less at the expense of delaying its packets.
