Energy consumption is a critical operational cost for Cloud providers. However, as commercial providers typically use fixed pricing schemes that are oblivious about the energy costs of running virtual machines, clients are not charged according to their actual energy impact. Some works have proposed energy-aware cost models that are able to capture each client’s real energy usage. However, those models cannot be naturally used for pricing Cloud services, as the energy cost is calculated after the termination of the service, and it depends on decisions taken by the provider, such as the actual placement of the client’s virtual machines. For those reasons, a client cannot estimate in advance how much it will pay. This paper presents a pricing model for virtualized Cloud providers that dynamically derives the energy costs per allocation unit and per work unit for each time period. They account for the energy costs of the provider’s static and dynamic energy consumption by sharing out them according to the virtual resource allocation and the real resource usage of running virtual machines for the corresponding time period. Newly arrived clients during that period can use these costs as a baseline to calculate their expenses in advance as a function of the number of requested allocation and work units. Our results show that providers can get comparable revenue to traditional pricing schemes, while offering to the clients more proportional prices than fixed-price models.

Peer Reviewed