A method and system for energy-saving scheduling in a data center

Abstract

The invention provides a data center energy-saving scheduling method and system. The method comprises the steps of obtaining resource utilization rates of all servers in a current data center, resource requirements of to-be-scheduled tasks in a task queue and current external environment parameters, and predicting total power consumption of the data center and machine room air conditioner settingparameters after the to-be-scheduled tasks are deployed on any server by utilizing a preset prediction model; and determining a data center energy-saving scheduling scheme conforming to a preset condition according to the prediction result, and scheduling the total energy consumption of the data center according to the scheme. The energy consumption of the server system and the energy consumptionof the machine room air conditioning system are jointly dispatched through a machine learning method, the problem that the energy saving efficiency is low due to the fact that an inaccurate energy consumption model is adopted for single-layer optimization and CFD simulation dispatching exists in the related technology is solved, and the effect of optimizing the total energy consumption of the datacenter in a cross-layer unified mode is achieved.

Description

technical field [0001] The invention relates to the field of data centers, in particular to a data center energy-saving scheduling method and system for realizing cross-layer unified energy consumption optimization of data centers. Background technique [0002] With the rapid development of cloud computing technology, as the physical platform of cloud computing, data centers around the world have also achieved unprecedented development. The rapidly growing number of data centers has also brought huge energy costs to operators. For example, in 2014, the total electricity consumption of data centers in the United States accounted for 1.8% of the total annual electricity consumption in the United States, and this value is still increasing year by year. In order to reduce the power consumption of data centers, academia and industry have proposed a series of energy-saving solutions. Because the server system and the computer room air conditioning system together account for mor...

AI Technical Summary

Problems solved by technology

[0004] The invention provides a data center energy-saving scheduling method and system, which jointly schedules the energy consumption of the server system and the computer room air-conditioning system through a machine learning method, and solves the problems in related technologies such as single-level optimization, inaccurate energy consumption models, and based on The problem of low energy saving efficiency caused by CFD simulation scheduling

Images