A Linear Polynomial NARMAX Model with Multiple Factors to Forecast Day-Ahead Electricity Prices

Catherine McHugh, Sonya Coleman, Dermot Kerr, Daniel McGlynn

Research output: Contribution to conferencePaper

Abstract

Forecasting algorithms are a valuable mechanism to aid in the prediction of future prices. Although various black-box modelling techniques have been applied to variations of this problem, we focus on the use of transparent models to enable understanding and interpretation of the developed model. We utilize a Nonlinear AutoRegressive Moving Average model with eXogenous input (NARMAX) for electricity price forecasting using multiple input factors. Energy data from a 14-week period in 2017 were analyzed to determine whether a NARMAX model could accurately predict day-ahead electricity prices and to check which input factors in the model were most significant. The model considered the closely correlated lags and included 13 input factors. There were two models developed in order to determine which variables played an important role in predicting future prices. Experimental results indicate that previous price, demand, gas, coal, and nuclear are the most significant factors that influence electricity prices. Gas was the highest weighted factor for both developed models. Previous price yielded the biggest Error Reduction Ratio (ERR), but when not included in the model, demand generated the biggest ERR value. To summarize a NARMAX model with an input regression lag of one and previous price included generates the best day-ahead forecast of electricity prices.

Conference

ConferenceSYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE
Abbreviated titleCiFER
CountryIndia
CityBenguluru
Period18/11/1820/11/18

Fingerprint

Electricity
Statistical Models
Coal gas
Gases

Keywords

  • NARMAX
  • Electricity price forecasting
  • Multiple factors
  • Energy market

Cite this

McHugh, C., Coleman, S., Kerr, D., & McGlynn, D. (Accepted/In press). A Linear Polynomial NARMAX Model with Multiple Factors to Forecast Day-Ahead Electricity Prices. Paper presented at SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE, Benguluru, India.
McHugh, Catherine ; Coleman, Sonya ; Kerr, Dermot ; McGlynn, Daniel. / A Linear Polynomial NARMAX Model with Multiple Factors to Forecast Day-Ahead Electricity Prices. Paper presented at SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE, Benguluru, India.6 p.
@conference{be7da9a47af84af9afaced46cf919fdb,
title = "A Linear Polynomial NARMAX Model with Multiple Factors to Forecast Day-Ahead Electricity Prices",
abstract = "Forecasting algorithms are a valuable mechanism to aid in the prediction of future prices. Although various black-box modelling techniques have been applied to variations of this problem, we focus on the use of transparent models to enable understanding and interpretation of the developed model. We utilize a Nonlinear AutoRegressive Moving Average model with eXogenous input (NARMAX) for electricity price forecasting using multiple input factors. Energy data from a 14-week period in 2017 were analyzed to determine whether a NARMAX model could accurately predict day-ahead electricity prices and to check which input factors in the model were most significant. The model considered the closely correlated lags and included 13 input factors. There were two models developed in order to determine which variables played an important role in predicting future prices. Experimental results indicate that previous price, demand, gas, coal, and nuclear are the most significant factors that influence electricity prices. Gas was the highest weighted factor for both developed models. Previous price yielded the biggest Error Reduction Ratio (ERR), but when not included in the model, demand generated the biggest ERR value. To summarize a NARMAX model with an input regression lag of one and previous price included generates the best day-ahead forecast of electricity prices.",
keywords = "NARMAX, Electricity price forecasting, Multiple factors, Energy market",
author = "Catherine McHugh and Sonya Coleman and Dermot Kerr and Daniel McGlynn",
year = "2018",
month = "9",
day = "1",
language = "English",
note = "SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE : IEEE Symposium on Computational Intelligence for Financial Engineering and Economics, CiFER ; Conference date: 18-11-2018 Through 20-11-2018",

}

McHugh, C, Coleman, S, Kerr, D & McGlynn, D 2018, 'A Linear Polynomial NARMAX Model with Multiple Factors to Forecast Day-Ahead Electricity Prices' Paper presented at SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE, Benguluru, India, 18/11/18 - 20/11/18, .

A Linear Polynomial NARMAX Model with Multiple Factors to Forecast Day-Ahead Electricity Prices. / McHugh, Catherine; Coleman, Sonya; Kerr, Dermot; McGlynn, Daniel.

2018. Paper presented at SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE, Benguluru, India.

Research output: Contribution to conferencePaper

TY - CONF

T1 - A Linear Polynomial NARMAX Model with Multiple Factors to Forecast Day-Ahead Electricity Prices

AU - McHugh, Catherine

AU - Coleman, Sonya

AU - Kerr, Dermot

AU - McGlynn, Daniel

PY - 2018/9/1

Y1 - 2018/9/1

N2 - Forecasting algorithms are a valuable mechanism to aid in the prediction of future prices. Although various black-box modelling techniques have been applied to variations of this problem, we focus on the use of transparent models to enable understanding and interpretation of the developed model. We utilize a Nonlinear AutoRegressive Moving Average model with eXogenous input (NARMAX) for electricity price forecasting using multiple input factors. Energy data from a 14-week period in 2017 were analyzed to determine whether a NARMAX model could accurately predict day-ahead electricity prices and to check which input factors in the model were most significant. The model considered the closely correlated lags and included 13 input factors. There were two models developed in order to determine which variables played an important role in predicting future prices. Experimental results indicate that previous price, demand, gas, coal, and nuclear are the most significant factors that influence electricity prices. Gas was the highest weighted factor for both developed models. Previous price yielded the biggest Error Reduction Ratio (ERR), but when not included in the model, demand generated the biggest ERR value. To summarize a NARMAX model with an input regression lag of one and previous price included generates the best day-ahead forecast of electricity prices.

AB - Forecasting algorithms are a valuable mechanism to aid in the prediction of future prices. Although various black-box modelling techniques have been applied to variations of this problem, we focus on the use of transparent models to enable understanding and interpretation of the developed model. We utilize a Nonlinear AutoRegressive Moving Average model with eXogenous input (NARMAX) for electricity price forecasting using multiple input factors. Energy data from a 14-week period in 2017 were analyzed to determine whether a NARMAX model could accurately predict day-ahead electricity prices and to check which input factors in the model were most significant. The model considered the closely correlated lags and included 13 input factors. There were two models developed in order to determine which variables played an important role in predicting future prices. Experimental results indicate that previous price, demand, gas, coal, and nuclear are the most significant factors that influence electricity prices. Gas was the highest weighted factor for both developed models. Previous price yielded the biggest Error Reduction Ratio (ERR), but when not included in the model, demand generated the biggest ERR value. To summarize a NARMAX model with an input regression lag of one and previous price included generates the best day-ahead forecast of electricity prices.

KW - NARMAX

KW - Electricity price forecasting

KW - Multiple factors

KW - Energy market

M3 - Paper

ER -

McHugh C, Coleman S, Kerr D, McGlynn D. A Linear Polynomial NARMAX Model with Multiple Factors to Forecast Day-Ahead Electricity Prices. 2018. Paper presented at SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE, Benguluru, India.