Evaluating a Cloud Federation Ecosystem to Reduce Carbon Footprint by Moving Computational Resources

Cloud federation is an emerging topic towards new dynamic scenarios in smart ecosystems, where new more flexible energy management strategies are needed than the traditional, in order to optimize mobility and energy efficiency. In this paper we focus both on cloud federation and energy efficiency to enforce a dynamic energy management strategy for the whole ecosystem, in order to reduce carbon dioxide emissions. More specifically, starting from our two-step approach, we evaluate a cloud federation ecosystem by moving computational resources among federated cloud DCs in order to maintain, for a forecast period, the related workload at the best Green Destination (GD) powered by renewable energy sources. To this end we present and discuss two simulated scenarios, and their experimental results, thus to proving the goodness of our approach. Moreover, an energy comparison between the transfer and the maintenance phases for the computational workload is made.