Applying Reinforcement Learning Method for Real-time Energy Management

Aida Borhan Dayani, Hamed Fazlollahtabar, Roya Ahmadiahangar, Argo Rosin, Mohammad Salay Naderi, Mehdi Bagheri

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

Abstract

today energy management and optimization is a key factor to control the whole production cycle, distribution and energy consumption. Electrical energy consumption optimization involves proper modeling and prediction. Preservation of energy-efficient resources and proper consumption management is one of the most important challenges in all countries of the world. In this study, we present a decision support system for managing energy by reinforcement learning. First, a set of different energy uncertain consumption data and adopted decisions were considered in the form of fuzzy. Then, the prediction of consumption was done by the Q-learning algorithm, which is a solution to the Markov decision problem. Then the rules are presented to describe what the system implies. The proposed method is capable of working in real-time approach and handle the consumption fluctuations in learning and predicting process.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728106526
DOIs
Publication statusPublished - Jun 1 2019
Event19th IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019 - Genoa, Italy
Duration: Jun 11 2019Jun 14 2019

Publication series

NameProceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019

Conference

Conference19th IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019
CountryItaly
CityGenoa
Period6/11/196/14/19

Fingerprint

Energy Management
Energy management
Reinforcement learning
Reinforcement Learning
Energy utilization
Real-time
Decision support systems
Learning algorithms
Energy Consumption
Energy Optimization
Q-learning
Prediction
Decision Support Systems
Energy
Energy Efficient
Decision problem
Preservation
Learning Algorithm
Fluctuations
Imply

Keywords

  • decision support system
  • Demand
  • Energy management
  • Q-learning algorithm
  • reinforcement learning

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Renewable Energy, Sustainability and the Environment
  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering
  • Environmental Engineering
  • Control and Optimization

Cite this

Dayani, A. B., Fazlollahtabar, H., Ahmadiahangar, R., Rosin, A., Naderi, M. S., & Bagheri, M. (2019). Applying Reinforcement Learning Method for Real-time Energy Management. In Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019 [8783766] (Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EEEIC.2019.8783766

Applying Reinforcement Learning Method for Real-time Energy Management. / Dayani, Aida Borhan; Fazlollahtabar, Hamed; Ahmadiahangar, Roya; Rosin, Argo; Naderi, Mohammad Salay; Bagheri, Mehdi.

Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8783766 (Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019).

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

Dayani, AB, Fazlollahtabar, H, Ahmadiahangar, R, Rosin, A, Naderi, MS & Bagheri, M 2019, Applying Reinforcement Learning Method for Real-time Energy Management. in Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019., 8783766, Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019, Institute of Electrical and Electronics Engineers Inc., 19th IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019, Genoa, Italy, 6/11/19. https://doi.org/10.1109/EEEIC.2019.8783766
Dayani AB, Fazlollahtabar H, Ahmadiahangar R, Rosin A, Naderi MS, Bagheri M. Applying Reinforcement Learning Method for Real-time Energy Management. In Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8783766. (Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019). https://doi.org/10.1109/EEEIC.2019.8783766
Dayani, Aida Borhan ; Fazlollahtabar, Hamed ; Ahmadiahangar, Roya ; Rosin, Argo ; Naderi, Mohammad Salay ; Bagheri, Mehdi. / Applying Reinforcement Learning Method for Real-time Energy Management. Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019).
@inproceedings{0b0d3eab45a74c3ba410153cfbcd8879,
title = "Applying Reinforcement Learning Method for Real-time Energy Management",
abstract = "today energy management and optimization is a key factor to control the whole production cycle, distribution and energy consumption. Electrical energy consumption optimization involves proper modeling and prediction. Preservation of energy-efficient resources and proper consumption management is one of the most important challenges in all countries of the world. In this study, we present a decision support system for managing energy by reinforcement learning. First, a set of different energy uncertain consumption data and adopted decisions were considered in the form of fuzzy. Then, the prediction of consumption was done by the Q-learning algorithm, which is a solution to the Markov decision problem. Then the rules are presented to describe what the system implies. The proposed method is capable of working in real-time approach and handle the consumption fluctuations in learning and predicting process.",
keywords = "decision support system, Demand, Energy management, Q-learning algorithm, reinforcement learning",
author = "Dayani, {Aida Borhan} and Hamed Fazlollahtabar and Roya Ahmadiahangar and Argo Rosin and Naderi, {Mohammad Salay} and Mehdi Bagheri",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/EEEIC.2019.8783766",
language = "English",
series = "Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019",
address = "United States",

}

TY - GEN

T1 - Applying Reinforcement Learning Method for Real-time Energy Management

AU - Dayani, Aida Borhan

AU - Fazlollahtabar, Hamed

AU - Ahmadiahangar, Roya

AU - Rosin, Argo

AU - Naderi, Mohammad Salay

AU - Bagheri, Mehdi

PY - 2019/6/1

Y1 - 2019/6/1

N2 - today energy management and optimization is a key factor to control the whole production cycle, distribution and energy consumption. Electrical energy consumption optimization involves proper modeling and prediction. Preservation of energy-efficient resources and proper consumption management is one of the most important challenges in all countries of the world. In this study, we present a decision support system for managing energy by reinforcement learning. First, a set of different energy uncertain consumption data and adopted decisions were considered in the form of fuzzy. Then, the prediction of consumption was done by the Q-learning algorithm, which is a solution to the Markov decision problem. Then the rules are presented to describe what the system implies. The proposed method is capable of working in real-time approach and handle the consumption fluctuations in learning and predicting process.

AB - today energy management and optimization is a key factor to control the whole production cycle, distribution and energy consumption. Electrical energy consumption optimization involves proper modeling and prediction. Preservation of energy-efficient resources and proper consumption management is one of the most important challenges in all countries of the world. In this study, we present a decision support system for managing energy by reinforcement learning. First, a set of different energy uncertain consumption data and adopted decisions were considered in the form of fuzzy. Then, the prediction of consumption was done by the Q-learning algorithm, which is a solution to the Markov decision problem. Then the rules are presented to describe what the system implies. The proposed method is capable of working in real-time approach and handle the consumption fluctuations in learning and predicting process.

KW - decision support system

KW - Demand

KW - Energy management

KW - Q-learning algorithm

KW - reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=85070826146&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070826146&partnerID=8YFLogxK

U2 - 10.1109/EEEIC.2019.8783766

DO - 10.1109/EEEIC.2019.8783766

M3 - Conference contribution

AN - SCOPUS:85070826146

T3 - Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019

BT - Proceedings - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -