Ultra-Short Term Wind Power Forecasting Based on LSTM Neural Network

Li, Jiateng; Geng, Duo; Zhang, Pei; Meng, Xin; Zhang, Liang; Gao, Fan

doi:10.1109/cieec47146.2019.cieec-2019625

Cited by 16 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to fully validate the performance of wind power prediction, the proposed model is compared with Back Propagation Neural Network (BPNN) [30], LSTM [16], and Logic Gated Unit Network (GRU) [31], and the results are shown in Table 4. This table demonstrates the enhanced predictive capabilities of time series modeling methods, particularly LSTM, GRU, and our proposed approach, which exhibit lower RMSE, MAPE, and higher QR than the BPNN model.…”

Section: Comparison With Classical Methodsmentioning

confidence: 99%

“…In this investigation, Pearson correlation coefficients are calculated between the input features and the predicted power for the initial 11 lag moments, and the outcomes are depicted in Figure 2. It merits emphasis that Li et al [16] have proposed that correlation coefficients exceeding 0.8 signify a robust and more productive correlation in time series data, which is beneficial for feature extraction. As can be seen from Figure 2, there are nine groups with correlation coefficient values exceeding 0.8, from t-1 to t-9.…”

Section: Time Lag Characterizationmentioning

confidence: 99%

See 1 more Smart Citation

An Ultra-Short-Term Wind Power Prediction Method Based on Quadratic Decomposition and Multi-Objective Optimization

Chen,

Zhang,

Tong

et al. 2024

EAI Endorsed Trans Energy Web

View full text Add to dashboard Cite

To augment the accuracy, stability, and qualification rate of wind power prediction, thereby fostering the secure and economical operation of wind farms, a method predicated on quadratic decomposition and multi-objective optimization for ultra-short-term wind power prediction is proposed. Initially, the original wind power signal is decomposed using a quadratic decomposition method constituted by the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Fuzzy Entropy (FE), and Symplectic Geometry Mode Decomposition (SGMD), thereby mitigating the randomness and volatility of the original signal. Subsequently, the decomposed signal components are introduced into the Deep Bidirectional Long Short-Term Memory (DBiLSTM) neural network for time series modeling, and the Sand Cat Swarm Optimization Algorithm (SCSO) is employed to optimize the network hyperparameters, thereby enhancing the network’s predictive performance. Ultimately, a multi-objective optimization loss that accommodates accuracy, stability, and grid compliance is proposed to guide network training. Experimental results reveal that the employed quadratic decomposition method and the proposed multi-objective optimization loss can effectively bolster the model’s predictive performance. Compared to other classical methods, the proposed method achieves optimal results across different seasons, thereby demonstrating robust practicality.

show abstract

Section: Comparison With Classical Methodsmentioning

confidence: 99%

Section: Time Lag Characterizationmentioning

confidence: 99%