A scalable resource provisioning scheme for the cloud using peer to peer resource discovery and multi-attribute utility theory

Abstract

Serving large number of users without compromising service availability and performance is key to the success of the cloud. A fundamental challenge in building such services is incorporating scalability and fail safe techniques for discovering and provisioning of resources. As peer-to-peer (P2P) architectures are invincible to these setbacks, the work proposes a P2P-based resource discovery and provisioning method for the cloud. It first addresses the multi attribute data publishing and the range querying inability of existing distributed hash table (DHT)-based P2P schemes and proposes an attribute hub-based discovery of provisioning information. Focused on that, a decentralised resource provisioning model is proposed using multi-attribute utility theory methods. The simulation shows that the proposed approach is 44.24% and 45.81% faster than the centralised and DHT-based approaches respectively in case of multidimensional range querying. It also shows the lesser number of service level objective (SLO) violations and migrations which are about 24.11% and 33.43% respectively.