Title :
Short-term electricity load forecasting using time series and ensemble learning methods
Author :
Papadopoulos, Sokratis ; Karakatsanis, Ioannis
Author_Institution :
Eng. Syst. & Manage. Dept., Masdar Inst. of Sci. & Technol., Abu Dhabi, United Arab Emirates
Abstract :
Day-ahead electricity load forecasts are presented for the ISO-NE CA area. Four different methods are discussed and compared, namely seasonal autoregressive moving average (SARIMA), seasonal autoregressive moving average with exogenous variable (SARIMAX), random forests (RF) and gradient boosting regression trees (GBRT). The forecasting performance of each model was evaluated by two metrics, namely mean absolute percentage error (MAPE) and root mean square error (RMSE). The results of this study showed that GBRT model is superior to the others for 24 hours ahead forecasts. Based on this study we claim that gradient boosting regression trees can be appropriate for load forecasting applications and yield accurate results.
Keywords :
autoregressive moving average processes; gradient methods; learning (artificial intelligence); load forecasting; mean square error methods; power engineering computing; regression analysis; time series; GBRT; ISO-NE CA area; MAPE; RF; RMSE; SARIMA; SARIMAX; day-ahead electricity load forecasting; ensemble learning methods; exogenous variable; gradient boosting regression trees; mean absolute percentage error; random forests; root mean square error; seasonal autoregressive moving average; short-term electricity load forecasting; time series; yield accurate results; Autoregressive processes; Electricity; Forecasting; Load modeling; Mathematical model; Predictive models; Time series analysis; Electricity load; Ensemble methods; Short-term forecasting; Time series;
Conference_Titel :
Power and Energy Conference at Illinois (PECI), 2015 IEEE
Conference_Location :
Champaign, IL
DOI :
10.1109/PECI.2015.7064913
