Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.37798/202170389

Deep neural network configuration sensitivity analysis in wind power forecasting

Josip Đaković orcid id orcid.org/0000-0002-3214-5197 ; HEP - Operator distribucijskog sustava, Slavonski Brod, Hrvatska
Bojan Franc ; Sveučilište u Zagrebu Fakultet elektrotehnike i računarstva, Zagreb, Hrvatska
Igor Kuzle orcid id orcid.org/0000-0001-8992-4098 ; Sveučilište u Zagrebu Fakultet elektrotehnike i računarstva, Zagreb, Hrvatska
Yongqian Liu ; North China Electric Power University, New Energy School, Beijing, China


Puni tekst: engleski pdf 1.134 Kb

str. 19-24

preuzimanja: 155

citiraj


Sažetak

The trend toward increasing integration of wind farms into the power system is a challenge for transmission and distribution system operators and electricity market operators. The variability of electricity generation from wind farms increases the requirements for flexibility needed for the reliable and stable operation of the power system. Operating a power system with a high share of renewables requires advanced generation and consumpti-on forecasting methods to ensure the reliable and economical operation of the system. Installed wind power capacities require advanced techniques to monitor and control such data-rich power systems. The rapid development of advanced artificial neural networks and data processing capabilities offers numerous potential applications. The effectiveness of advanced deep recurrent neural networks with long-term memory is constantly being demonstrated for learning complex temporal sequence-to-sequence dependencies. This paper presents the application of deep learning methods to wind power production forecasting. The models are trained using historical wind farm generation measurements and NWP weather forecasts for the areas of Croatian wind farms. Furthermore, a comparison of the accuracy of the proposed models with currently used forecasting tools is presented.

Ključne riječi

Wind power forecasting, deep learning, recurrent neural networks, LSTM, big data analytics, wind farms

Hrčak ID:

289134

URI

https://hrcak.srce.hr/289134

Datum izdavanja:

16.8.2022.

Posjeta: 648 *