Forecasting Day-Ahead Electricity Prices With A SARIMAX Model

Catherine Mc Hugh; Sonya Coleman; Dermot Kerr; Daniel McGlynn

doi:10.1109/SSCI44817.2019.9002930

Forecasting Day-Ahead Electricity Prices With A SARIMAX Model

Catherine Mc Hugh
, Sonya Coleman
, Dermot Kerr
, Daniel McGlynn

Project Plug Lts T/A Click Energy

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

27 Citations (Scopus)

136 Downloads (Pure)

Abstract

Electricity prices display nonlinear behaviour making it difficult to forecast prices in the market. In addition, various external factors influence electricity prices therefore predicting the day-ahead electricity price is subject to other factors fluctuating. Time-series models learn to follow past market trends and then use historical information as training input to predict future output. This paper focusses on understanding and interpreting statistical approaches for electricity price forecasting and explains these techniques through time-series application with real energy data. The model considered here is a Seasonal AutoRegressive Integrated Moving Average model with eXogenous variables (SARIMAX) as electricity prices follow a seasonal pattern controlled by various external factors. By applying algorithm rules for differencing to remove continuing trends, the data becomes stationary and parameters, 14 external factors, are chosen to predict day ahead electricity prices. In the presented experimental results, the Root Mean Square Error (RMSE) was reasonably low and the model accurately predicted electricity prices.

Original language	English
Title of host publication	The 2019 IEEE Symposium Series on Computational Intelligence
Place of Publication	Xiamen, China
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1523-1529
Number of pages	7
ISBN (Electronic)	9781728124858
ISBN (Print)	978-1-7281-2486-5
DOIs	https://doi.org/10.1109/SSCI44817.2019.9002930
Publication status	Published (in print/issue) - 20 Feb 2020
Event	2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019 - Xiamen, China Duration: 6 Dec 2019 → 9 Dec 2019

Publication series

Name	2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

Conference

Conference	2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019
Country/Territory	China
City	Xiamen
Period	6/12/19 → 9/12/19

Funding

ACKNOWLEDGMENT This work was funded through DfE CAST scholarship in collaboration with Click Energy.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Electricity price forecasting
SARIMAX modelling
Short-term
Seasonality
Exogenous variables

Access to Document

10.1109/SSCI44817.2019.9002930

SSCI2019_AcceptanceVersionAuthor Accepted Manuscript, 419 KB

Cite this

Mc Hugh, C., Coleman, S., Kerr, D., & McGlynn, D. (2020). Forecasting Day-Ahead Electricity Prices With A SARIMAX Model. In The 2019 IEEE Symposium Series on Computational Intelligence (pp. 1523-1529). Article 9002930 (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSCI44817.2019.9002930

@inproceedings{91fb85a214c64d739e8b6db8d93ba13b,

title = "Forecasting Day-Ahead Electricity Prices With A SARIMAX Model",

abstract = "Electricity prices display nonlinear behaviour making it difficult to forecast prices in the market. In addition, various external factors influence electricity prices therefore predicting the day-ahead electricity price is subject to other factors fluctuating. Time-series models learn to follow past market trends and then use historical information as training input to predict future output. This paper focusses on understanding and interpreting statistical approaches for electricity price forecasting and explains these techniques through time-series application with real energy data. The model considered here is a Seasonal AutoRegressive Integrated Moving Average model with eXogenous variables (SARIMAX) as electricity prices follow a seasonal pattern controlled by various external factors. By applying algorithm rules for differencing to remove continuing trends, the data becomes stationary and parameters, 14 external factors, are chosen to predict day ahead electricity prices. In the presented experimental results, the Root Mean Square Error (RMSE) was reasonably low and the model accurately predicted electricity prices.",

keywords = "Electricity price forecasting, SARIMAX modelling, Short-term, Seasonality, Exogenous variables",

author = "\{Mc Hugh\}, Catherine and Sonya Coleman and Dermot Kerr and Daniel McGlynn",

year = "2020",

month = feb,

day = "20",

doi = "10.1109/SSCI44817.2019.9002930",

language = "English",

isbn = "978-1-7281-2486-5",

series = "2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1523--1529",

booktitle = "The 2019 IEEE Symposium Series on Computational Intelligence",

address = "United States",

note = "2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019 ; Conference date: 06-12-2019 Through 09-12-2019",

}

Mc Hugh, C, Coleman, S , Kerr, D & McGlynn, D 2020, Forecasting Day-Ahead Electricity Prices With A SARIMAX Model. in The 2019 IEEE Symposium Series on Computational Intelligence., 9002930, 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019, Institute of Electrical and Electronics Engineers Inc., Xiamen, China, pp. 1523-1529, 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019, Xiamen, China, 6/12/19. https://doi.org/10.1109/SSCI44817.2019.9002930

Forecasting Day-Ahead Electricity Prices With A SARIMAX Model. / Mc Hugh, Catherine; Coleman, Sonya ; Kerr, Dermot et al.
The 2019 IEEE Symposium Series on Computational Intelligence. Xiamen, China: Institute of Electrical and Electronics Engineers Inc., 2020. p. 1523-1529 9002930 (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019).

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

TY - GEN

T1 - Forecasting Day-Ahead Electricity Prices With A SARIMAX Model

AU - Mc Hugh, Catherine

AU - Coleman, Sonya

AU - Kerr, Dermot

AU - McGlynn, Daniel

PY - 2020/2/20

Y1 - 2020/2/20

N2 - Electricity prices display nonlinear behaviour making it difficult to forecast prices in the market. In addition, various external factors influence electricity prices therefore predicting the day-ahead electricity price is subject to other factors fluctuating. Time-series models learn to follow past market trends and then use historical information as training input to predict future output. This paper focusses on understanding and interpreting statistical approaches for electricity price forecasting and explains these techniques through time-series application with real energy data. The model considered here is a Seasonal AutoRegressive Integrated Moving Average model with eXogenous variables (SARIMAX) as electricity prices follow a seasonal pattern controlled by various external factors. By applying algorithm rules for differencing to remove continuing trends, the data becomes stationary and parameters, 14 external factors, are chosen to predict day ahead electricity prices. In the presented experimental results, the Root Mean Square Error (RMSE) was reasonably low and the model accurately predicted electricity prices.

AB - Electricity prices display nonlinear behaviour making it difficult to forecast prices in the market. In addition, various external factors influence electricity prices therefore predicting the day-ahead electricity price is subject to other factors fluctuating. Time-series models learn to follow past market trends and then use historical information as training input to predict future output. This paper focusses on understanding and interpreting statistical approaches for electricity price forecasting and explains these techniques through time-series application with real energy data. The model considered here is a Seasonal AutoRegressive Integrated Moving Average model with eXogenous variables (SARIMAX) as electricity prices follow a seasonal pattern controlled by various external factors. By applying algorithm rules for differencing to remove continuing trends, the data becomes stationary and parameters, 14 external factors, are chosen to predict day ahead electricity prices. In the presented experimental results, the Root Mean Square Error (RMSE) was reasonably low and the model accurately predicted electricity prices.

KW - Electricity price forecasting

KW - SARIMAX modelling

KW - Short-term

KW - Seasonality

KW - Exogenous variables

UR - https://www.scopus.com/pages/publications/85080936115

UR - http://ssci2019.org/

U2 - 10.1109/SSCI44817.2019.9002930

DO - 10.1109/SSCI44817.2019.9002930

M3 - Conference contribution

AN - SCOPUS:85080936115

SN - 978-1-7281-2486-5

T3 - 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

SP - 1523

EP - 1529

BT - The 2019 IEEE Symposium Series on Computational Intelligence

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Xiamen, China

T2 - 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

Y2 - 6 December 2019 through 9 December 2019

ER -

Mc Hugh C, Coleman S , Kerr D, McGlynn D. Forecasting Day-Ahead Electricity Prices With A SARIMAX Model. In The 2019 IEEE Symposium Series on Computational Intelligence. Xiamen, China: Institute of Electrical and Electronics Engineers Inc. 2020. p. 1523-1529. 9002930. (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019). doi: 10.1109/SSCI44817.2019.9002930

Forecasting Day-Ahead Electricity Prices With A SARIMAX Model

Abstract

Publication series

Conference

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Algorithmic approaches to energy market price prediction

Cite this

Forecasting Day-Ahead Electricity Prices With A SARIMAX Model

Abstract

Publication series

Conference

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Student theses

Algorithmic approaches to energy market price prediction

Cite this