An Improved ELM Model Based on CEEMD-LZC and Manifold Learning for Short-Term Wind Power Prediction

Zhang, Chao; Ding, Ming; Wang, Weisheng; Bi, Rui; Miao, Leying; Yu, Hai

doi:10.1109/access.2019.2936828

Cited by 28 publications

(19 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, determine the K value of the least square fitting. By testing the K value in References [10,20], the optimal K = 15 can be achieved. Then, normalize and matrix the fitted data with BN.…”

Section: Select Combination Weighting Methodsmentioning

confidence: 99%

“…Even though the above research can meet the basic goal of wind power prediction, it is still easy to fall into the limitations of the model itself, which can be supplemented by the optimization algorithm or other models to further improve the prediction effect. Therefore, the method of multi model combination was introduced to overcome the limitations of the single model [14][15][16][17][18][19][20][21]. The work in Reference [14] proposed a combination model of the support vector regression model and grey model, and the result showed that the combination model can improve the prediction accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combined Optimization Prediction Model of Regional Wind Power Based on Convolution Neural Network and Similar Days

Yang

Zha

et al. 2020

Machines

View full text Add to dashboard Cite

With the continuous optimization of energy structures, wind power generation has become the dominant new energy source. The strong random fluctuation of natural wind will bring challenges to power system dispatching, so it is necessary to predict wind power. In order to improve the short-term prediction accuracy of regional wind power, this paper proposes a new combination prediction model based on convolutional neural network (CNN) and similar days analysis. Firstly, the least square fitting and batch normalization (BN) are used to preprocess the data, and then the recent historical wind power data set for CNN is established. Secondly, the Pearson correlation coefficient and cosine similarity combination method are utilized to find similar days in the long-term data set, and the prediction model based on similar days is constructed by the weighting method. Finally, based on the particle swarm optimization (PSO) method, a combined forecasting model is established. The results show that the combined model can accurately predict the future short-term wind power curve, and the prediction accuracy is improved to different extents compared to a single method.

show abstract

Section: Select Combination Weighting Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Combined Optimization Prediction Model of Regional Wind Power Based on Convolution Neural Network and Similar Days

Yang

Zha

et al. 2020

Machines

View full text Add to dashboard Cite

show abstract

“…Also, the power imbalance of the wind turbines can result in a significant loss in their economical profit. Accurately predicting wind power is essential to decrease the impact of uncertainty and energy costs and enabling good management and integration of wind turbines in a smart grid [1]- [4].…”

Section: Introductionmentioning

confidence: 99%

Wind Power Prediction Using Ensemble Learning-Based Models

Lee

Harrou

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Wind power is one of the most potential energies and the major available renewable energy sources. Precisely predicting wind power production is essential for the management and the integration of wind power in a smart grid. The goal of this study is to predict wind power production with sufficient accuracy based on various factors using ensemble learning-based methods that consider the time-dependent nature of the wind power measurements. Essentially, the ensemble learning methods combine multiple learners to obtain an enhanced prediction performance in comparison to conventional standalone learners. In addition, they reduce the overall prediction error and have the capacity to merge various models. At first, this paper investigates the prediction capability of the well-known ensemble approaches Boosted Trees, Random Forest, and Generalized Random Forest for wind power prediction. We compared the prediction performance of these ensemble models to two frequently used prediction methods: Gaussian process regression, and Support Vector Regression. Experimental measurements recorded every ten minutes from actual wind turbines located in France and Turkey are used to test the prediction efficiency of the studied models. Experimental results have shown that the ensemble methods can predict wind power production with high accuracy compared to the standalone models. Furthermore, the findings clearly reveal that the lagged variables contribute significantly to the ensemble models, and permits constructing more parsimonious models.

show abstract

“…But when it comes to short-term wind power prediction, large calculation consumption makes the physical model not competent for high-precision prediction. And the statistical model such as Auto-Regressive and Moving Average model (ARMA) [5], Autoregressive Integrated Moving Average model (ARIMA) [6], Support Vector Machine (SVM) [7], Least Square Support Vector Machine (LSSVM) [8], Extreme Learning Machine (ELM) [9]- [11] are adopted because of its fast calculation speed and high accuracy. The hybrid model not only uses the statistical model but also integrates the physical model, especially using NWP.…”

Section: Introductionmentioning

confidence: 99%

Multi-Step Short-Term Wind Power Prediction Based on Three-level Decomposition and Improved Grey Wolf Optimization

Han

Tong

2020

IEEE Access

View full text Add to dashboard Cite

Wind power prediction is of great importance in enhancing wind energy penetration. This paper proposes a novel wind power prediction method which combining three-level decomposition with optimized prediction method. In the decomposition part, the Wavelet Packet Decomposition (WPD) is introduced as the first level decomposition, then the obtained sub-series are further decomposed by Variable Mode Decomposition (VMD). At last, Singular Spectrum Analysis (SSA) is carried out for each Intrinsic Mode Function (IMF), and the dominant component and residual components are separated as the input of the prediction. In the prediction part, Kernel Extreme Learning Machine (KELM) is adopted to complete the multi-steps wind power prediction. In this paper, an Improved Grey Wolf Optimization (IGWO) algorithm with redesign of the hierarchy and architecture is proposed, which especially suitable for optimizing wind power prediction. Finally, ten different models are compared, and the results show that the proposed method in this paper can extract the trend information of wind power greatly and has achieved excellent accuracy in short-term wind power prediction. INDEX TERMS Wind power prediction, three-level decomposition, improved grey wolf algorithm, multi-step prediction, kernel extreme learning machine. NOMENCLATURE

show abstract

An Improved ELM Model Based on CEEMD-LZC and Manifold Learning for Short-Term Wind Power Prediction

Cited by 28 publications

References 32 publications

Combined Optimization Prediction Model of Regional Wind Power Based on Convolution Neural Network and Similar Days

Combined Optimization Prediction Model of Regional Wind Power Based on Convolution Neural Network and Similar Days

Wind Power Prediction Using Ensemble Learning-Based Models

Multi-Step Short-Term Wind Power Prediction Based on Three-level Decomposition and Improved Grey Wolf Optimization

Contact Info

Product

Resources

About