Dynamic cloud pricing for revenue maximization

DYNAMIC CLOUD PRICING FOR REVENUE MAXIMIZATION

ABSTRACT:

In cloud computing, a provider leases its computing resources in the form of virtual machines to users, and a price is charged for the period they are used. Though static pricing is the dominant pricing strategy in today’s market, intuitively price ought to be dynamically updated to improve revenue. The fundamental challenge is to design an optimal dynamic pricing policy, with the presence of stochastic demand and perishable resources, so that the expected long-term revenue is maximized. In this paper, we make three contributions in addressing this question. First, we conduct an empirical study of the spot price history of Amazon, and find that surprisingly, the spot price is unlikely to be set according to market demand. This has important implications on understanding the current market, and motivates us to develop and analyze market-driven dynamic pricing mechanisms. Second, we adopt a revenue management framework from economics, and formulate the revenue maximization problem with dynamic pricing as a stochastic dynamic program. We characterize its optimality conditions, and prove important structural results. Finally, we extend to consider a non-homogeneous demand model.

EXISTING SYSTEM:

Though static pricing is the dominant strategy today, dynamic pricing emerges as an attractive alternative to better cope with unpredictable customer demand. The motivation is intuitive and simple: pricing should be leveraged strategically to influence demand to better utilize unused capacity, and generate more revenue. Indeed, Amazon EC2 has introduced a “spot pricing” feature, where the spot price for a virtual instance is dynamically

updated to match supply and demand as claimed in.
DISADVANTAGES OF EXISTING SYSTEM:

v A provider naturally wishes to set a higher price to get a higher profit margin; yet in doing so, it also bears the risk of discouraging demand in the future.

v  It is nontrivial to balance this intrinsic tradeoff with perishable capacity and stochastic demand.

PROPOSED SYSTEM:

              Cloud computing poses new challenges to solving revenue maximization problems. First, little is known about how the spot price is adjusted, and what factors are considered in the pricing algorithm, by a real-world provider such as Amazon. Also, little is known about demand statistics, and how demand reacts to price changes. In fact, though Amazon publishes its spot price history, very few insights are gained on important aspects related to modeling of the market.

                   Second, for a cloud provider, revenue not only depends on the number of customers, but also on the duration of usage. Thus, not only the arrival but also the departure of demand is stochastic, and have to be taken into account when collecting revenue. This clearly adds to the modeling complexity.

                    we consider the scenario where the cloud provider with fixed capacity updates the spot price according to market demand in this paper. Our second contribution is that we formulate the revenue maximization problem as a finite-horizon stochastic dynamic program, with stochastic demand arrivals and departures. We characterize optimality conditions for the stochastic problem and prove important structural results.

 We also extend our model to the case with non-homogeneous

demand. We conduct an asymptotic analysis on this more general but difficult problem. We prove a surprising result that when the demand arrival and departure rates are linear with system utilization, i.e., number of existing instances, the optimal price is only a function of time and is independent of the system utilization.

ADVANTAGES OF PROPOSED SYSTEM:

v The optimal pricing policy exhibits time and utilization monotonicity, and the optimal revenue has a concave structure.

v The fundamental tradeoff between pricing to the future to attract more revenue from future demand, and pricing to the present to extract more revenue from existing customers.

SYSTEM CONFIGURATION:-

HARDWARE REQUIREMENTS:-

    ·       Processor         -       Pentium –IV

·       Speed                      -       1.1 Ghz

·       RAM                       -       512 MB(min)

·       Hard Disk                -       40 GB

·       Key Board               -       Standard Windows Keyboard

·       Mouse                     -       Two or Three Button Mouse

·       Monitor                   -       LCD/LED

 

SOFTWARE REQUIREMENTS:

·       Operating system    :       Windows XP.

·       Coding Language   :       C# .Net

·       Data Base                :       SQL Server 2005

·       Tool                        :       VISUAL STUDIO 2008.

REFERENCE:

Dynamic Cloud Pricing for Revenue Maximization

Hong Xu and Baochun Li, “DYNAMIC CLOUD PRICING FOR REVENUE MAXIMIZATION” IEEE TRANSACTION ON CLOUD COMPUTING, VOL. 1, NO. 1, DECEMBER 2013