The Forecasting of Short-Term Wind Speed on Wind Farm Based on Phase Space Reconstruction and Neural Network

2012 ◽  
Vol 246-247 ◽  
pp. 496-500
Author(s):  
Ying Ying Su ◽  
Fei Ma ◽  
Hai Yan Zhang ◽  
Zhi Qiang Liao ◽  
Peng Jun
Keyword(s):  
Neural Network ◽  
Phase Space ◽  
Wind Speed ◽  
Wind Farm ◽  
Absolute Error ◽  
Phase Space Reconstruction ◽  
The Novel ◽  
Short Term ◽  
Sample Data ◽  
The Mean

The forecasting precision of short-term wind speed is not high for its chaos and time-varying. Aimed at the problem, the novel data space is reconstructed with the best embedding dimension and time delay according to the phase space reconstruction. On the basis, neural network (NN) is used as the modeling tool with the novel sample data. Meanwhile, the structure of NN is confirmed compared with the others on the precision. In the end, the model of short-term wind speed is able to be obtained. The results show that the method is available and the Mean absolute error (MAE) is decreased to 16.2% for 2 hours.

Short-Term Wind Speed Forecasting by Using Chaotic Theory and SVM

2013 ◽  
Vol 300-301 ◽  
pp. 842-847 ◽  
Author(s):  
Cai Hong Zhu ◽  
Ling Ling Li ◽  
Jun Hao Li ◽  
Jian Sen Gao
Keyword(s):  
Phase Space ◽  
Wind Speed ◽  
Wind Farm ◽  
Phase Space Reconstruction ◽  
Percentage Error ◽  
Support Vector ◽  
Forecasting Model ◽  
Particle Swarm Algorithm ◽  
Short Term ◽  
Wind Speed Forecast

The wind speed forecast is the basis of the wind power forecast. The wind speed has the characteristics of random non-smooth so obviously that its precise forecast is extremely difficult. Therefore, a forecasting method based on the theory of chaotic phase-space reconstruction and SVM was put forward in this paper and a forecasting model of Chaotic Support Vector Machine was built. In order to improve the precision and generalization ability, the key parameters in the phase space reconstruction and the key parameters of SVM were carried out joint optimization by using particle swarm algorithm in the paper. Then the optimal parameters were brought into the forecasting model to forecast short-term wind speed. The above method was applied to wind speed forecast of a wind farm in Inner Mongolia, China. In the experiments of computer simulation, the absolute percentage error of forecasting results was only 12.51%, which showed this method was effective for short-term wind speed forecast.

Wind Power Short-Term Forcasting of BP Neural Network Based on the Small-World Optimization

2014 ◽  
Vol 933 ◽  
pp. 384-389
Author(s):  
Xin Zhao ◽  
Shuang Xin Wang
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Wind Power ◽  
Bp Neural Network ◽  
Wind Direction ◽  
Wind Farm ◽  
Prediction Method ◽  
Small World ◽  
Power Method ◽  
Short Term

Wind power short-term forcasting of BP neural network based on the small-world optimization is proposed. First, the initial data collected from wind farm are revised, and the unreasonable data are found out and revised. Second, the small-world optimization BP neural network model is proposed, and the model is used on the prediction method of wind speed and wind direction, and the prediction method of power. Finally, by simulation analysis, the NMAE and NRMSE of the power method are smaller than those of the wind speed and wind direction method when the wind power data of one hour later are predicted. When the power method are used to forecast the data one hour later, NMAE is 5.39% and NRMSE is 6.98%.

Ultra-Short-Term Wind Speed and Power Forecast Based on Dynamic Selective Neural Network Ensemble

2014 ◽  
Vol 568-570 ◽  
pp. 868-873
Author(s):  
Yan Hua Liu ◽  
Ze Dong
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Wind Speed ◽  
Wind Power ◽  
Wind Farm ◽  
Stable Operation ◽  
Neural Network Ensemble ◽  
Short Term ◽  
The Neural Networks ◽  
Generalization Errors

With the scale of grid-connected wind farms increasing, accurate forecast of ultra-short-term wind speed and wind power is very important to the stable operation of power systems. This paper presents a dynamic selective neural network ensemble (DSNNE) forecast method, which makes use of K nearest neighbor algorithm to collect the generalization errors of certain different BP neural networks and RBF neural networks into a performance matrix and then the neural networks with low local generalization errors are dynamically selected and locally dynamic averaging is applied to the neural networks in order to conduct the final results of the ensemble. Then this method is applied to realize the wind speed and power ultra-short-term advance forecast, taking the wind speed and wind turbine power output from a wind farm in China as the original data. The research results show that DSNNE improves the generalization ability of the neural network system and the prediction accuracy of wind power and wind speed significantly. It proves the validity and effectiveness of the DSNNE with controlling the biggest mean relative error of 2 minutes ahead wind power and wind speed forecast as low as 25% and 16% respectively.

Wind Speed Forecast for Wind Farms Based on Phase Space Reconstruction of Wavelet Neural Network

2012 ◽  
Vol 433-440 ◽  
pp. 840-845 ◽  
Author(s):  
Xiao Bing Xu ◽  
Jun He ◽  
Jian Ping Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Phase Space ◽  
Wind Speed ◽  
Network Model ◽  
Neural Network Model ◽  
Phase Space Reconstruction ◽  
Wavelet Neural Network ◽  
Non Linear ◽  
Wind Speed Forecast

Wind speed forecast is a non-linear and non-smooth problem. nonlinear and non-stationary are two kinds of mathematical problem, it is difficult to model with a single method, so that, a wavelet neural network model is set, the non-linear process of wind speed is forecast by neural networks and the non-stationary process of wind speed is decomposed into quasi-stationary at different frequency scales by multi-scale characteristics of wavelet transforms. wavelet combined with neural network model avoid the neural network model that can not handle non-stationary questions .while, the effect of indefinite inputs are removed by embedding dimension of phase space to determine neural networks inputs. The simulation results show that phase space reconstruction of wavelet neural network is more accuracy than the ordinary BP neural network. It could be well applied in wind speed forecasts.

Identification of Voltage Disturbances Based on Phase Space Reconstruction and BP Neural Network

2013 ◽  
Vol 303-306 ◽  
pp. 966-969
Author(s):  
Zi Teng Hu ◽  
Li Min Jia ◽  
De Chen Yao
Keyword(s):  
Neural Network ◽  
Phase Space ◽  
Bp Neural Network ◽  
Phase Space Reconstruction ◽  
Quality Analysis ◽  
Voltage Sag ◽  
Phase Space Theory ◽  
Voltage Swells ◽  
The Mean ◽  
The Time Domain

A identification method via phase space reconstruction and BP neural network was proposed for identifying three types of voltage disturbances (voltage swells, voltage sag, voltage flicker). In this method, firstly, phase space reconstruction was utilized for describing voltage disturbances; secondly, the mean radius of each cycle of phase space trajectory in accordance with the time-domain was extracted from voltage signals; finally, the identification of voltage disturbances was obtained by BP neural network. The simulation results in Matlab show that the proposed method is capable of high accuracy to identify three types of voltage disturbances, and further validates the efficiency of phase space theory in power quality analysis.

Ultra-Short-Term Forecasting Based on Phase Space Reconstruction and Wind Power Wind

2015 ◽  
Vol 713-715 ◽  
pp. 1444-1447
Author(s):  
De Yin Du ◽  
Bao Fan Chen
Keyword(s):  
Phase Space ◽  
Wind Speed ◽  
Power Systems ◽  
Wind Power ◽  
Wind Farm ◽  
Wind Farms ◽  
Stable Operation ◽  
Short Term ◽  
Short Term Forecasting ◽  
Turbine Output

The amount of random variation of wind speed, wind turbine output power are volatile, a lot of wind power will be on the safe and stable operation of power systems and power quality pose serious challenges, so the wind farm wind speed and power generation forecast scheduling and management of wind farms play an important role. According wind with chaotic discuss the use of phase space CC method to reconstruct the chaotic time series, and the phase space of a wind farm 10 units were reconstructed using the weighted first order local prediction model to obtain short-term within 1h wind forecast values obtained using the power curve conversion method of generating power for each unit. By examples show that the proposed method is feasible and effective.

scholarly journals Analysing Uncertainties in Offshore Wind Farm Power Output using Measure Correlate Predict Methodologies

2019 ◽  
Author(s):  
Michael Denis Mifsud ◽  
Tonio Sant ◽  
Robert Nicholas Farrugia
Keyword(s):  
Wind Speed ◽  
Wind Direction ◽  
Power Output ◽  
Wind Farm ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Offshore Wind ◽  
Energy Yield ◽  
Offshore Wind Farm ◽  
The Mean

Abstract. This paper investigates the uncertainties resulting from different Measure-Correlate-Predict methods to project the power and energy yield from a wind farm. The analysis is based on a case study that utilizes short-term data acquired from a LiDAR wind measurement system deployed at a coastal site in the northern part of the island of Malta and long-term measurements from the island’s international airport. The wind speed at the candidate site is measured by means of a LiDAR system. The predicted power output for a hypothetical offshore wind farm from the various MCP methodologies is compared to the actual power output obtained directly from the input of LiDAR data to establish which MCP methodology best predicts the power generated. The power output from the wind farm is predicted by inputting wind speed and direction derived from the different MCP methods into windPRO® (https://www.emd.dk/windpro). The predicted power is compared to the power output generated from the actual wind and direction data by using the Mean Squared Error (MSE) and the Mean Absolute Error (MAE) measures. This methodology will establish which combination of MCP methodology and wind farm configuration will have the least prediction error. The best MCP methodology which combines prediction of wind speed and wind direction, together with the topology of the wind farm, is that using Artificial Neural Networks. However, the study concludes that the other MCP methodologies cannot be discarded as it is always best to compare different combinations of MCP methodologies for wind speed and wind direction, together with different wake models and wind farm topologies.

Sign in / Sign up

Export Citation Format

Share Document