Opportunistic Scheduling in Clouds Partially Powered by Green Energy

Abstract

The fast growth of demand for computing and storage resources in data centers has considerably increased their energy consumption. Improving the utilization of data center resources and integrating renewable energy, such as solar and wind, has been proposed to reduce both the brown energy consumption and carbon footprint of the data centers. In this paper, we propose a novel framework oPportunistic schedulIng broKer infrAstructure (PIKA) to save energy in small mono-site data centers. In order to reduce the brown energy consumption, PIKA integrates resource overcommit techniques that help to minimize the number of powered-on Physical Machines (PMs). On the other hand, PIKA dynamically schedules the jobs and adjusts the number of powered-on PMs to match the variable renewable energy supply. Our simulations with a real-world job workload and solar power traces demonstrate that PIKA saves brown energy consumption by up to 44.9% compared to a typical scheduling algorithm.

Leveraging Renewable Energy in Edge Clouds for Data Stream Analysis in IoT

“…Most of previous studies [26] agree on the fact that the dynamic server power consumption mainly depends on the working CPU frequency. The server power consumption is taken for different CPU load profiles as described in [13]. Furthermore, our experimental results show in particular that a server on idle state consumes roughly half of its maximal power consumption.…”

“…In [13], Li et al explain that such a system cannot be satisfied when the workload contains real-time jobs. The proposed solution consists in using Energy Storage Devices (ESDs) [14] to store the surplus electricity generated from renewable energy sources.…”

“…In order to increase the usage of renewable energy, one way consists in carefully scheduling the workload to align with the timevarying renewable energy. In [13], Li et al propose an online algorithm making use of opportunistic scheduling for optimizing solar energy utilization in a small-/mediumscale data center without energy storage. This approach leverages two ideas: 1) delay part of jobs which could be suspended within limit time (e.g., batch jobs) until solar energy becomes available; 2) when the renewable energy production cannot fully support the entire workload energy consumption, the system migrate the jobs from underutilized servers to others and switches-off them with the help of consolidation techniques.…”

“…The network energy consumption model is defined in a similar way in [25] and based on bit. These models were integrated into the simulator we developed in [13]. In order to extrapolate to large-scale, the second half of our experiments are held using this simulator.…”

Balancing the Use of Batteries and Opportunistic Scheduling Policies for Maximizing Renewable Energy Consumption in a Cloud Data Center

“…But instead, opportunistic scheduling algorithms can make advantage of renewable energy availability to perform jobs with low priorities [7]. Opportunistic policies distinguish two kind of computing jobs: jobs requiring to run continuously (like web servers) and jobs that can be delayed and interrupted, but with a deadline constraint (such batch jobs include monthly payroll computation for example).…”