A Novel Resource Pricing Mechanism based on Multi-Player Gaming Model in Cloud Environments

Recently, cloud computing has become a promising network platform for non-trivial applications. The key feature of cloud computing is on-demand resource provision by utility paradigm. Therefore, resource pricing mechanism plays an important role for realizing on-demand resource provision. Unfortunately, existing resource pricing mechanism will result in many negative effects on system performance, such as low-efficient negotiation, extra communication costs and etc. In this paper, we present a novel resource pricing mechanism, which is based on multiplayer gaming model and capable of realizing batch resource allocation in an efficient manner. In this mechanism, we introduce a set of virtual resource brokers which is responsible for figuring most rationale resource prices in elastic cloud environment. To investigate the effectiveness and performance of our pricing mechanism, extensive experiments are conducted, and we compare its performance with various approaches, include marketbased approaches and auction mechanisms. The results show that our pricing mechanism is more effective to realizing batch resource allocation, especially when the system workload is intensive. In addition, our mechanism can significantly reduce the negotiation costs comparing with exiting approaches.