Abstract

Cloud federation is a recently proposed paradigm that advocates resource sharing among multiple cloud providers (CPs). In cloud federation, the demanding CPs with resource limitation can outsource their requests to other supplying CPs with idle resources. Pricing places an important role in incentivizing the resource sharing among the CPs. In this paper, we consider the cloud federation with one supplying CPs and multiple demanding CPs. We propose a prediction-based pricing scheme to maximize the social welfare for the case with incomplete information. We also analyze the impact of prediction error and derive the worst-case lower bound of the efficiency of our proposed prediction-based pricing scheme.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call