Short-term Kinetic Energy Forecast using a Structural Time Series Model: Study Case of Nordic Power System (CROSBI ID 697017)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Gonzalez-Longatt, Francisco ; Acosta, Martha N. ; Chamorro, Harold R. ; Topić, Danijel
engleski
Short-term Kinetic Energy Forecast using a Structural Time Series Model: Study Case of Nordic Power System
Modern power systems are experiencing a gradual substitution of the classical synchronous generators by power electronic-based technologies ; as a consequence, there is an increased interested in estimating the total rotating inertia. This paper proposes the use of the decomposable time series model to short term forecast of the total kinetic energy (KE) of a power system. The structure of the forecasting model includes three main components: trend, a seasonal and an irregular component. As the Nordic Power System (NPS) is expected a reduction of the total kinetic energy, this paper uses a time series of KE to test the proposed approach. A cross-validation process is used in this paper, numerical results of the mean absolute percentage error indicate forecast the error in the forecasting is below 5% for predictions one hour into the future.
Time series analysis , Predictive models , Forecasting , Data models , Mathematical model , Market research , Kinetic energy
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1-6.
2020.
objavljeno
10.1109/SST49455.2020.9264087
Podaci o matičnoj publikaciji
Proceedings of 2020 International Conference on Smart Systems and Technologies (SST)
Žagar, Drago
Osijek: Faculty of Electrical engineering, computer science and information technology Osijek
978-1-7281-9759-3
Podaci o skupu
International Conference on Smart Systems and Technologies 2020 (SST 2020)
predavanje
14.10.2020-16.10.2020
Osijek, Hrvatska