Research on short-term photovoltaic power prediction based on multi-scale similar days and ESN-KELM dual core prediction model

Naiqing Li, Longhao Li, Fan Zhang, Ticao Jiao, Shuang Wang, Xuefeng Liu and Xinghua Wu

Energy, 2023, vol. 277, issue C

Abstract: Photovoltaic (PV) power generation has emerged as an essential means of developing and utilizing new energy. Accurate PV power prediction is critical for building a new power system generation and guaranteeing system stability when a high proportion of renewable energy is connected. Therefore, this research proposes a hybrid prediction method based on multi-scale similar days and ESN-KELM dual-kernel prediction to increase the prediction accuracy of PV power generation. First, the multi-scale similar days algorithm is used to determine similar days of the forecast day as the model training data. This operation can reduce the impact of the randomness of PV power output on the model performance. Second, the hidden features of PV power are mined using a fast iterative filter decomposition method. Based on the complexity of the components, the corresponding ESN-KELM dual-kernel prediction models are established. An improved Archimedes optimization approach is used to optimize the ESN-KELM model's parameters. Next, the predicted power is obtained by aggregating the predicted results of each component. Ultimately, the method is validated using historical operational data from PV power plants. The results indicate that the proposed model can achieve well prediction results for various seasons and weather conditions.

Keywords: Photovoltaic power prediction; Fast iterative filter decomposition; Multiscale similar days; Improved archimedes algorithm; Kernel extreme learning machine; Echo state network (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223009519
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:277:y:2023:i:c:s0360544223009519

DOI: 10.1016/j.energy.2023.127557

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().