Day-ahead electricity price forecasting using artificial intelligence-based algorithms

Deregulation and privatization of electricity markets has brought greater attention to electricity price forecasting (EPF) problem in day-ahead and intraday markets since a reliable forecast ensures market participants develop bidding strategies that aim to maximize their profit. Nonlinear and non-stationary characteristics of electricity prices ensemble a barrier in front of an accurate forecast and have required researchers to analyze the effects of exogenous variables such as economic metrics and neighboring countries' prices. In this paper, three different artificial intelligence-based algorithms namely multiple linear regression (MLR), autoregressive integrated moving average (ARIMA) with exogenous variables, and extreme gradient boosting decision trees (XGBoost) are applied to forecast day-ahead electricity prices of the Turkish electricity market by considering the aforementioned exogenous variables. Test results have shown that the XGBoost model has superior results in the error metrics than the other employed methods. Substantial error decrease in symmetric mean absolute percentage error, normalized root mean square error, normalized mean absolute error, and mean absolute scaled error metrics by 19.256%, 19.834%, 23.060%, and 23.016% is observed with respect to the closest performing MLR method on the test set. © 2023 IEEE.