Capacity Management of Hyperscale Data Centers Using Predictive Modelling
Big Data applications have become increasingly popular with the emergence of cloud computing and the explosion of artificial intelligence. The increasing adoption of data-intensive machines and services is driving the need for more power to keep the data centers of the world running. It has become c...
Published in: | Energies |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2019
|
Subjects: | |
Online Access: | https://doi.org/10.3390/en12183438 |
id |
ftmdpi:oai:mdpi.com:/1996-1073/12/18/3438/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/1996-1073/12/18/3438/ 2023-08-20T04:07:54+02:00 Capacity Management of Hyperscale Data Centers Using Predictive Modelling Raihan Ul Islam Xhesika Ruci Mohammad Shahadat Hossain Karl Andersson Ah-Lian Kor 2019-09-06 application/pdf https://doi.org/10.3390/en12183438 EN eng Multidisciplinary Digital Publishing Institute https://dx.doi.org/10.3390/en12183438 https://creativecommons.org/licenses/by/4.0/ Energies; Volume 12; Issue 18; Pages: 3438 learning differential evolution belief rule-based expert systems predictive modelling data center Text 2019 ftmdpi https://doi.org/10.3390/en12183438 2023-07-31T22:35:11Z Big Data applications have become increasingly popular with the emergence of cloud computing and the explosion of artificial intelligence. The increasing adoption of data-intensive machines and services is driving the need for more power to keep the data centers of the world running. It has become crucial for large IT companies to monitor the energy efficiency of their data-center facilities and to take actions on the optimization of these heavy electricity consumers. This paper proposes a Belief Rule-Based Expert System (BRBES)-based predictive model to predict the Power Usage Effectiveness (PUE) of a data center. The uniqueness of this model consists of the integration of a novel learning mechanism consisting of parameter and structure optimization by using BRBES-based adaptive Differential Evolution (BRBaDE), significantly improving the accuracy of PUE prediction. This model has been evaluated by using real-world data collected from a Facebook data center located in Luleå, Sweden. In addition, to prove the robustness of the predictive model, it has been compared with other machine learning techniques, such as an Artificial Neural Network (ANN) and an Adaptive Neuro Fuzzy Inference System (ANFIS), where it showed a better result. Further, due to the flexibility of the BRBES-based predictive model, it can be used to capture the nonlinear dependencies of many variables of a data center, allowing the prediction of PUE with much accuracy. Consequently, this plays an important role to make data centers more energy-efficient. Text Luleå Luleå Luleå MDPI Open Access Publishing Energies 12 18 3438 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
learning differential evolution belief rule-based expert systems predictive modelling data center |
spellingShingle |
learning differential evolution belief rule-based expert systems predictive modelling data center Raihan Ul Islam Xhesika Ruci Mohammad Shahadat Hossain Karl Andersson Ah-Lian Kor Capacity Management of Hyperscale Data Centers Using Predictive Modelling |
topic_facet |
learning differential evolution belief rule-based expert systems predictive modelling data center |
description |
Big Data applications have become increasingly popular with the emergence of cloud computing and the explosion of artificial intelligence. The increasing adoption of data-intensive machines and services is driving the need for more power to keep the data centers of the world running. It has become crucial for large IT companies to monitor the energy efficiency of their data-center facilities and to take actions on the optimization of these heavy electricity consumers. This paper proposes a Belief Rule-Based Expert System (BRBES)-based predictive model to predict the Power Usage Effectiveness (PUE) of a data center. The uniqueness of this model consists of the integration of a novel learning mechanism consisting of parameter and structure optimization by using BRBES-based adaptive Differential Evolution (BRBaDE), significantly improving the accuracy of PUE prediction. This model has been evaluated by using real-world data collected from a Facebook data center located in Luleå, Sweden. In addition, to prove the robustness of the predictive model, it has been compared with other machine learning techniques, such as an Artificial Neural Network (ANN) and an Adaptive Neuro Fuzzy Inference System (ANFIS), where it showed a better result. Further, due to the flexibility of the BRBES-based predictive model, it can be used to capture the nonlinear dependencies of many variables of a data center, allowing the prediction of PUE with much accuracy. Consequently, this plays an important role to make data centers more energy-efficient. |
format |
Text |
author |
Raihan Ul Islam Xhesika Ruci Mohammad Shahadat Hossain Karl Andersson Ah-Lian Kor |
author_facet |
Raihan Ul Islam Xhesika Ruci Mohammad Shahadat Hossain Karl Andersson Ah-Lian Kor |
author_sort |
Raihan Ul Islam |
title |
Capacity Management of Hyperscale Data Centers Using Predictive Modelling |
title_short |
Capacity Management of Hyperscale Data Centers Using Predictive Modelling |
title_full |
Capacity Management of Hyperscale Data Centers Using Predictive Modelling |
title_fullStr |
Capacity Management of Hyperscale Data Centers Using Predictive Modelling |
title_full_unstemmed |
Capacity Management of Hyperscale Data Centers Using Predictive Modelling |
title_sort |
capacity management of hyperscale data centers using predictive modelling |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2019 |
url |
https://doi.org/10.3390/en12183438 |
genre |
Luleå Luleå Luleå |
genre_facet |
Luleå Luleå Luleå |
op_source |
Energies; Volume 12; Issue 18; Pages: 3438 |
op_relation |
https://dx.doi.org/10.3390/en12183438 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/en12183438 |
container_title |
Energies |
container_volume |
12 |
container_issue |
18 |
container_start_page |
3438 |
_version_ |
1774719847265992704 |