Load Forecasting Modelling of Data Centers and IT Systems by Using Artificial Neural Networks

Abstract

A data center is a repository that houses computing facilities like servers, routers, switches and firewalls, as well as supporting components like backup equipment, fire suppression facilities and air conditioning. Data centers nowadays are proliferating all over the world because of increasing demand for Internet applications. Our goal is to find a way to optimize energy consumption of data centers by encompassing automation control system devices and load forecasting. In this paper, the authors prepared a server for modelling a data center and a software named DAEMS (Data Acquisition and Energy Management Software) to collect data for forecasting of electricity by using Artificial Neural Networks. The forecasting model is then used to produce a load profile of a server.