| Autors: Zarkov, Z. Z., Stoyanov, L. S., Draganovska, I. I., Lazarov, V. D. Title: The Comparison of different approaches for solar radiation forecasting using Artificial Neural Network Keywords: Artificial neural network, solar radiation forecasting Abstract: The paper presents the comparison of different approaches for forecasting of the solar radiation using artificial neural networks (ANN). Different approaches for this forecasting are possible. One of the most used statistical method is the artificial neural network. The main drawback of this method is the need of large amount of collected data for the network learning. The authors’ team dispose with large database to avoid this disadvantage. Three approaches for the solar radiation forecasting are considered. The difference is in the input variables. The first approach uses information for the solar radiation for 6 days before the forecasted one. The others two approaches use historical data for the forecasted day – respectively 2 and 4 years before this day. For each approach two different topologies are considered – with one and two hidden layers. The results show the advantages and the drawbacks of each approach in function of the topology. References Issue
|
Цитирания (Citation/s):
1. Al-Ornary, M., Albatayneh, A., Aljarrah, R., Alzaareer, K. Reliability Evaluation of GSR Prediction Using Neural Networks with Variant Atmospheric Parameters (2022) 2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022, pp. 1156-1161. - 2022 - в издания, индексирани в Scopus или Web of Science
2. Matushkin, D., & Bosak, A. (2023). DESIGN OF A MATLAB GUI FOR SHORT-TERM SOLAR FORECASTING BASED ON DEEP LEARNING. Vidnovluvana Energetika , (3(74), 32-41. https://doi.org/10.36296/1819-8058.2023.3(74).32-41 - 2023 - от чужди автори в чужди издания, неиндексирани в Scopus или Web of Science
Вид: публикация в национален форум с межд. уч., публикация в реферирано издание, индексирана в Scopus
