Combining varying training data-based artificial intelligence models for energy price forecasting

ABSTRACT

In this work, the price-forecasting accuracy of an ensemble of seasonal auto-regressive integrated moving average (SARIMA), multiple linear regression (MLR), feed-forward neural network (FFNN), and radial basis function (RBF) network models has been assessed in a single series modeling framework. The methodology involved training the individual models using past data windows of varying sizes and making the forecast for the next five days on a daily rolling basis. The hourly spot price data of the Iberian Electricity Market (MIBEL) is selected as the test case system. All the models have been tested on high and low-volatile data sets to assess their forecasting abilities. The forecast performance has also been assessed by participating in a real-time forecasting competition and comparing it with the earlier models proposed in the literature. The results show that the ensemble model is effective in producing better forecasts. But its forecast accuracy is greatly affected by the size of the training window and the combination of various models. The ensemble of the FFNN and RBF network models performs best when conditions are volatile. Moreover, during volatile periods it is better to use a small window size for training as compared to a large window size.

COEDITOR-IN-CHIEF:

• Kuo, Cheng-Chien

ASSOCIATE EDITOR:

• Kuo, Cheng-Chien

KEYWORDS:

• Electricity markets
• short-term forecasting
• training framework
• artificial intelligence models

Nomenclature

ACF	=	autocorrelation function
AIC	=	akaike information criterion
ANN	=	artificial neural network
ARMAHX	=	autoregressive moving average hilbertian model with exogenous variables
$B$	=	backward shift operator
BIC	=	bayesian information criterion
CNN	=	convolution neural network
DAM	=	day-ahead market
DMAE	=	daily weighted mean absolute errors
DNN	=	deep neural network
EEPFC	=	energy price forecast competition
EPEX	=	European power exchange
FFNN	=	feed-forward neural network
GRU	=	gated recurrent unit
ITM	=	intraday market
KELM	=	kernel extreme learning machine
LSTM	=	long-short term memory
MCP	=	market clearing price
MAE	=	mean absolute error
MIBEL	=	Iberian Electricity Market
MLE	=	maximum likelihood estimation
MLR	=	multiple linear regression
PACF	=	partial autocorrelation function
PJM	=	Pennsylvania-New Jersey-Maryland
RBF	=	radial basis function
RMSE	=	root mean square error
RNN	=	recurrent neural network
RVM	=	relevance vector machine
SARIMA	=	seasonal AR integrated MA
SMAPE	=	symmetric mean absolute percentage error
WMAE	=	weekly weighted mean AE
WT	=	wavelet transform

Acknowledgments

The authors would like to express their regard to the anonymous editors and reviewers, whose insightful comments contributed to raise the caliber.

Disclosure statement

No potential conflict of interest was reported by the author(s).