Energy Consumption Model Of Data Center And Real Time Energy Consumption System

In recent years,cloud computing data center has been developed rapidly because of its high data utilization,flexible management and good expansibility.However,more computing resources and storage resources are concentrated in the cloud,which brings more challenges to the efficient management of energy consumption.Although cloud computing is considered as a kind of green computing,it does not provide a mature solution to evaluate and reduce energy consumption.Therefore,more efficient cloud computing management model is still needed.Energy consumption model is an important part of the cloud data center.In the continuous operation of the cloud data center,users and managers need to understand how their behavior affects the computer energy consumption,and thus take the appropriate regulatory measures to achieve the purpose of optimizing the energy efficiency.Today,with the continuous expansion of the size of the cloud data center,data center energy consumption characteristics have become complex and diverse.This paper solves the problem of energy consumption of data centers from two perspectives:First,calculate the characteristics of data center and to build the energy consumption model.Second,design and implementation of energy consumption system.In this paper,an accurate nonlinear energy consumption model is constructed based on the system utilization.The components of the energy consumption of the nodes,including CPU,memory,hard disk,and so on.Through the data analysis and regression analysis to obtain the final energy consumption model.In the model of energy consumption,the eff-ect of CPU on the energy consumption of other components is considered in this paper,and the influence factors are designed to ensure the accuracy of the model.Real time energy consumption system is a subsystem of the special fund energy management system based on the Internet of things.Real time energy consumption system based on Struts2 framework to build.Mainly include real time display,the definition of energy consumption and special task energy consumption calculation.In each computing node,the CPU utilization,memory utilization and hard disk utilization were collected and recorded in the log file.Real time display module through the high frequency scanning log file,the system utilization rate of each component is obtained,and the energy consumption model is used to calculate the energy consumption and the data is stored in the database.All kinds of energy consumption data can be obtained at a certain energy consumption custom query nodes by querying the database.Special task energy consumption calculation is the energy consumption value of the parallel algorithm in the parent system.