2021
DOI: 10.1109/access.2021.3062764
|View full text |Cite
|
Sign up to set email alerts
|

A Multistage Hybrid Model ICEEMDAN-SE-VMD-RDPG for a Multivariate Solar Irradiance Forecasting

Abstract: Accuracy of solar irradiance forecasting is imperative for the effective utilization and integration of solar energy into the power system. To forecast global horizontal irradiance based on a multivariate meteorological data; this study first evaluates five standalone models, including recurrent deterministic policy gradient (RDPG), long short term memory (LSTM) neural network, extreme gradient boosting (XGB), Gaussian process regression (GPR), and support vector regression (SVR). The RDPG model outperforms th… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
5
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 21 publications
(9 citation statements)
references
References 78 publications
0
5
0
Order By: Relevance
“…0: Divide SI data into training and testing sets. 0: Structure SI data as described in (24), and then normalize SI data using (25). 0: while i ≤ n do end To assess the accuracy of HIFA, we use the root mean square error (RMSE) and mean absolute error (MAE), formulated as follows [35]: where N s , SI P and SI E are the numbers of samples, the predicted and observed values of solar irradiance, respectively.…”
Section: Hifa Algorithm and Assessmentmentioning
confidence: 99%
See 1 more Smart Citation
“…0: Divide SI data into training and testing sets. 0: Structure SI data as described in (24), and then normalize SI data using (25). 0: while i ≤ n do end To assess the accuracy of HIFA, we use the root mean square error (RMSE) and mean absolute error (MAE), formulated as follows [35]: where N s , SI P and SI E are the numbers of samples, the predicted and observed values of solar irradiance, respectively.…”
Section: Hifa Algorithm and Assessmentmentioning
confidence: 99%
“…In [24], a k-means technique has been employed to split training sets into many groups, and then GRU has been used with each group. The authors of [25] have assessed 5 standalone models, including recurrent deterministic policy gradient, LSTM, Gaussian process regression, extreme gradient boosting, and support vector regression for solar irradiance forecasting while proposing an improved ensemble method. The study of [26] has adopted a multitask learning method to perform a multi-time scale forecast to enhance the accuracy rate as well as the computational efficiency.…”
Section: Introductionmentioning
confidence: 99%
“…Zhang et al proposed to construct a mixed prediction model of EEMD and LSTM in the prediction of surface temperature, and the empirical results show that the prediction effect of this model is better than that of macshine learning prediction models such as Recurrent Neural Network (RNN), LSTM, and EMD-RNN. [32] developed a two-stage hybrid model, including ICEEMDAN-recurrent deterministic policy gradient (RDPG) and variational mode decomposition-RDPG, to forecast the solar irradiance. [33] proposed a hybrid influent forecasting model based on multimodal and ensemble-based deep learning, showing a good performance in predicting the long-term and short-term loads of circuits.…”
Section: Introductionmentioning
confidence: 99%
“…However, Lahmiri and Boukadoum [30] found that it is not safe to use VMD alone for denoising. To solve the problems caused by using CEEM-DAN and VMD alone, some researchers have used EMDrelated methods in combination with VMD methods in recent years and achieved better results [31][32][33][34]. From these literatures, it can be seen that the combination of the two methods can significantly improve the decomposition process and has a better noise suppression effect than a single one.…”
Section: Introductionmentioning
confidence: 99%