Demand-response power management strategy using time shifting capabilities
Tipus de documentText en actes de congrés
EditorAssociation for Computing Machinery (ACM)
Condicions d'accésAccés restringit per política de l'editorial
Energy efficiency is an important concern in the operation and deployment of the communications networks and cloud computing services, and due to the rising energy consumption, demand-response strategies are envisioned as promising alternatives. Despite the fact that many works have been proposed to improve the energy efficiency, these techniques and mechanisms do not consider the dynamic behavior of the energy generation or the possibility of rescheduling the energy loads according to the amount of available energy, moreover these proposals are mostly focused on reducing energy consumption. In this context, this paper presents a novel strategy in which the data centers, at the core of the network infrastructure, services and innovations, perform the power management by fostering the cooperation of consumers to adapt the energy demands to the available power. In this demand-response approach, data centers as power managers, are responsible for executing algorithms that allows to obtain the optimal scheduling of tasks in time. This proactive redistribution of demands aims to maximize the full available power utilization and minimize power waste. The proposed strategy is developed to find the exact solution using brute force algorithms based on a combinatorial algorithm, in order to be able to develop future heuristics for practical implementations. Simulations results validate its performance, while demonstrating improvements in the use of power and in the execution of tasks.
CitacióTipantuña, C., Hesselbach, X. Demand-response power management strategy using time shifting capabilities. A: International Conference on Future Energy Systems. "e-Energy 2018: proceedings of the 9th ACM International Conference on Future Energy Systems: June 12-15, 2018: Karlsruhe, Germany". New York: Association for Computing Machinery (ACM), 2018, p. 480-485.
Versió de l'editorhttps://dl.acm.org/citation.cfm?doid=3208903.3213519
|E2DC 2018 paperConference.pdf||787,1Kb||Accés restringit|