Enhancing fairness in P2P cloud federations

A dynamic capacity supply controller is proposed to enhance fairness in federations.A study is done using the Network of Favors as incentive mechanism for cooperation.Fairness goals are attained by collaborative peers with different sizes and needs.Free riders are isolated much more efficiently in low resource contention scenarios. This work presents a non-monetary market system mechanism for resource sharing within a decentralized lightweight Peer-to-Peer (P2P) federation of private cloud providers. The mechanism is intended to enable collaborative peers to take appropriate decisions guaranteeing suitable levels of satisfaction and fairness as well as isolation of non-collaborative peers. The proposed scheme leverages the notion of the Network of Favors, formerly advanced as an incentive mechanism for P2P opportunistic desktop grids in which peers are concerned primarily with their satisfaction, not fairness. An enhancement of the Network of Favors is presented here that consists in the introduction of a control loop mechanism limiting the amount of resources that a private cloud is willing to provide to other members of federation, thereby indirectly keeping resource contention at an adequate level for discouraging free riding and guaranteeing an appropriate degree of fairness with only minor impact on the satisfaction levels of collaborative peers.

[1]  Yong Meng Teo,et al.  Dynamic Resource Pricing on Federated Clouds , 2010, 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing.

[2]  Nazareno Andrade,et al.  Discouraging free riding in a peer-to-peer CPU-sharing grid , 2004, Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004..

[3]  P. Sedgwick Matching , 2009, BMJ : British Medical Journal.

[4]  Hector Garcia-Molina,et al.  The Eigentrust algorithm for reputation management in P2P networks , 2003, WWW '03.

[5]  Rajkumar Buyya,et al.  Inter‐Cloud architectures and application brokering: taxonomy and survey , 2014, Softw. Pract. Exp..

[6]  Ernesto Damiani,et al.  Managing and Sharing Servents' Reputations in P2P Systems , 2003, IEEE Trans. Knowl. Data Eng..

[8]  Leandros Tassiulas,et al.  Reputation-Based Resource Allocation in P2P Systems of Rational Users , 2010, IEEE Transactions on Parallel and Distributed Systems.

[9]  Yixin Diao,et al.  Feedback Control of Computing Systems , 2004 .

[10]  Ryszard Kowalczyk,et al.  Pure exchange markets for resource sharing in federated clouds , 2010, Concurr. Comput. Pract. Exp..

[11]  Benny Rochwerger,et al.  Reservoir - When One Cloud Is Not Enough , 2011, Computer.

[12]  Paul Marshall,et al.  Elastic Site: Using Clouds to Elastically Extend Site Resources , 2010, 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing.

[13]  Nazareno Andrade,et al.  Automatic grid assembly by promoting collaboration in peer-to-peer grids , 2007, J. Parallel Distributed Comput..

[14]  J E Staddon,et al.  Matching, maximizing, and hill-climbing. , 1983, Journal of the experimental analysis of behavior.

[15]  Jordi Torres,et al.  Economic model of a Cloud provider operating in a federated Cloud , 2012, Inf. Syst. Frontiers.