TY - GEN
T1 - A New Hybrid Forecasting Model for Solar Energy Output
AU - Abedinia, Oveis
AU - Sobhani, Behrouz
AU - Bagheri, Mehdi
N1 - Funding Information:
ACKNOWLEDGMENT The authors acknowledge the financial support of this study provided by the Collaborative Research Project (CRP) Grant of Nazarbayev University under grant no. (021220CRP0322).
Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In recent years, photovoltaic solar power plants have been widely adopted worldwide due to their favorable energy potential and accessibility. However, despite its accessibility, the output power characteristics of solar energy are inherently unstable. When integrating this energy generation into the power grid, the presence of unbalanced electric currents can adversely affect various control components of the system. Consequently, there is a growing demand for accurate short-term power forecasting. This paper introduces a novel hybrid model to address the aforementioned challenge. The proposed method encompasses three interconnected networks: Boost by Refinement (BF), Mixture of Experts (MoE), and Enhanced MoE (EMoE). Within these networks, the problem space is initially divided into distinct classes, which are then combined using a specific approach. The obtained results provide compelling evidence supporting the effectiveness and superiority of the proposed method.
AB - In recent years, photovoltaic solar power plants have been widely adopted worldwide due to their favorable energy potential and accessibility. However, despite its accessibility, the output power characteristics of solar energy are inherently unstable. When integrating this energy generation into the power grid, the presence of unbalanced electric currents can adversely affect various control components of the system. Consequently, there is a growing demand for accurate short-term power forecasting. This paper introduces a novel hybrid model to address the aforementioned challenge. The proposed method encompasses three interconnected networks: Boost by Refinement (BF), Mixture of Experts (MoE), and Enhanced MoE (EMoE). Within these networks, the problem space is initially divided into distinct classes, which are then combined using a specific approach. The obtained results provide compelling evidence supporting the effectiveness and superiority of the proposed method.
KW - hybrid model
KW - neural networks
KW - prediction
KW - solar energy
UR - http://www.scopus.com/inward/record.url?scp=85168705486&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85168705486&partnerID=8YFLogxK
U2 - 10.1109/EEEIC/ICPSEurope57605.2023.10194845
DO - 10.1109/EEEIC/ICPSEurope57605.2023.10194845
M3 - Conference contribution
AN - SCOPUS:85168705486
T3 - Proceedings - 2023 IEEE International Conference on Environment and Electrical Engineering and 2023 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2023
BT - Proceedings - 2023 IEEE International Conference on Environment and Electrical Engineering and 2023 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2023
A2 - Leonowicz, Zbigniew
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Conference on Environment and Electrical Engineering and 2023 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2023
Y2 - 6 June 2023 through 9 June 2023
ER -
