A NEW SERVICE MECHANISM FOR PROFITOPTIMIZATIONS OF A CLOUD PROVIDER AND ITS USERS
ABSTRACT
In this paper, we try to design a service mechanism for profit optimizations of both a cloud provider and its multiple users.Weconsider the problem from a game theoretic perspective and characterize the relationship between the cloud provider and its multipleusers as a Stackelberg game, in which the strategies of all users are subject to that of the cloud provider. The cloud provider triesto select and provision appropriate servers and configure a proper request allocation strategy to reduce energy cost while satisfyingits cloud users at the same time. We approximate its servers selection space by adding a controlling parameter and configure anoptimal request allocation strategy. For each user, we design a utility function which combines the net profit with time efficiency andtry to maximize its value under the strategy of the cloud provider. We formulate the competitions a all users as a generalizedNash equilibrium problem (GNEP). We solve the problem by employing variational inequality (VI) theory and prove that there exists ageneralized Nash equilibrium solution set for the formulated GNEP. Finally, we propose an iterative algorithm (IA), which characterizesthe whole process of our proposed service mechanism. We conduct some numerical calculations to verify our theoretical analyses.The experimental results show that our IA algorithm can benefit both of a cloud provider and its multiple users by configuring properstrategies.
EXISTING SYSTEM:
Some works have been done for profit optimizations ofcloud centers in the literature. Themethods are presented. In, Lampe et al.proposed a heuristic method to tackle profit maximizationfor a cloud provider. They focus on auction profitmaximization in the context of multiple virtual machines(VMs). In, Goudarzi and Pedram developeda heuristic to deal with profit maximization in cloudcomputing system with service level agreements. Theytry to reduce cost by powering off appropriate servers,i.e., selecting appropriate servers to provide services.More recently, Cao et al.proposed an optimal methodfor energy saving under continuous dynamic voltagefrequency scaling (DVFS) environment. Specifically, theytry to configure appropriate speed for each server tosave energy. However, as shown in Table 1, all thesemethods mainly consider from the perspective of thecloud provider.To our knowledge, hardly any previous works investigatemultiple users′ profit optimizations, let alone optimizingthe profits of a cloud provider and its users at thesame time. In this work, we first try to optimize multipleusers′ profits. Since multiple cloud users compete forusing the resources of a cloud provider, and the utilityof each user is affected by the decisions (service requeststrategies) of other users, it is natural to analyze thebehaviors of such systems as strategic games
PROPOSED SYSTEM:
In this paper, we try to design a new service mechanismfor profit optimizations of both a cloud provider andits multiple users. We consider the problem from a gametheoretic perspective and characterize the relationshipbetween the cloud provider and its users as a Stackelberggame, in which the strategies of all users are subject tothat of the cloud provider. In our mechanism, the cloudprovider tries to select appropriate servers and configurea proper request allocation strategy to reduce energy costwhile satisfying its users at the same time.The main contributions of this paper are listed asfollows.• We characterize the relationship between the cloudprovider and its users as a Stackelberg game, andtry to optimize the profits of both a cloud providerand its users at the same time.• We formulate the competitions a all users as ageneralized Nash equilibrium problem (GNEP), andprove that there exists a generalized Nash equilibriumsolution set for the formulated GNEP.• We solve the GNEP by employing varational inequality(VI) theory and propose an iterative algorithm(IA) to characterize the whole process of ourproposed service mechanism.
CONCLUSIONS AND FUTURE WORK
With the popularization of cloud computing and itsmany advantages such as cost-effectiveness, elasticity,and scalability, more and more applications are movedfrom local computing environment to cloud center. Inthis work, we try to design a new service mechanismfor profit optimizations of both a cloud provider and itsmultiple users.We consider the problem from a game theoretic perspectiveand characterize the relationship between thecloud provider and its multiple users as a Stackelberggame, in which the strategies of all users are subjectto that of the cloud provider. The cloud provider triesto select appropriate servers and configure a properrequest allocation strategy to reduce energy cost whilesatisfying its cloud users at the same time. We approximateits server selection space by adding a controllingparameter and configure an optimal request allocationstrategy. For each user, we design a utility functionwhich combines the net profit with time efficiency andtry to maximize its value under the strategy of the cloudprovider. We formulate the competitions a all usersas a generalized Nash equilibrium problem (GNEP). Wesolve the problem by employing varational inequality(VI) theory and prove that there exists a generalizedNash equilibrium solution set for the formulated GNEP.Finally, we propose an iterative algorithm (IA), whichcharacterizes the whole process of our proposed servicemechanism. We conduct some numerical calculations toverify our theoretical analyses. The experimental resultsshow that our IA algorithm can reduce energy cost andimprove users utilities to certain extent by configuringproper strategies.As part of future work, we will study the cloudcenter choice a multiple different cloud providersor determine a proper mixed choice strategy. Another directionis the opposite, we consider problem from cloudproviders and study the competitions a multiplecloud providers, which may incorporate charge price,service quality, and so on.
REFERENCES
[1] A. Prasad and S. Rao, “A mechanism design approach to resourceprocurement in cloud computing,” Computers, IEEE Transactionson, vol. 63, no. 1, pp. 17–30, Jan 2014.
[2] R. Pal and P. Hui, “Economic models for cloud service markets:Pricing and capacity planning,” Theoretical Computer Science, vol.496, no. 0, pp. 113 – 124, 2013.
[3] P. D. Kaur and I. Chana, “A resource elasticity framework forqos-aware execution of cloud applications,” Future GenerationComputer Systems, vol. 37, no. 0, pp. 14 – 25, 2014.
[4] L. Duan, D. Zhan, and J. Hohnerlein, “Optimizing cloud datacenter energy efficiency via dynamic prediction of cpu idle intervals,”in 2015 IEEE 8th International Conference on Cloud Computing.IEEE, 2015, pp. 985–988.
[5] Z. Li, J. Ge, H. Hu, W. Song, H. Hu, and B. Luo, “Cost and energyaware scheduling algorithm for scientific workflows with deadlineconstraint in clouds,” IEEE Transactions on Services Computing,2015, doi: 10.1109/TSC.2015.2466545.
[6] A. Greenberg, J. Hamilton, D. A. Maltz, and P. Patel, “The costof a cloud: research problems in data center networks,” ACMSIGCOMM computer communication review, vol. 39, no. 1, pp. 68–73, 2008.
[7] J. Cao, K. Hwang, K. Li, and A. Zomaya, “Optimal multiserverconfiguration for profit maximization in cloud computing,” Paralleland Distributed Systems, IEEE Transactions on, vol. 24, no. 6,pp. 1087–1096, June 2013.
[8] Y. Feng, B. Li, and B. Li, “Price competition in an oligopoly marketwith multiple iaas cloud providers,” Computers, IEEE Transactionson, vol. 63, no. 1, pp. 59–73, Jan 2014.
[9] J. Cao, K. Li, and I. Stojmenovic, “Optimal power allocationand load distribution for multiple heterogeneous multicore serverprocessors across clouds and data centers,” Computers, IEEETransactions on, vol. 63, no. 1, pp. 45–58, Jan 2014.
[10] S. Jrgensen and G. Zaccour, “A survey of game-theoretic modelsof cooperative advertising,” European Journal of Operational Research,vol. 237, no. 1, pp. 1 – 14, 2014