Evolutionary neural network based energy consumption forecast for cloud computing

Yong Wee Foo, Cindy Goh, Hong Chee Lim, Zhi Hui Zhan, Yun Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

14 Citations (Scopus)

Abstract

The success of Hadoop, an open-source framework for massively parallel and distributed computing, is expected to drive energy consumption of cloud data centers to new highs as service providers continue to add new infrastructure, services and capabilities to meet the market demands. While current research on data center airflow management, HVAC (Heating, Ventilation and Air Conditioning) system design, workload distribution and optimization, and energy efficient computing hardware and software are all contributing to improved energy efficiency, energy forecast in cloud computing remains a challenge. This paper reports an evolutionary computation based modeling and forecasting approach to this problem. In particular, an evolutionary neural network is developed and structurally optimized to forecast the energy load of a cloud data center. The results, both in terms of forecasting speed and accuracy, suggest that the evolutionary neural network approach to energy consumption forecasting for cloud computing is highly promising.

LanguageEnglish
Title of host publicationProceedings - 2015 International Conference on Cloud Computing Research and Innovation, ICCCRI 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages53-64
Number of pages12
ISBN (Electronic)9781509001446
DOIs
Publication statusPublished - 26 Feb 2016
Event3rd International Conference on Cloud Computing Research and Innovation, ICCCRI 2015 - Singapore, Singapore
Duration: 26 Oct 201527 Oct 2015

Conference

Conference3rd International Conference on Cloud Computing Research and Innovation, ICCCRI 2015
CountrySingapore
CitySingapore
Period26/10/1527/10/15

Fingerprint

Cloud computing
Energy utilization
Neural networks
Distributed computer systems
Parallel processing systems
Dynamic loads
Air conditioning
Evolutionary algorithms
Ventilation
Energy efficiency
Systems analysis
Hardware
Heating

Keywords

  • cloud computing
  • energy efficiency
  • evolutionary computing
  • genetic algorithm
  • hadoop
  • neural networks

Cite this

Foo, Y. W., Goh, C., Lim, H. C., Zhan, Z. H., & Li, Y. (2016). Evolutionary neural network based energy consumption forecast for cloud computing. In Proceedings - 2015 International Conference on Cloud Computing Research and Innovation, ICCCRI 2015 (pp. 53-64). [7421894] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCCRI.2015.17
Foo, Yong Wee ; Goh, Cindy ; Lim, Hong Chee ; Zhan, Zhi Hui ; Li, Yun. / Evolutionary neural network based energy consumption forecast for cloud computing. Proceedings - 2015 International Conference on Cloud Computing Research and Innovation, ICCCRI 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 53-64
@inproceedings{a30490d32bcf4977b296c175d707231f,
title = "Evolutionary neural network based energy consumption forecast for cloud computing",
abstract = "The success of Hadoop, an open-source framework for massively parallel and distributed computing, is expected to drive energy consumption of cloud data centers to new highs as service providers continue to add new infrastructure, services and capabilities to meet the market demands. While current research on data center airflow management, HVAC (Heating, Ventilation and Air Conditioning) system design, workload distribution and optimization, and energy efficient computing hardware and software are all contributing to improved energy efficiency, energy forecast in cloud computing remains a challenge. This paper reports an evolutionary computation based modeling and forecasting approach to this problem. In particular, an evolutionary neural network is developed and structurally optimized to forecast the energy load of a cloud data center. The results, both in terms of forecasting speed and accuracy, suggest that the evolutionary neural network approach to energy consumption forecasting for cloud computing is highly promising.",
keywords = "cloud computing, energy efficiency, evolutionary computing, genetic algorithm, hadoop, neural networks",
author = "Foo, {Yong Wee} and Cindy Goh and Lim, {Hong Chee} and Zhan, {Zhi Hui} and Yun Li",
year = "2016",
month = "2",
day = "26",
doi = "10.1109/ICCCRI.2015.17",
language = "English",
pages = "53--64",
booktitle = "Proceedings - 2015 International Conference on Cloud Computing Research and Innovation, ICCCRI 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Foo, YW, Goh, C, Lim, HC, Zhan, ZH & Li, Y 2016, Evolutionary neural network based energy consumption forecast for cloud computing. in Proceedings - 2015 International Conference on Cloud Computing Research and Innovation, ICCCRI 2015., 7421894, Institute of Electrical and Electronics Engineers Inc., pp. 53-64, 3rd International Conference on Cloud Computing Research and Innovation, ICCCRI 2015, Singapore, Singapore, 26/10/15. https://doi.org/10.1109/ICCCRI.2015.17

Evolutionary neural network based energy consumption forecast for cloud computing. / Foo, Yong Wee; Goh, Cindy; Lim, Hong Chee; Zhan, Zhi Hui; Li, Yun.

Proceedings - 2015 International Conference on Cloud Computing Research and Innovation, ICCCRI 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 53-64 7421894.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Evolutionary neural network based energy consumption forecast for cloud computing

AU - Foo, Yong Wee

AU - Goh, Cindy

AU - Lim, Hong Chee

AU - Zhan, Zhi Hui

AU - Li, Yun

PY - 2016/2/26

Y1 - 2016/2/26

N2 - The success of Hadoop, an open-source framework for massively parallel and distributed computing, is expected to drive energy consumption of cloud data centers to new highs as service providers continue to add new infrastructure, services and capabilities to meet the market demands. While current research on data center airflow management, HVAC (Heating, Ventilation and Air Conditioning) system design, workload distribution and optimization, and energy efficient computing hardware and software are all contributing to improved energy efficiency, energy forecast in cloud computing remains a challenge. This paper reports an evolutionary computation based modeling and forecasting approach to this problem. In particular, an evolutionary neural network is developed and structurally optimized to forecast the energy load of a cloud data center. The results, both in terms of forecasting speed and accuracy, suggest that the evolutionary neural network approach to energy consumption forecasting for cloud computing is highly promising.

AB - The success of Hadoop, an open-source framework for massively parallel and distributed computing, is expected to drive energy consumption of cloud data centers to new highs as service providers continue to add new infrastructure, services and capabilities to meet the market demands. While current research on data center airflow management, HVAC (Heating, Ventilation and Air Conditioning) system design, workload distribution and optimization, and energy efficient computing hardware and software are all contributing to improved energy efficiency, energy forecast in cloud computing remains a challenge. This paper reports an evolutionary computation based modeling and forecasting approach to this problem. In particular, an evolutionary neural network is developed and structurally optimized to forecast the energy load of a cloud data center. The results, both in terms of forecasting speed and accuracy, suggest that the evolutionary neural network approach to energy consumption forecasting for cloud computing is highly promising.

KW - cloud computing

KW - energy efficiency

KW - evolutionary computing

KW - genetic algorithm

KW - hadoop

KW - neural networks

UR - http://www.scopus.com/inward/record.url?scp=84964864006&partnerID=8YFLogxK

U2 - 10.1109/ICCCRI.2015.17

DO - 10.1109/ICCCRI.2015.17

M3 - Conference contribution book

SP - 53

EP - 64

BT - Proceedings - 2015 International Conference on Cloud Computing Research and Innovation, ICCCRI 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Foo YW, Goh C, Lim HC, Zhan ZH, Li Y. Evolutionary neural network based energy consumption forecast for cloud computing. In Proceedings - 2015 International Conference on Cloud Computing Research and Innovation, ICCCRI 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 53-64. 7421894 https://doi.org/10.1109/ICCCRI.2015.17