Deep learning for power system data analysis

Elena Mocanu, Phong H. Nguyen, Madelaeine Gibescu

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

3 Citations (Scopus)

Abstract

Unprecedented high volumes of data are available in the smart grid context, facilitated by the growth of home energy management systems and advanced metering infrastructure. In order to automatically extract knowledge from, and take advantage of this useful information to improve grid operation, recently developed machine learning techniques can be used, in both supervised and unsupervised ways. The proposed chapter will focus on deep learning methods and will be structured as follows: Firstly, as a starting point with respect to the state of the art, the most known deep learning concepts, such as deep belief networks and high-order restricted Boltzmann machine (i.e., conditional restricted Boltzmann machine, factored conditional restricted Boltzmann machine, four-way conditional restricted Boltzmann machine), are presented. Both, their theoretical advantages and limitations are discussed, such as computational requirements, convergence, and stability. Consequently, two applications for building energy prediction using supervised and unsupervised deep learning methods will be presented. The chapter concludes with a glimpse into the future trends highlighting some open questions as well as new possible applications, which are expected to bring benefits toward better planning and operation of the smart grid, by helping customers to adopt energy conserving behaviors and their transition from a passive to an active role.
Original languageEnglish
Title of host publicationBig Data Application in Power Systems
EditorsReza Arghandeh, Yuxun Zhou
PublisherElsevier
Chapter7
Pages125-158
Number of pages34
ISBN (Electronic)978-0-12-811969-3
ISBN (Print)978-0-12-811968-6
DOIs
Publication statusPublished - 27 Nov 2017
Externally publishedYes

Fingerprint

Advanced metering infrastructures
Energy management systems
Bayesian networks
Learning systems
Planning
Deep learning

Keywords

  • Deep Learning
  • Energy prediction
  • Reinforcement learning
  • Supervised learning
  • Transfer learning
  • Unsupervised learning
  • Time series

Cite this

Mocanu, E., Nguyen, P. H., & Gibescu, M. (2017). Deep learning for power system data analysis. In R. Arghandeh, & Y. Zhou (Eds.), Big Data Application in Power Systems (pp. 125-158). Elsevier. https://doi.org/10.1016/B978-0-12-811968-6.00007-3
Mocanu, Elena ; Nguyen, Phong H. ; Gibescu, Madelaeine. / Deep learning for power system data analysis. Big Data Application in Power Systems. editor / Reza Arghandeh ; Yuxun Zhou. Elsevier, 2017. pp. 125-158
@inbook{a494500ff2e24ab6bd62dd3137408117,
title = "Deep learning for power system data analysis",
abstract = "Unprecedented high volumes of data are available in the smart grid context, facilitated by the growth of home energy management systems and advanced metering infrastructure. In order to automatically extract knowledge from, and take advantage of this useful information to improve grid operation, recently developed machine learning techniques can be used, in both supervised and unsupervised ways. The proposed chapter will focus on deep learning methods and will be structured as follows: Firstly, as a starting point with respect to the state of the art, the most known deep learning concepts, such as deep belief networks and high-order restricted Boltzmann machine (i.e., conditional restricted Boltzmann machine, factored conditional restricted Boltzmann machine, four-way conditional restricted Boltzmann machine), are presented. Both, their theoretical advantages and limitations are discussed, such as computational requirements, convergence, and stability. Consequently, two applications for building energy prediction using supervised and unsupervised deep learning methods will be presented. The chapter concludes with a glimpse into the future trends highlighting some open questions as well as new possible applications, which are expected to bring benefits toward better planning and operation of the smart grid, by helping customers to adopt energy conserving behaviors and their transition from a passive to an active role.",
keywords = "Deep Learning, Energy prediction, Reinforcement learning, Supervised learning, Transfer learning, Unsupervised learning, Time series",
author = "Elena Mocanu and Nguyen, {Phong H.} and Madelaeine Gibescu",
year = "2017",
month = "11",
day = "27",
doi = "10.1016/B978-0-12-811968-6.00007-3",
language = "English",
isbn = "978-0-12-811968-6",
pages = "125--158",
editor = "Reza Arghandeh and Yuxun Zhou",
booktitle = "Big Data Application in Power Systems",
publisher = "Elsevier",

}

Mocanu, E, Nguyen, PH & Gibescu, M 2017, Deep learning for power system data analysis. in R Arghandeh & Y Zhou (eds), Big Data Application in Power Systems. Elsevier, pp. 125-158. https://doi.org/10.1016/B978-0-12-811968-6.00007-3

Deep learning for power system data analysis. / Mocanu, Elena; Nguyen, Phong H.; Gibescu, Madelaeine.

Big Data Application in Power Systems. ed. / Reza Arghandeh; Yuxun Zhou. Elsevier, 2017. p. 125-158.

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

TY - CHAP

T1 - Deep learning for power system data analysis

AU - Mocanu, Elena

AU - Nguyen, Phong H.

AU - Gibescu, Madelaeine

PY - 2017/11/27

Y1 - 2017/11/27

N2 - Unprecedented high volumes of data are available in the smart grid context, facilitated by the growth of home energy management systems and advanced metering infrastructure. In order to automatically extract knowledge from, and take advantage of this useful information to improve grid operation, recently developed machine learning techniques can be used, in both supervised and unsupervised ways. The proposed chapter will focus on deep learning methods and will be structured as follows: Firstly, as a starting point with respect to the state of the art, the most known deep learning concepts, such as deep belief networks and high-order restricted Boltzmann machine (i.e., conditional restricted Boltzmann machine, factored conditional restricted Boltzmann machine, four-way conditional restricted Boltzmann machine), are presented. Both, their theoretical advantages and limitations are discussed, such as computational requirements, convergence, and stability. Consequently, two applications for building energy prediction using supervised and unsupervised deep learning methods will be presented. The chapter concludes with a glimpse into the future trends highlighting some open questions as well as new possible applications, which are expected to bring benefits toward better planning and operation of the smart grid, by helping customers to adopt energy conserving behaviors and their transition from a passive to an active role.

AB - Unprecedented high volumes of data are available in the smart grid context, facilitated by the growth of home energy management systems and advanced metering infrastructure. In order to automatically extract knowledge from, and take advantage of this useful information to improve grid operation, recently developed machine learning techniques can be used, in both supervised and unsupervised ways. The proposed chapter will focus on deep learning methods and will be structured as follows: Firstly, as a starting point with respect to the state of the art, the most known deep learning concepts, such as deep belief networks and high-order restricted Boltzmann machine (i.e., conditional restricted Boltzmann machine, factored conditional restricted Boltzmann machine, four-way conditional restricted Boltzmann machine), are presented. Both, their theoretical advantages and limitations are discussed, such as computational requirements, convergence, and stability. Consequently, two applications for building energy prediction using supervised and unsupervised deep learning methods will be presented. The chapter concludes with a glimpse into the future trends highlighting some open questions as well as new possible applications, which are expected to bring benefits toward better planning and operation of the smart grid, by helping customers to adopt energy conserving behaviors and their transition from a passive to an active role.

KW - Deep Learning

KW - Energy prediction

KW - Reinforcement learning

KW - Supervised learning

KW - Transfer learning

KW - Unsupervised learning

KW - Time series

U2 - 10.1016/B978-0-12-811968-6.00007-3

DO - 10.1016/B978-0-12-811968-6.00007-3

M3 - Chapter

SN - 978-0-12-811968-6

SP - 125

EP - 158

BT - Big Data Application in Power Systems

A2 - Arghandeh, Reza

A2 - Zhou, Yuxun

PB - Elsevier

ER -

Mocanu E, Nguyen PH, Gibescu M. Deep learning for power system data analysis. In Arghandeh R, Zhou Y, editors, Big Data Application in Power Systems. Elsevier. 2017. p. 125-158 https://doi.org/10.1016/B978-0-12-811968-6.00007-3