Wind Speed Forecasting Based on Extreme Gradient Boosting

Cai, Ren; Xie, Siyu; Wang, Bozhong; Yang, Ruijiang; Xu, Daosen; He, Yihui

doi:10.1109/access.2020.3025967

Cited by 44 publications

(18 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Gradient boosting method represents a very flexible non-parametric machine learning technique for regression (or classification) that has proven to be very efficient in many contexts. Although its use in wind speed or wind power forecasting has been limited (see e.g., [5,31]), given its very competitive performances in many other domains, it deserves to be considered in the present study. XGBoost [6] and LightGBM [21] are two of the most popular GB algorithms that achieve stateof-the-art performances for fitting the relationship between features and labels.…”

Section: Prediction Methodsmentioning

confidence: 99%

Leveraging Data from Nearby Stations to Improve Short-Term Wind Speed Forecasts

Baile¹,

J.F.²

2022

SSRN Journal

View full text Add to dashboard Cite

Section: Prediction Methodsmentioning

confidence: 99%

Leveraging Data from Nearby Stations to Improve Short-Term Wind Speed Forecasts

Baile¹,

J.F.²

2022

SSRN Journal

View full text Add to dashboard Cite

“…Model-model machine learning yang juga populer pada masalah segmentasi adalah artificial neural network (ANN) (Pourdaryaei et al, 2019), support vector regression (SVR) (Li, Wang, Cheng, & Bai, 2020), dan metode Convolutional Neural Network (CNN). Disisi lain, metode-metode di atas sering terjebak pada optimum lokal dan overfitting (Cai et al, 2020). XGBoost adalah motode machine learning yang sangat populer.…”

Section: Tinjauan Pustaka Penelitian Terkaitunclassified

Model Hibrid Genetic-Xgboost Dan Principal Component Analysis Pada Segmentasi Dan Peramalan Pasar

Siringoringo

Perangin-angin

Jamaluddin

2021

jmika

View full text Add to dashboard Cite

Extreme Gradient Boosting(XGBoost) is a popular boosting algorithm based on decision trees. XGBoost is the best in the boosting group. XGBoost has excellent convergence. On the other hand, XGBoost is a Hyper parameterized model. Determining the value of each parameter is classified as difficult, resulting in the results obtained being trapped in the local optimum situation. Determining the value of each parameter manually, of course, takes a lot of time. In this study, a Genetic Algorithm (GA) is applied to find the optimal value of the XGBoost hyperparameter on the market segmentation problem. The evaluation of the model is based on the ROC curve. Test result. The ROC test results for several SVM, Logistic Regression, and Genetic-XGBoost models are 0.89; 0.98; 0.99. The results show that the Genetic-XGBoost model can be applied to market segmentation and forecasting.

show abstract

“…Recently, the gradient boosting machines (GBMs) [13] have developed rapidly due to their low computational resources, fast training speed, and high fitting accuracy. They are widely used in regression and classification tasks, such as wind speed forecasting [14,15], fault diagnosis [16,17], and anomaly detection [18,19]. The light gradient boosting machine (LGBM) [20] is a novel GBM proposed by Ke et al in 2017.…”

Section: Introductionmentioning

confidence: 99%

Degradation Trend Prediction of Pumped Storage Unit Based on MIC-LGBM and VMD-GRU Combined Model

et al. 2022

View full text Add to dashboard Cite

The harsh operating environment aggravates the degradation of pumped storage units (PSUs). Degradation trend prediction (DTP) provides important support for the condition-based maintenance of PSUs. However, the complexity of the performance degradation index (PDI) sequence poses a severe challenge of the reliability of DTP. Additionally, the accuracy of healthy model is often ignored, resulting in an unconvincing PDI. To solve these problems, a combined DTP model that integrates the maximal information coefficient (MIC), light gradient boosting machine (LGBM), variational mode decomposition (VMD) and gated recurrent unit (GRU) is proposed. Firstly, MIC-LGBM is utilized to generate a high-precision healthy model. MIC is applied to select the working parameters with the most relevance, then the LGBM is utilized to construct the healthy model. Afterwards, a performance degradation index (PDI) is generated based on the LGBM healthy model and monitoring data. Finally, the VMD-GRU prediction model is designed to achieve precise DTP under the complex PDI sequence. The proposed model is verified by applying it to a PSU located in Zhejiang province, China. The results reveal that the proposed model achieves the highest precision healthy model and the best prediction performance compared with other comparative models. The absolute average (|AVG|) and standard deviation (STD) of fitting errors are reduced to 0.0275 and 0.9245, and the RMSE, MAE, and R2 are 0.00395, 0.0032, and 0.9226 respectively, on average for two operating conditions.

show abstract

Wind Speed Forecasting Based on Extreme Gradient Boosting

Cited by 44 publications

References 45 publications

Leveraging Data from Nearby Stations to Improve Short-Term Wind Speed Forecasts

Leveraging Data from Nearby Stations to Improve Short-Term Wind Speed Forecasts

Model Hibrid Genetic-Xgboost Dan Principal Component Analysis Pada Segmentasi Dan Peramalan Pasar

Degradation Trend Prediction of Pumped Storage Unit Based on MIC-LGBM and VMD-GRU Combined Model

Contact Info

Product

Resources

About