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.

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.

scholarly journals Probabilistic Short-Term Wind Power Forecasting Using Sparse Bayesian Learning and NWP

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Kaikai Pan ◽  
Zheng Qian ◽  
Niya Chen
Keyword(s):  
Wind Power ◽  
Bayesian Learning ◽  
Weather Prediction ◽  
Parameters Optimization ◽  
Gaussian Kernel ◽  
Sparse Bayesian Learning ◽  
Short Term ◽  
Wind Power Forecasting ◽  
Proposed Model ◽  
Power Forecasting

Probabilistic short-term wind power forecasting is greatly significant for the operation of wind power scheduling and the reliability of power system. In this paper, an approach based on Sparse Bayesian Learning (SBL) and Numerical Weather Prediction (NWP) for probabilistic wind power forecasting in the horizon of 1–24 hours was investigated. In the modeling process, first, the wind speed data from NWP results was corrected, and then the SBL was used to build a relationship between the combined data and the power generation to produce probabilistic power forecasts. Furthermore, in each model, the application of SBL was improved by using modified-Gaussian kernel function and parameters optimization through Particle Swarm Optimization (PSO). To validate the proposed approach, two real-world datasets were used for construction and testing. For deterministic evaluation, the simulation results showed that the proposed model achieves a greater improvement in forecasting accuracy compared with other wind power forecast models. For probabilistic evaluation, the results of indicators also demonstrate that the proposed model has an outstanding performance.

Short-Term Wind Power Forecasting in Wind Power Plants of North China Based on Support Vector Regression Analysis

2014 ◽  
Vol 705 ◽  
pp. 284-288
Author(s):  
Hai Jian Shao ◽  
Hai Kun Wei
Keyword(s):  
Support Vector Regression ◽  
Wind Power ◽  
Power Plants ◽  
Heuristic Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Short Term ◽  
Wind Power Forecasting ◽  
Wind Power Plants ◽  
Power Forecasting

This paper investigates the short-term wind power forecasting and demonstrates accurate modeling, which utilizes two representative heuristic algorithms (i.e. wavelet neural network (WNN) and Multilayer Perceptron (MLP)), and statistical machine learning techniques (i.e. Support Vector Regression (SVR)). The proposed method generates the performances of different approaches for random time series, characterized with high accuracy and high generalization capability. The employed data is obtained through Sampling equipment in Real Wind Power Plants (Power generation equipment is Dongfang Steam Turbine Co., Ltd. weak wind turbine type--FD77 with German REpower company technology). The main innovation of this paper comes from: (a) problem may encounter in the real application is in consideration such as corrupt, missing value and noisy data. (b) Data lag estimation are provided to investigate the data distribution and obtain the best input variables, respectively. (c) Comparison between MLP neural networks, WNN and SVR with optimized kernel parameters based on Grid-search method are provided to demonstrate the best forecasting approaches. The purpose of this paper is to provide a method with reference value for short-term wind power forecasting.

scholarly journals Robustness of Short-Term Wind Power Forecasting against False Data Injection Attacks

Energies ◽  
2020 ◽  
Vol 13 (15) ◽  
pp. 3780 ◽  
Author(s):  
Yao Zhang ◽  
Fan Lin ◽  
Ke Wang
Keyword(s):  
Wind Power ◽  
Support Vector ◽  
Probabilistic Forecasting ◽  
Short Term ◽  
Wind Power Forecasting ◽  
False Data Injection ◽  
Forecasting Models ◽  
Injection Attacks ◽  
The Impact ◽  
Power Forecasting

The accuracy of wind power forecasting depends a great deal on the data quality, which is so susceptible to cybersecurity attacks. In this paper, we study the cybersecurity issue of short-term wind power forecasting. We present one class of data attacks, called false data injection attacks, against wind power deterministic and probabilistic forecasting. We show that any malicious data can be injected to historical data without being discovered by one of the commonly-used anomaly detection techniques. Moreover, we testify that attackers can launch such data attacks even with limited resources. To study the impact of data attacks on the forecasting accuracy, we establish the framework of simulating false data injection attacks using the Monte Carlo method. Then, the robustness of six representative wind power forecasting models is tested. Numerical results on real-world data demonstrate that the support vector machine and k-nearest neighbors combined with kernel density estimator are the most robust deterministic and probabilistic forecasting ones among six representative models, respectively. Nevertheless, none of them can issue accurate forecasts under very strong false data attacks. This presents a serious challenge to the community of wind power forecasting. The challenge is to study robust wind power forecasting models dealing with false data attacks.

Sign in / Sign up

Export Citation Format

Share Document