Hour-ahead photovoltaic power forecast using a hybrid GRA-LSTM model based on multivariate meteorological factors and historical power datasets

Chen, Biaowei; Lin, Peijie; Lin, Yi; Lai, Yunfeng; Cheng, Shuying; Chen, Zhicong; Wu, Lijun

doi:10.1088/1755-1315/431/1/012059

Cited by 8 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data sets were created with identical time window sizes and proportions to ensure a uniform experimental environment. To benchmark the proposed model, we compared it with various statistical models such as ARIMAX, exponential smoothing (ES), and GPR [19], which are well-suited for large datasets, as well as machine learning-based models including XGBOOST [26], SVM[100], and deep learning-based models such as CNN [28], LSTM [29], GRU [30], LSTM-Attention(LSTM-A) [31], CNN-LSTM [32], and ConvLSTM [33]. The parameters of all algorithms in the comparison test are optimized for this situation, and the significant hyperparameter settings of all the models mentioned above are shown in TABLE IV.…”

Section: Comparative Experimentalmentioning

confidence: 99%

“…Further analysis of the basic weather types, such as sunny, cloudy, and rainy, is carried out using readily available meteorological data [14], [15], [16]. To find a method that can obtain appropriate training samples under various complicated weather conditions, indicators such as cosine similarity [17], Euclidean distance [18], and gray correlation [19] are often adopted to evaluate the similarity among samples. Furthermore, historical samples whose indicators are higher than the threshold value are selected as training sets and verification sets to analyze the similarity of PV power between the forecast day and the historical sample.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Two-Stage Method for Ultra-Short-Term PV Power Forecasting Based on Data-Driven

et al. 2023

View full text Add to dashboard Cite

To promote the real-time dispatching of a power grid and balanced decision-making of power producers, accuracy and real-time forecasting are two main problems that need to be solved in ultra-shortterm photovoltaic (PV) forecasting. Focusing on the problems of slow model training speed and low forecasting accuracy due to the redundancy of training data samples and insufficient long periodic capture of data in complex weather, this paper proposes a two-stage method for ultra-short-term PV power forecasting based on data-driven. In the meteorological analysis stage, the generation power samples similar to the forecast day were extracted by inputting daily meteorological features and using maximal information coefficient (MIC) weighted grey correlation degree to form the corresponding forecast data set. In the power forecasting stage, the temporal convolutional used network (TCN) extracts local features to maintain the sequence of extracted features. Then the bidirectional gating unit (BiGRU) combined with the Skip connection strategy was used to fully learn the long and the short time sequence of photovoltaic sequences, and the attention mechanism was used to pay adaptive attention to the more important historical states. This study experimented on the measured data from a photovoltaic power station in Southeastern China. The experimental results show that this method is effective in photovoltaic power short-term forecasts. In addition, compared with some traditional forecasting models, this method has smaller forecasting errors and higher robustness in the time scales of 15 minutes, 30 minutes, 45 minutes, and 60 minutes.

show abstract

Section: Comparative Experimentalmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Two-Stage Method for Ultra-Short-Term PV Power Forecasting Based on Data-Driven

et al. 2023

View full text Add to dashboard Cite

show abstract

“…When predicting the fertilization of forests, Chen et al [32] discovered that the gray relation analysis-particle swarm optimization-back-propagation (GRA-PSO-BP) model was more reliable than the BP and BP-PSO models. Chen and Lin [33] found that the GRA-LSTM model was robust in the short-term forecasting of PV power plants. Chen et al [34] developed the GRA-NARX model to forecast changes of dissolved oxygen mass concentration in surface water; however, the model's accuracy tends to decline with time.…”

Section: Introductionmentioning

confidence: 99%

A Novel GRA-NARX Model for Water Level Prediction of Pumping Stations

Liu

Lei

et al. 2022

Water

View full text Add to dashboard Cite

It is necessary but difficult to accurately predict the water levels in front of the pumping stations of an open-channel water transfer project because of the complex interactions among hydraulic structures. In this study, a novel GRA-NARX (gray relation analysis—nonlinear auto-regressive exogenous) model is proposed based on a gray relation analysis (GRA) and nonlinear auto-regressive exogenous (NARX) neural network for 2 h ahead for the prediction of water levels in front of pumping stations, in which an improved algorithm of the NARX neural network is used to obtain the optimal combination of the time delay and the hidden neurons number, and GRA is used to reduce the prediction complexity and improve the prediction accuracy by filtering input factors. Then, the sensitivity to changes of the training algorithm is analyzed, and the prediction performance is compared with that of the NARX and GRA-BP (gray relation analysis back-propagation) models. A case study is performed in the Tundian pumping station of the Miyun project, China, to demonstrate the reliability and accuracy of the proposed model. It is revealed that the GRA-NARX-BR (gray relation analysis—nonlinear auto-regressive exogenous—Bayesian regularization) model has higher accuracy than the model based only on a NARX neural network and the GRA-BP model with a correlation coefficient (R) of 0.9856 and a mean absolute error (MAE) of 0.00984 m. The proposed model is effective in predicting the water levels in front of the pumping stations of a complex open-channel water transfer project.

show abstract

Big Data and Deep Learning Analytics for Robust PV Power Forecast in Smart Grids

Zhang

Wang

Dehghanian

2021

Advanced Technologies for Solar Photovoltaics Energy Systems

View full text Add to dashboard Cite

Hour-ahead photovoltaic power forecast using a hybrid GRA-LSTM model based on multivariate meteorological factors and historical power datasets

Cited by 8 publications

References 10 publications

A Two-Stage Method for Ultra-Short-Term PV Power Forecasting Based on Data-Driven

A Two-Stage Method for Ultra-Short-Term PV Power Forecasting Based on Data-Driven

A Novel GRA-NARX Model for Water Level Prediction of Pumping Stations

Big Data and Deep Learning Analytics for Robust PV Power Forecast in Smart Grids

Contact Info

Product

Resources

About