Developing Wind Power Forecasting Algorithm Based on the Support Vector Machine and Gradient Boosting Machine for the KPX Wind Power Forecasting Competition

2019 ◽  
Vol 68 (12) ◽  
pp. 1694-1703
Author(s):  
Eunchong Park ◽  
Sooyeon Kim ◽  
Seungwoo Son ◽  
Seoyoung Park ◽  
Duehee Lee
Keyword(s):  
Support Vector Machine ◽  
Wind Power ◽  
Gradient Boosting ◽  
Support Vector ◽  
Wind Power Forecasting ◽  
Gradient Boosting Machine ◽  
Power Forecasting

scholarly journals Short Term Wind Power Prediction Based on Data Regression and Enhanced Support Vector Machine

Energies ◽  
2020 ◽  
Vol 13 (23) ◽  
pp. 6319
Author(s):  
Chia-Sheng Tu ◽  
Chih-Ming Hong ◽  
Hsi-Shan Huang ◽  
Chiung-Hsing Chen
Keyword(s):  
Support Vector Machine ◽  
Wind Speed ◽  
Regression Model ◽  
Wind Power ◽  
Support Vector ◽  
Forecasting Model ◽  
Short Term ◽  
Wind Power Forecasting ◽  
Data Regression ◽  
Power Forecasting

This paper presents a short-term wind power forecasting model for the next day based on historical marine weather and corresponding wind power output data. Due the large amount of historical marine weather and wind power data, we divided the data into clusters using the data regression (DR) algorithm to get meaningful training data, so as to reduce the number of modeling data and improve the efficiency of computing. The regression model was constructed based on the principle of the least squares support vector machine (LSSVM). We carried out wind speed forecasting for one hour and one day and used the correlation between marine wind speed and the corresponding wind power regression model to realize an indirect wind power forecasting model. Proper parameter settings for LSSVM are important to ensure its efficiency and accuracy. In this paper, we used an enhanced bee swarm optimization (EBSO) to perform the parameter optimization for LSSVM, which not only improved the forecast model availability, but also improved the forecasting accuracy.

Short-Term Wind Power Forecasting Based on Least-Square Support Vector Machine (LSSVM)

2013 ◽  
Vol 448-453 ◽  
pp. 1825-1828 ◽  
Author(s):  
Xiao Li ◽  
Xin Wang ◽  
Yi Hui Zheng ◽  
Li Xue Li ◽  
Li Dan Zhou ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Wind Power ◽  
Test Sample ◽  
Least Square ◽  
Support Vector ◽  
Machine Method ◽  
Wind Power Forecasting ◽  
Forecasting Method ◽  
Reasonable Choice ◽  
Power Forecasting

In order to improve the rate and accuracy of wind power forecasting, the Least-Square Support Vector Machine method (LSSVM) is presented. LSSVM adopts equality constraints and defines the least-square system as the objective function, which can simplify the forecasting method to a large extent, as well as accelerate the rate of wind power forecasting. Through the analysis of the original load data, a reasonable choice on training set and test sample set is made in the simulation. Besides, many factors, such as, the temperature, wind direction, wind speed and power previous, are taken into consideration. The result shows that LSSVM is more effective than that of SVM.

scholarly journals A XGBoost Model with Weather Similarity Analysis and Feature Engineering for Short-Term Wind Power Forecasting

2019 ◽  
Vol 9 (15) ◽  
pp. 3019 ◽  
Author(s):  
Huan Zheng ◽  
Yanghui Wu
Keyword(s):  
Wind Power ◽  
Gradient Boosting ◽  
Support Vector ◽  
Similarity Analysis ◽  
Feature Engineering ◽  
Short Term ◽  
Wind Power Forecasting ◽  
Proposed Model ◽  
Extreme Gradient Boosting ◽  
Power Forecasting

Large-scale wind power access may cause a series of safety and stability problems. Wind power forecasting (WPF) is beneficial to dispatch in advance. In this paper, a new extreme gradient boosting (XGBoost) model with weather similarity analysis and feature engineering is proposed for short-term wind power forecasting. Based on the similarity among historical days’ weather, k-means clustering algorithm is used to divide the samples into several categories. Additionally, we also create some time features and drop unimportant features through feature engineering. For each category, we make predictions using XGBoost. The results of the proposed model are compared with the back propagation neural network (BPNN) and classification and regression tree (CART), random forests (RF), support vector regression (SVR), and a single XGBoost model. It is shown that the proposed model produces the highest forecasting accuracy among all these models.

Sign in / Sign up

Export Citation Format

Share Document