TY - GEN
T1 - Comparison of Medium-Term Load Forecasting Methods (Splitted Linear Regression and Artificial Neural Networks) in Electricity Systems Located in Tropical Regions
AU - Setiawan, Agus
AU - Arifin, Zainal
AU - Sudiarto, Budi
AU - Jufri, Fauzan Hanif
AU - Haramaini, Qasthalani
AU - Garniwa, Iwa
N1 - Funding Information:
ACKNOWLEDGMENT This research was supported by PT PLN (Persero). We thank all parties involved who provided data, insight, and expertise that greatly assisted the research, as well as comments and reviews which helped bring this research to complete fruition.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Load forecasting for the medium term to supply power plants within 1 month, can optimize the economic dispatch of generators that will be used to supply large systems. The accuracy of forecasting the half-hourly load will result in a more efficient electricity supply in a system that uses flat rates on the utility side. In this paper, the author tries to compare the forecasting methods of linear regression, Artificial Neural Networks, and Splitted Linear Regression. This method is applied to the largest system in Indonesia, a country located at the tropical region which has different characteristics from countries that have four seasons. At the end of this study, it can be concluded that the Splitted Linear Regression method has the highest performance with the lowest MAPE value of 2.63%.
AB - Load forecasting for the medium term to supply power plants within 1 month, can optimize the economic dispatch of generators that will be used to supply large systems. The accuracy of forecasting the half-hourly load will result in a more efficient electricity supply in a system that uses flat rates on the utility side. In this paper, the author tries to compare the forecasting methods of linear regression, Artificial Neural Networks, and Splitted Linear Regression. This method is applied to the largest system in Indonesia, a country located at the tropical region which has different characteristics from countries that have four seasons. At the end of this study, it can be concluded that the Splitted Linear Regression method has the highest performance with the lowest MAPE value of 2.63%.
KW - deep learning load forecasting
KW - MAPE
KW - medium-term load forecasting
KW - Splitted linear regression
UR - http://www.scopus.com/inward/record.url?scp=85146111435&partnerID=8YFLogxK
U2 - 10.1109/CGEE55282.2022.9976521
DO - 10.1109/CGEE55282.2022.9976521
M3 - Conference contribution
AN - SCOPUS:85146111435
T3 - 2022 3rd International Conference on Clean and Green Energy Engineering, CGEE 2022
SP - 84
EP - 88
BT - 2022 3rd International Conference on Clean and Green Energy Engineering, CGEE 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd International Conference on Clean and Green Energy Engineering, CGEE 2022
Y2 - 28 August 2022 through 30 August 2022
ER -
