Multi-step time series forecasting of electric load using machine learning models

Shamsul Masum; Ying Liu; John Chiverton

doi:10.1007/978-3-319-91253-0_15

Multi-step time series forecasting of electric load using machine learning models

Shamsul Masum, Ying Liu, John Chiverton

Centre for Healthcare Modelling & Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1601 Downloads (Pure)

Abstract

Multi-step forecasting is very challenging and there are a lack of studies available that consist of machine learning algorithms and methodologies for multi-step forecasting. It has also been found that lack of collaborations between these different fields is creating a barrier to further developments. In this paper, multi-step time series forecasting are performed on three nonlinear electric load datasets extracted from Open-Power-System-Data.org using two machine learning models. Multi-step forecasting performance of Auto-Regressive Integrated Moving Average (ARIMA) and Long-Short-Term-Memory (LSTM) based Recurrent Neural Networks (RNN) models are compared. Comparative analysis of forecasting performance of the two models reveals that the LSTM model has superior performance in comparison to the ARIMA model for multi-step electric load forecasting.

Original language	English
Title of host publication	17th International Conference on Artificial Intelligence and Soft Computing
Subtitle of host publication	ICAISC 2018
Editors	Leszek Rutkowski, Rafał Scherer, Marcin Korytkowski, Witold Pedrycz, Ryszard Tadeusiewicz, Jacek Zurada
Publisher	Springer Nature
Pages	148-159
Number of pages	12
ISBN (Electronic)	978-3-319-91253-0
ISBN (Print)	978-3-319-91252-3
DOIs	https://doi.org/10.1007/978-3-319-91253-0_15
Publication status	Published - Jun 2018
Event	International Conference on Artificial Intelligence and Soft Computing - Mercure Zakopane Kasprowy Hotel, Zakopane, Poland Duration: 3 Jun 2018 → 7 Jun 2018 Conference number: 17th http://icaisc.eu/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	10841
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	International Conference on Artificial Intelligence and Soft Computing
Abbreviated title	ICAISC 2018
Country/Territory	Poland
City	Zakopane
Period	3/06/18 → 7/06/18
Internet address	http://icaisc.eu/

Keywords

ARIMA
LSTM
Multi-step forecasting
Time Series Analysis

Access to Document

10.1007/978-3-319-91253-0_15

5234
The final authenticated version is available online at: http://dx.doi.org/10.1007%2F978-3-319-91253-0_15.
Accepted author manuscript (Post-print), 389 KB

Cite this

Masum, S., Liu, Y., & Chiverton, J. (2018). Multi-step time series forecasting of electric load using machine learning models. In L. Rutkowski, R. Scherer, M. Korytkowski, W. Pedrycz, R. Tadeusiewicz, & J. Zurada (Eds.), 17th International Conference on Artificial Intelligence and Soft Computing: ICAISC 2018 (pp. 148-159). (Lecture Notes in Computer Science ; Vol. 10841). Springer Nature. https://doi.org/10.1007/978-3-319-91253-0_15

Masum, Shamsul ; Liu, Ying ; Chiverton, John. / Multi-step time series forecasting of electric load using machine learning models. 17th International Conference on Artificial Intelligence and Soft Computing: ICAISC 2018. editor / Leszek Rutkowski ; Rafał Scherer ; Marcin Korytkowski ; Witold Pedrycz ; Ryszard Tadeusiewicz ; Jacek Zurada. Springer Nature, 2018. pp. 148-159 (Lecture Notes in Computer Science ).

@inproceedings{26e317389f3744dbbfcdfe4b03d9fc19,

title = "Multi-step time series forecasting of electric load using machine learning models",

abstract = "Multi-step forecasting is very challenging and there are a lack of studies available that consist of machine learning algorithms and methodologies for multi-step forecasting. It has also been found that lack of collaborations between these different fields is creating a barrier to further developments. In this paper, multi-step time series forecasting are performed on three nonlinear electric load datasets extracted from Open-Power-System-Data.org using two machine learning models. Multi-step forecasting performance of Auto-Regressive Integrated Moving Average (ARIMA) and Long-Short-Term-Memory (LSTM) based Recurrent Neural Networks (RNN) models are compared. Comparative analysis of forecasting performance of the two models reveals that the LSTM model has superior performance in comparison to the ARIMA model for multi-step electric load forecasting.",

keywords = "ARIMA, LSTM, Multi-step forecasting, Time Series Analysis",

author = "Shamsul Masum and Ying Liu and John Chiverton",

year = "2018",

month = jun,

doi = "10.1007/978-3-319-91253-0_15",

language = "English",

isbn = "978-3-319-91252-3",

series = "Lecture Notes in Computer Science ",

publisher = "Springer Nature",

pages = "148--159",

editor = "Leszek Rutkowski and Rafa{\l} Scherer and Marcin Korytkowski and Witold Pedrycz and Ryszard Tadeusiewicz and Jacek Zurada",

booktitle = "17th International Conference on Artificial Intelligence and Soft Computing",

note = "International Conference on Artificial Intelligence and Soft Computing, ICAISC 2018 ; Conference date: 03-06-2018 Through 07-06-2018",

url = "http://icaisc.eu/",

}

Masum, S, Liu, Y & Chiverton, J 2018, Multi-step time series forecasting of electric load using machine learning models. in L Rutkowski, R Scherer, M Korytkowski, W Pedrycz, R Tadeusiewicz & J Zurada (eds), 17th International Conference on Artificial Intelligence and Soft Computing: ICAISC 2018. Lecture Notes in Computer Science , vol. 10841, Springer Nature, pp. 148-159, International Conference on Artificial Intelligence and Soft Computing, Zakopane, Poland, 3/06/18. https://doi.org/10.1007/978-3-319-91253-0_15

Multi-step time series forecasting of electric load using machine learning models. / Masum, Shamsul; Liu, Ying; Chiverton, John.

17th International Conference on Artificial Intelligence and Soft Computing: ICAISC 2018. ed. / Leszek Rutkowski; Rafał Scherer; Marcin Korytkowski; Witold Pedrycz; Ryszard Tadeusiewicz; Jacek Zurada. Springer Nature, 2018. p. 148-159 (Lecture Notes in Computer Science ; Vol. 10841).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Multi-step time series forecasting of electric load using machine learning models

AU - Masum, Shamsul

AU - Liu, Ying

AU - Chiverton, John

N1 - Conference code: 17th

PY - 2018/6

Y1 - 2018/6

N2 - Multi-step forecasting is very challenging and there are a lack of studies available that consist of machine learning algorithms and methodologies for multi-step forecasting. It has also been found that lack of collaborations between these different fields is creating a barrier to further developments. In this paper, multi-step time series forecasting are performed on three nonlinear electric load datasets extracted from Open-Power-System-Data.org using two machine learning models. Multi-step forecasting performance of Auto-Regressive Integrated Moving Average (ARIMA) and Long-Short-Term-Memory (LSTM) based Recurrent Neural Networks (RNN) models are compared. Comparative analysis of forecasting performance of the two models reveals that the LSTM model has superior performance in comparison to the ARIMA model for multi-step electric load forecasting.

AB - Multi-step forecasting is very challenging and there are a lack of studies available that consist of machine learning algorithms and methodologies for multi-step forecasting. It has also been found that lack of collaborations between these different fields is creating a barrier to further developments. In this paper, multi-step time series forecasting are performed on three nonlinear electric load datasets extracted from Open-Power-System-Data.org using two machine learning models. Multi-step forecasting performance of Auto-Regressive Integrated Moving Average (ARIMA) and Long-Short-Term-Memory (LSTM) based Recurrent Neural Networks (RNN) models are compared. Comparative analysis of forecasting performance of the two models reveals that the LSTM model has superior performance in comparison to the ARIMA model for multi-step electric load forecasting.

KW - ARIMA

KW - LSTM

KW - Multi-step forecasting

KW - Time Series Analysis

U2 - 10.1007/978-3-319-91253-0_15

DO - 10.1007/978-3-319-91253-0_15

M3 - Conference contribution

SN - 978-3-319-91252-3

T3 - Lecture Notes in Computer Science

SP - 148

EP - 159

BT - 17th International Conference on Artificial Intelligence and Soft Computing

A2 - Rutkowski, Leszek

A2 - Scherer, Rafał

A2 - Korytkowski, Marcin

A2 - Pedrycz, Witold

A2 - Tadeusiewicz, Ryszard

A2 - Zurada, Jacek

PB - Springer Nature

T2 - International Conference on Artificial Intelligence and Soft Computing

Y2 - 3 June 2018 through 7 June 2018

ER -

Masum S, Liu Y, Chiverton J. Multi-step time series forecasting of electric load using machine learning models. In Rutkowski L, Scherer R, Korytkowski M, Pedrycz W, Tadeusiewicz R, Zurada J, editors, 17th International Conference on Artificial Intelligence and Soft Computing: ICAISC 2018. Springer Nature. 2018. p. 148-159. (Lecture Notes in Computer Science ). Epub 2018 May 11. doi: 10.1007/978-3-319-91253-0_15

Multi-step time series forecasting of electric load using machine learning models

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this