An integrated method with adaptive decomposition and machine learning for renewable energy power generation forecasting

Li, Guomin; Yu, Leyi; Zhang, Ying; Sun, Peng; Li, Ruixuan; Zhang, Yagang; Li, Gengyin; Wang, Pengfei

doi:10.1007/s11356-023-25194-3

Cited by 7 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With respect to PV power generation, the off-grid mode is gradually replaced by the grid-connected mode, which means that PV power generation is incorporated into the grid as a microgrid. However, due to the influence of external factors, such as solar radiation fluctuation, PV output power is intermittent and volatile (Wang et al 2023;Li et al 2023), and thus the PV output power prediction is imperative for the grid stability (Liu et al 2022).…”

Section: Introductionmentioning

confidence: 99%

A new hybrid model for photovoltaic output power prediction

Zou,

Wei,

Song

et al. 2023

Environ Sci Pollut Res

View full text Add to dashboard Cite

Recently, with the development of renewable energy technologies, photovoltaic (PV) power generation is widely used in the grid. However, as PV power generation is influenced by external factors, such as solar radiation fluctuation, PV output power is intermittent and volatile, and thus the accurate PV output power prediction is imperative for the grid stability. To address this issue, the artificial rabbits optimization is firstly improved by various strategies, then based on convolutional neural network and bidirectional long short-term memory (CBiLSTM) with improved artificial rabbits optimization (IARO), a new hybrid model denoted by IARO-CBiLSTM is proposed to predict PV output power. Moreover, inputs of IARO-CBiLSTM are optimized by analyzing influential factors of PV output power with Pearson correlation coefficient method. Finally, in order to verify the prediction accuracy, IARO-CBiLSTM is compared with other well-known methods under different weather conditions and different seasons, and the compared results show that IARO-CBiLSTM performs better in terms of various evaluation metrics.

show abstract

Section: Introductionmentioning

confidence: 99%