A machine learning approach to modelling escalator demand response

Research output: Contribution to journalArticleScientificpeer-review

Standard

A machine learning approach to modelling escalator demand response. / Uimonen, Semen; Tukia, Toni; Ekström, Jussi; Siikonen, Marja-Liisa; Lehtonen, Matti.

In: ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, Vol. 90, 103521, 01.04.2020.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

APA

Vancouver

Author

Bibtex - Download

@article{cace3f2f00e44cd4811598f644fecf11,
title = "A machine learning approach to modelling escalator demand response",
abstract = "This article relates to the topic of the escalator demand response potential. Previous studies mapped escalators as an unrealized potential for additional demand response. The decrease of the nominal speed is the proposed method of reducing the power consumption of an escalator that comes at the cost of passenger travel time and queuing. This work proposes a solution to a problem of selecting appropriate escalators from a large pool to accommodate the target of power curtailment at a minimum cost and highlights the escalator features that constitute the best demand response candidates. The paper compares four methods which differ in calculation speed and accuracy. The primal solution is the earlier developed and enhanced simulation-based model. The random forest and the neural network models provide a solution trained on the output of the simulation-based model aiming to enhance the calculation speed. Finally, all of the developed solutions are compared to the random selection of escalators. The comparison of the proposed statistical approaches shows that the random forest outperforms the neural networks with a maximum error in the prediction of the overall costs in the range of 10.5{\%} of the simulation-based model solution, while the neural network solution lies within 10{\%}–58{\%}, depending on the targeted value of the power reduction. Statistical approaches enable performing predictions for different times of the day and for new escalator populations without the need for time-demanding simulations. Comparison to the random selection of escalators demonstrates that the proposed models generally outperform the random selection at least seven-fold.",
keywords = "Demand response, Escalators, Modelling, Neural networks, Random forest, Vertical transportation",
author = "Semen Uimonen and Toni Tukia and Jussi Ekstr{\"o}m and Marja-Liisa Siikonen and Matti Lehtonen",
year = "2020",
month = "4",
day = "1",
doi = "10.1016/j.engappai.2020.103521",
language = "English",
volume = "90",
journal = "ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE",
issn = "0952-1976",
publisher = "Elsevier Limited",

}

RIS - Download

TY - JOUR

T1 - A machine learning approach to modelling escalator demand response

AU - Uimonen, Semen

AU - Tukia, Toni

AU - Ekström, Jussi

AU - Siikonen, Marja-Liisa

AU - Lehtonen, Matti

PY - 2020/4/1

Y1 - 2020/4/1

N2 - This article relates to the topic of the escalator demand response potential. Previous studies mapped escalators as an unrealized potential for additional demand response. The decrease of the nominal speed is the proposed method of reducing the power consumption of an escalator that comes at the cost of passenger travel time and queuing. This work proposes a solution to a problem of selecting appropriate escalators from a large pool to accommodate the target of power curtailment at a minimum cost and highlights the escalator features that constitute the best demand response candidates. The paper compares four methods which differ in calculation speed and accuracy. The primal solution is the earlier developed and enhanced simulation-based model. The random forest and the neural network models provide a solution trained on the output of the simulation-based model aiming to enhance the calculation speed. Finally, all of the developed solutions are compared to the random selection of escalators. The comparison of the proposed statistical approaches shows that the random forest outperforms the neural networks with a maximum error in the prediction of the overall costs in the range of 10.5% of the simulation-based model solution, while the neural network solution lies within 10%–58%, depending on the targeted value of the power reduction. Statistical approaches enable performing predictions for different times of the day and for new escalator populations without the need for time-demanding simulations. Comparison to the random selection of escalators demonstrates that the proposed models generally outperform the random selection at least seven-fold.

AB - This article relates to the topic of the escalator demand response potential. Previous studies mapped escalators as an unrealized potential for additional demand response. The decrease of the nominal speed is the proposed method of reducing the power consumption of an escalator that comes at the cost of passenger travel time and queuing. This work proposes a solution to a problem of selecting appropriate escalators from a large pool to accommodate the target of power curtailment at a minimum cost and highlights the escalator features that constitute the best demand response candidates. The paper compares four methods which differ in calculation speed and accuracy. The primal solution is the earlier developed and enhanced simulation-based model. The random forest and the neural network models provide a solution trained on the output of the simulation-based model aiming to enhance the calculation speed. Finally, all of the developed solutions are compared to the random selection of escalators. The comparison of the proposed statistical approaches shows that the random forest outperforms the neural networks with a maximum error in the prediction of the overall costs in the range of 10.5% of the simulation-based model solution, while the neural network solution lies within 10%–58%, depending on the targeted value of the power reduction. Statistical approaches enable performing predictions for different times of the day and for new escalator populations without the need for time-demanding simulations. Comparison to the random selection of escalators demonstrates that the proposed models generally outperform the random selection at least seven-fold.

KW - Demand response

KW - Escalators

KW - Modelling

KW - Neural networks

KW - Random forest

KW - Vertical transportation

UR - http://www.scopus.com/inward/record.url?scp=85078833978&partnerID=8YFLogxK

U2 - 10.1016/j.engappai.2020.103521

DO - 10.1016/j.engappai.2020.103521

M3 - Article

AN - SCOPUS:85078833978

VL - 90

JO - ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE

JF - ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE

SN - 0952-1976

M1 - 103521

ER -

ID: 41324346