As energy costs become increasingly greater contributors to a cloud provider's overall costs, it is important for the cloud to recoup these energy costs from its tenants for profitability via appropriate pricing design. The poor predictability of real-world tenants' demand and demand responses (DRs) make such pricing design a challenging problem. We formulate a leader-follower game-based cloud pricing framework with the goal of maximizing cloud's profit. The key distinguishing aspect of our approach is our emphasis on modeling both the cloud and its tenants as working with low predictability in their inputs. Consequently, we model them as employing myopic control with short-term predictive models. Our empirical evaluation using tenant trace from IBM production data centers shows that (i) cloud's profit and VM prices are sensitive to the tradeoffs between its energy costs, tenant's demand and DR, and (ii) the cloud's estimation of tenants' demands/DR may significantly affect its profitability.@en

The energy-performance optimization of datacenters becomes ever challenging, due to heterogeneous workloads featuring different performance constraints. In addition to conventional web service, MapReduce presents another important workload class, whose performance highly depends on data availability/locality and shows different degrees of delay sensitivities, such as batch vs. interactive MapReduce. However, current energy optimization solutions are mainly designed for a subset of these workloads and their key features. Here, we present an energy minimization framework, in particular, a concave minimization problem, that specifically considers time variability, data locality, and delay sensitivity of web, batch-, and interactive-MapReduce. We aim to maximize the usage of MapReduce servers by using their spare capacity to run non-MapReduce workloads, while controlling the workload delays through the execution of MapReduce tasks, in particular batch ones. We develop an optimal algorithm with complexity O(T2) in case of perfect workload information, T being the length of the time horizon in number of control windows, and derive the structure of optimal policy for the case of uncertain workload information. Using extensive simulation results, we show that the proposed methodology can efficiently minimize the datacenter energy cost while fulfilling the delay constraints of workloads.@en