This work presents a multi-objective approach for scheduling energy consumption in data centers considering traditional and green energy data sources. This problem is addressed as a whole by simultaneously scheduling the state of the servers and the cooling devices, and by scheduling the workload of the data center, which is comprised of a set of independent tasks with due dates. Its goal is to simultaneously minimize the energy consumption budget of the data center, the energy consumption deviation from a reference profile, and the amount of tasks whose due dates are violated. Two multi-objective evolutionary algorithms hybridized with a greedy heuristic are proposed and are enhanced by applying simulated annealing for post hoc optimization. Experimental results show that these methods are able to reduce energy consumption budget by about 60% while adequately following a power consumption profile and providing a high quality of service. These results confirm the effectiveness of the proposed algorithmic approach and the usefulness of green energy sources for data center infrastructures.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited