scholarly journals An Ensemble Forecasting Model of Wind Power Outputs Based on Improved Statistical Approaches

Energies ◽  
2020 ◽  
Vol 13 (5) ◽  
pp. 1071 ◽  
Author(s):  
Yeojin Kim ◽  
Jin Hur
Keyword(s):  
Wind Power ◽  
Large Scale ◽  
Moving Average ◽  
Wind Farms ◽  
Ensemble Forecasting ◽  
Support Vector ◽  
Forecasting Model ◽  
Single Model ◽  
Simulation Based ◽  
Power Outputs

The number of wind-generating resources has increased considerably, owing to concerns over the environmental impact of fossil-fuel combustion. Therefore, wind power forecasting is becoming an important issue for large-scale wind power grid integration. Ensemble forecasting, which combines several forecasting techniques, is considered a viable alternative to conventional single-model-based forecasting for improving the forecasting accuracy. In this work, we propose the day-ahead ensemble forecasting of wind power using statistical methods. The ensemble forecasting model consists of three single forecasting approaches: autoregressive integrated moving average with exogenous variable (ARIMAX), support vector regression (SVR), and the Monte Carlo simulation-based power curve model. To apply the methodology, we conducted forecasting using the historical data of wind farms located on Jeju Island, Korea. The results were compared between a single model and an ensemble model to demonstrate the validity of the proposed method.

scholarly journals Research and Application of Hybrid Wind-Energy Forecasting Models Based on Cuckoo Search Optimization

Energies ◽  
2019 ◽  
Vol 12 (19) ◽  
pp. 3675 ◽  
Author(s):  
Ru Hou ◽  
Yi Yang ◽  
Qingcong Yuan ◽  
Yanhua Chen
Keyword(s):  
Wind Speed ◽  
Wind Energy ◽  
Wind Power ◽  
Large Scale ◽  
Search Algorithm ◽  
Moving Average ◽  
Wind Farms ◽  
Cuckoo Search ◽  
Hybrid Models ◽  
Forecasting Accuracy

Wind energy is crucial renewable and sustainable resource, which plays a major role in the energy mix in many countries around the world. Accurately forecasting the wind energy is not only important but also challenging in order to schedule the wind power generation and to ensure the security of wind-power integration. In this paper, four kinds of hybrid models based on cyclic exponential adjustment, adaptive coefficient methods and the cuckoo search algorithm are proposed to forecast the wind speed on large-scale wind farms in China. To verify the developed hybrid models’ effectiveness, wind-speed data from four sites of Xinjiang Uygur Autonomous Region located in northwest China are collected and analyzed. Multiple criteria are used to quantitatively evaluate the forecasting results. Simulation results indicate that (1) the proposed four hybrid models achieve desirable forecasting accuracy and outperform traditional back-propagating neural network, autoregressive integrated moving average as well as single adaptive coefficient methods, and (2) the parameters of hybrid models optimized by artificial intelligence contribute to higher forecasting accuracy compared with predetermined parameters.

A New Real Time Forecasting Model for Wind Power

2012 ◽  
Vol 260-261 ◽  
pp. 231-235
Author(s):  
Song Xu ◽  
Shou Lun Chen
Keyword(s):  
Support Vector Machine ◽  
Real Time ◽  
Wind Power ◽  
High Dimension ◽  
Large Scale ◽  
Support Vector ◽  
Forecasting Model ◽  
New Model ◽  
The Real ◽  
Dimension Space

Wind power is the most large-scale development of technical and economic conditions of non-hydro renewable energy. The real time forecasting for wind power is difficult because of the wind power data has nonlinear interaction. A new real time forecasting model for wind power is established. In the model, state space reconstruction is used to transfer the original wind power time series to high dimension space. The input vector and anticipant output vector can be gained by the changed data in the high dimension space. Based on the theory of support vector machine, the real time forecasting model is established with the principle of structural risk minimization of support vector machine. The new model is used for the real time forecasting of wind power. The results prove the efficiency and validity of the new model.

scholarly journals A Compound Wind Power Forecasting Strategy Based on Clustering, Two-Stage Decomposition, Parameter Optimization, and Optimal Combination of Multiple Machine Learning Approaches

Energies ◽  
2019 ◽  
Vol 12 (18) ◽  
pp. 3586 ◽  
Author(s):  
Sizhou Sun ◽  
Jingqi Fu ◽  
Ang Li
Keyword(s):  
Wind Power ◽  
Large Scale ◽  
Wind Farm ◽  
Search Algorithm ◽  
Interpolation Method ◽  
Least Square ◽  
Support Vector ◽  
Two Stage ◽  
Wind Power Forecasting ◽  
Power Forecasting

Given the large-scale exploitation and utilization of wind power, the problems caused by the high stochastic and random characteristics of wind speed make researchers develop more reliable and precise wind power forecasting (WPF) models. To obtain better predicting accuracy, this study proposes a novel compound WPF strategy by optimal integration of four base forecasting engines. In the forecasting process, density-based spatial clustering of applications with noise (DBSCAN) is firstly employed to identify meaningful information and discard the abnormal wind power data. To eliminate the adverse influence of the missing data on the forecasting accuracy, Lagrange interpolation method is developed to get the corrected values of the missing points. Then, the two-stage decomposition (TSD) method including ensemble empirical mode decomposition (EEMD) and wavelet transform (WT) is utilized to preprocess the wind power data. In the decomposition process, the empirical wind power data are disassembled into different intrinsic mode functions (IMFs) and one residual (Res) by EEMD, and the highest frequent time series IMF1 is further broken into different components by WT. After determination of the input matrix by a partial autocorrelation function (PACF) and normalization into [0, 1], these decomposed components are used as the input variables of all the base forecasting engines, including least square support vector machine (LSSVM), wavelet neural networks (WNN), extreme learning machine (ELM) and autoregressive integrated moving average (ARIMA), to make the multistep WPF. To avoid local optima and improve the forecasting performance, the parameters in LSSVM, ELM, and WNN are tuned by backtracking search algorithm (BSA). On this basis, BSA algorithm is also employed to optimize the weighted coefficients of the individual forecasting results that produced by the four base forecasting engines to generate an ensemble of the forecasts. In the end, case studies for a certain wind farm in China are carried out to assess the proposed forecasting strategy.

scholarly journals Resonance Stability Analysis of Large-Scale Wind Power Bases with Type-IV Wind Generators

Energies ◽  
2020 ◽  
Vol 13 (19) ◽  
pp. 5220
Author(s):  
Facai Xing ◽  
Zheng Xu ◽  
Zheren Zhang ◽  
Yangqing Dan ◽  
Yanwei Zhu
Keyword(s):  
Wind Power ◽  
Large Scale ◽  
Wind Farms ◽  
Negative Resistance ◽  
Resonance Mode ◽  
Resonance Structure ◽  
Power Bases ◽  
Impedance Model ◽  
Wind Generators ◽  
Type Iv

To guarantee the reliable and efficient development of wind power generation, oscillation problems in large-scale wind power bases with Type-IV generators are investigated from the view of resonance stability in this paper. Firstly, the transfer characteristics of disturbances in Type-IV wind generators are analyzed to establish their impedance model, based on the balance principle of frequency components. Subsequently, considering the dynamic characteristics of the transmission network and the interaction among several wind farms, the resonance structure of a practical wind power base is analyzed based on the s-domain nodal admittance matrix method. Furthermore, the unstable mechanism of the resonance mode is further illustrated by the negative-resistance effect theory. Finally, the established impedance model of the Type-IV wind generator and the resonance structure analysis results of the wind power bases are verified through the time-domain electro-magnetic transient simulation in PSCAD/EMTDC. Case studies indicate that there is a certain resonance instability risk in large-scale wind power bases in a frequency range of 1–100 Hz, and the unstable resonance mode is strongly related to the negative-resistance effect and the capacitive effect of Type-IV wind generators.

scholarly journals A Self-Regulation Strategy for the Power Fluctuation of the Islanded Voltage Source Converter (VSC) Station Delivering Large-Scale Wind Power

Energies ◽  
2020 ◽  
Vol 13 (3) ◽  
pp. 560
Author(s):  
Juanjuan Sun ◽  
Hui Wang ◽  
Xiaomin Zhu ◽  
Qian Pu
Keyword(s):  
Wind Power ◽  
Large Scale ◽  
Self Regulation ◽  
Wind Farms ◽  
The Self ◽  
Voltage Source ◽  
Time Variability ◽  
Frequency Regulation ◽  
Voltage Source Converter ◽  
Power Fluctuation

When the power source of a voltage source converter (VSC) station at the sending end solely depends on wind power generation, the station is operating in an islanding mode. In this case, the power fluctuation of the wind power will be entirely transmitted to the receiving-end grid. A self-regulation scheme of power fluctuation is proposed in this paper to solve this problem. Firstly, we investigated the short-time variability characteristic of the wind power in a multi-terminal direct-current (MTDC) project in China. Then we designed a virtual frequency (VF) control strategy at the VSC station based on the common constant voltage constant frequency (CVCF) control of VSC station. By cooperating with the primary frequency regulation (PFR) control at the wind farms, the self-regulation of active power pooling at the VSC station was realized. The control parameters of VF and PFR control were carefully settled through the steady-state analysis of the MTDC grid. The self-regulation effect had been demonstrated by a twenty-four-hour simulation. The results showed that the proposed scheme could effectively smoothen the power fluctuation.

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.

Study on Medium-Term and Short-Term Wind Power Forecasting Methods

2013 ◽  
Vol 361-363 ◽  
pp. 318-322
Author(s):  
Gui Zhong Wu ◽  
Yuan Biao Zhang ◽  
Cheng Su ◽  
Yu Jie Liu
Keyword(s):  
Neural Network ◽  
Wind Power ◽  
Average Method ◽  
Moving Average ◽  
Forecasting Model ◽  
Power Prediction ◽  
Medium Term ◽  
Accuracy Rate ◽  
Short Term ◽  
Weighted Moving Average

In the paper, the wind power prediction is devided into medium-term forecasts and short-term forecasts. For medium-term forecasts, we use the weighted moving average method and BP neural network forecasting model, while for short-term forecasts, the ARMA model and combination forecasting model based on the maximum entropy principle are used. The application example shows that the weighted moving average method is easy and can precisely obtain the fluctuation trend of the wind power, while the accuracy rate of the BP neural network forecasting model is 91.23%, which is better than the former. The predictive results of the ARMA model are similar with actual trends and its accuracy rate is 88.98%. The combination model integrates the advantages of the BP neural network and ARMA model, and its accuracy rate is up to 92.58%.

A Wind-Thermal Hydropower Coordination Control Strategy Based on Multiple Constraints of Large-Scale Wind Power Integration

2013 ◽  
Vol 724-725 ◽  
pp. 463-468
Author(s):  
Jian Bo Wang ◽  
Wen Ying Liu ◽  
Wei Zheng ◽  
Chen Liang
Keyword(s):  
Wind Power ◽  
Control Strategy ◽  
Large Scale ◽  
Thermal Power ◽  
Wind Farms ◽  
System Stability ◽  
Maximum Output ◽  
Multiple Constraints ◽  
Operating Characteristics ◽  
Output Constraints

Due to the fluctuations and intermittency of wind power, large-scale wind farms integration will cause adverse impact on the safety and stability of the system,such as harmonic pollution, bad power quality, system stability destruction.On the basis of multiple constraints, including hydropower’s and thermal power’s operating characteristics, determination of reserve capacity considering wind power forecasting bias, climbing speed constraints, and maximum output constraints, this paper proposed a control strategy of joint coordination of wind, hydropower and thermal power, which suppressed the fluctuations of wind power effectively. At last, the article give a simulation to verify the feasibility of the control strategy to stabilize system frequency.

Mechanism Research about Impact of Large-Scale Wind Power Integration on Grid Loss

2014 ◽  
Vol 1070-1072 ◽  
pp. 200-203
Author(s):  
Ze Tian Wei ◽  
Wen Ying Liu ◽  
Fu Chao Liu ◽  
Jian Zong Zhuo
Keyword(s):  
Wind Power ◽  
Transmission Lines ◽  
Power Flow ◽  
Large Scale ◽  
Wind Farms ◽  
Active Power ◽  
Equivalent Model ◽  
Factors Affecting ◽  
Main Factors ◽  
Grid Loss

This paper firstly analyzes the mechanism of transmission line and transformer loss and illustrates the equivalent model and calculating method. Then creates a simple three-node model and discusses the main factors which affect the grid loss with adequate formula. At last, we draw a concise conclusion that there are several factors affecting grid loss. The main factors are the location of wind power access, the active power flow of transmission lines, the active power output of wind farms and the voltage level of wind power access.

Sign in / Sign up

Export Citation Format

Share Document