This study explores the initiation mechanisms of convective wind events,emphasizing their variability across different atmospheric circulation patterns.Historically,the inadequate feature categorization within multi-f...This study explores the initiation mechanisms of convective wind events,emphasizing their variability across different atmospheric circulation patterns.Historically,the inadequate feature categorization within multi-faceted forecast models has led to suboptimal forecast efficacy,particularly for events in dynamically weak forcing conditions during the warm season.To improve the prediction accuracy of convective wind events,this research introduces a novel approach that combines machine learning techniques to identify varying meteorological flow regimes.Convective winds(CWs)are defined as wind speeds reaching or exceeding 17.2 m s^(-1)and severe convective winds(SCWs)as speeds surpassing 24.5 m s^(-1).This study examines the spatial and temporal distribution of CW and SCW events from 2013 to 2021 and their circulation dynamics associated with three primary flow regimes:cold air advection,warm air advection,and quasibarotropic conditions.Key circulation features are used as input variables to construct an effective weather system pattern recognition model.This model employs an Adaptive Boosting(AdaBoost)algorithm combined with Random Under-Sampling(RUS)to address the class imbalance issue,achieving a recognition accuracy of 90.9%.Furthermore,utilizing factor analysis and Support Vector Machine(SVM)techniques,three specialized and independent probabilistic prediction models are developed based on the variance in predictor distributions across different flow regimes.By integrating the type of identification model with these prediction models,an enhanced comprehensive model is constructed.This advanced model autonomously identifies flow types and accordingly selects the most appropriate prediction model.Over a three-year validation period,this improved model outperformed the initially unclassified model in terms of prediction accuracy.Notably,for CWs and SCWs,the maximum Peirce Skill Score(PSS)increased from 0.530 and 0.702 to 0.628 and 0.726,respectively,and the corresponding maximum Threat Score(TS)improved from 0.087 and 0.024 to 0.120 and 0.026.These improvements were significant across all samples,with the cold air advection type showing the greatest enhancement due to the significant spatial variability of each factor.Additionally,the model improved forecast precision by prioritizing thermal factors,which played a key role in modulating false alarm rates in warm air advection and quasi-barotropic flow regimes.The results confirm the critical contribution of circulation feature recognition and segmented modeling to enhancing the adaptability and predictive accuracy of weather forecast models.展开更多
Large-scale wind turbine generator systems have strong nonlinear multivariable characteristics with many uncertain factors and disturbances. Automatic control is crucial for the efficiency and reliability of wind turb...Large-scale wind turbine generator systems have strong nonlinear multivariable characteristics with many uncertain factors and disturbances. Automatic control is crucial for the efficiency and reliability of wind turbines. On the basis of simplified and proper model of variable speed variable pitch wind turbines, the effective wind speed is estimated using extended Kaiman filter. Intelligent control schemes proposed in the paper include two loops which operate in synchronism with each other. At below-rated wind speed, the inner loop adopts adaptive fuzzy control based on variable universe for generator torque regulation to realize maximum wind energy capture. At above-rated wind speed, a controller based on least square support vector machine is proposed to adjust pitch angle and keep rated output power. The simulation shows the effectiveness of the intelligent control.展开更多
Accurate forecasting of wind velocity can improve the economic dispatch and safe operation of the power system. Support vector machine (SVM) has been proved to be an efficient approach for forecasting. According to th...Accurate forecasting of wind velocity can improve the economic dispatch and safe operation of the power system. Support vector machine (SVM) has been proved to be an efficient approach for forecasting. According to the analysis with support vector machine method, the drawback of determining the parameters only by experts' experience should be improved. After a detailed description of the methodology of SVM and simulated annealing, an improved algorithm was proposed for the automatic optimization of parameters using SVM method. An example has proved that the proposed method can efficiently select the parameters of the SVM method. And by optimizing the parameters, the forecasting accuracy of the max wind velocity increases by 34.45%, which indicates that the new SASVM model improves the forecasting accuracy.展开更多
An accurate vertical wind speed(WS)data estimation is required to determine the potential for wind farm installation.In general,the vertical extrapolation of WS at different heights must consider different parameters ...An accurate vertical wind speed(WS)data estimation is required to determine the potential for wind farm installation.In general,the vertical extrapolation of WS at different heights must consider different parameters fromdifferent locations,such as wind shear coefficient,roughness length,and atmospheric conditions.The novelty presented in this article is the introduction of two steps optimization for the Recurrent Neural Networks(RNN)model to estimate WS at different heights using measurements from lower heights.The first optimization of the RNN is performed to minimize a differentiable cost function,namely,mean squared error(MSE),using the Broyden-Fletcher-Goldfarb-Shanno algorithm.Secondly,the RNN is optimized to reduce a non-differentiable cost function using simulated annealing(RNN-SA),namely mean absolute error(MAE).Estimation ofWS vertically at 50 m height is done by training RNN-SA with the actualWS data a 10–40 m heights.The estimatedWS at height of 50 m and the measured WS at 10–40 heights are further used to train RNN-SA to obtain WS at 60 m height.This procedure is repeated continuously until theWS is estimated at a height of 180 m.The RNN-SA performance is compared with the standard RNN,Multilayer Perceptron(MLP),Support Vector Machine(SVM),and state of the art methods like convolutional neural networks(CNN)and long short-term memory(LSTM)networks to extrapolate theWS vertically.The estimated values are also compared with realWS dataset acquired using LiDAR and tested using four error metrics namely,mean squared error(MSE),mean absolute percentage error(MAPE),mean bias error(MBE),and coefficient of determination(R2).The numerical experimental results show that the MSE values between the estimated and actualWS at 180mheight for the RNN-SA,RNN,MLP,and SVM methods are found to be 2.09,2.12,2.37,and 2.63,respectively.展开更多
由于风速随机性大且影响风速大小的因素较多,为了提高风速预测的准确性,研究了将支持向量机(support vectorm ach ine,SVM)应用于风速预测的方法。通过交叉验证选取LIBSVM回归机的最优参数组合并建立模型。实验结果表明,该方法在风速的...由于风速随机性大且影响风速大小的因素较多,为了提高风速预测的准确性,研究了将支持向量机(support vectorm ach ine,SVM)应用于风速预测的方法。通过交叉验证选取LIBSVM回归机的最优参数组合并建立模型。实验结果表明,该方法在风速的实际预测中具有可行性。展开更多
Under the context of global climate change,the frequent occurrence of strong winds in Guyuan has significantly hindered the development of local facility agriculture.Using hourly meteorological data from the Sanying N...Under the context of global climate change,the frequent occurrence of strong winds in Guyuan has significantly hindered the development of local facility agriculture.Using hourly meteorological data from the Sanying National Station and the Guyuan Greenhouse Station between April 2024 and April 2025,this study employed machine learning methods to develop wind speed prediction models based on BP neural network,support vector machine,and random forest(referred to as BP,SVM,and RF models),aiming to provide references for local disaster prevention and mitigation.The results indicate that:1)Wind speed at the Guyuan Greenhouse Station exhibits the strongest correlation with that at the National Station(0.489-0.595),followed by temperature and 24-hour precipitation(0.116-0.336).2)The mean absolute error(MAE)of the BP,RF,and SVM models at all heights is below 1.5 m/s,the root mean square error(RMSE)is under 2.1 m/s,and the forecast accuracy(FA)exceeds 75%,indicating satisfactory model performance.Compared to 3 m,the MAE and RMSE of 0.5 m are larger,while the FA is smaller.This indicates that the wind speed of 0.5 m is close to the ground,and is more affected by surface roughness and turbulence effects,resulting in greater randomness and making the model more difficult.3)Based on case analyses of May 10 and May 1,2024,the overall simulation performance ranks as“RF model>SVM model>BP model”;however,the SVM model demonstrates higher accuracy in simulating strong wind events.展开更多
基金Guangdong S&T Program(2024A1111120024)CMA Innovation and Development Fund(CXFZ2024J014)+3 种基金CMA Youth Innovation Team(CMA2024QN01)PRB Meteorological Open Research Fund(ZJLY202425-GD02)GBA Meteorological S&T Program(GHMA2024Y04)Guangzhou Meteorological Research Project(Z202401)。
文摘This study explores the initiation mechanisms of convective wind events,emphasizing their variability across different atmospheric circulation patterns.Historically,the inadequate feature categorization within multi-faceted forecast models has led to suboptimal forecast efficacy,particularly for events in dynamically weak forcing conditions during the warm season.To improve the prediction accuracy of convective wind events,this research introduces a novel approach that combines machine learning techniques to identify varying meteorological flow regimes.Convective winds(CWs)are defined as wind speeds reaching or exceeding 17.2 m s^(-1)and severe convective winds(SCWs)as speeds surpassing 24.5 m s^(-1).This study examines the spatial and temporal distribution of CW and SCW events from 2013 to 2021 and their circulation dynamics associated with three primary flow regimes:cold air advection,warm air advection,and quasibarotropic conditions.Key circulation features are used as input variables to construct an effective weather system pattern recognition model.This model employs an Adaptive Boosting(AdaBoost)algorithm combined with Random Under-Sampling(RUS)to address the class imbalance issue,achieving a recognition accuracy of 90.9%.Furthermore,utilizing factor analysis and Support Vector Machine(SVM)techniques,three specialized and independent probabilistic prediction models are developed based on the variance in predictor distributions across different flow regimes.By integrating the type of identification model with these prediction models,an enhanced comprehensive model is constructed.This advanced model autonomously identifies flow types and accordingly selects the most appropriate prediction model.Over a three-year validation period,this improved model outperformed the initially unclassified model in terms of prediction accuracy.Notably,for CWs and SCWs,the maximum Peirce Skill Score(PSS)increased from 0.530 and 0.702 to 0.628 and 0.726,respectively,and the corresponding maximum Threat Score(TS)improved from 0.087 and 0.024 to 0.120 and 0.026.These improvements were significant across all samples,with the cold air advection type showing the greatest enhancement due to the significant spatial variability of each factor.Additionally,the model improved forecast precision by prioritizing thermal factors,which played a key role in modulating false alarm rates in warm air advection and quasi-barotropic flow regimes.The results confirm the critical contribution of circulation feature recognition and segmented modeling to enhancing the adaptability and predictive accuracy of weather forecast models.
文摘Large-scale wind turbine generator systems have strong nonlinear multivariable characteristics with many uncertain factors and disturbances. Automatic control is crucial for the efficiency and reliability of wind turbines. On the basis of simplified and proper model of variable speed variable pitch wind turbines, the effective wind speed is estimated using extended Kaiman filter. Intelligent control schemes proposed in the paper include two loops which operate in synchronism with each other. At below-rated wind speed, the inner loop adopts adaptive fuzzy control based on variable universe for generator torque regulation to realize maximum wind energy capture. At above-rated wind speed, a controller based on least square support vector machine is proposed to adjust pitch angle and keep rated output power. The simulation shows the effectiveness of the intelligent control.
基金Project(71071052) supported by the National Natural Science Foundation of ChinaProject(JB2011097) supported by the Fundamental Research Funds for the Central Universities of China
文摘Accurate forecasting of wind velocity can improve the economic dispatch and safe operation of the power system. Support vector machine (SVM) has been proved to be an efficient approach for forecasting. According to the analysis with support vector machine method, the drawback of determining the parameters only by experts' experience should be improved. After a detailed description of the methodology of SVM and simulated annealing, an improved algorithm was proposed for the automatic optimization of parameters using SVM method. An example has proved that the proposed method can efficiently select the parameters of the SVM method. And by optimizing the parameters, the forecasting accuracy of the max wind velocity increases by 34.45%, which indicates that the new SASVM model improves the forecasting accuracy.
文摘An accurate vertical wind speed(WS)data estimation is required to determine the potential for wind farm installation.In general,the vertical extrapolation of WS at different heights must consider different parameters fromdifferent locations,such as wind shear coefficient,roughness length,and atmospheric conditions.The novelty presented in this article is the introduction of two steps optimization for the Recurrent Neural Networks(RNN)model to estimate WS at different heights using measurements from lower heights.The first optimization of the RNN is performed to minimize a differentiable cost function,namely,mean squared error(MSE),using the Broyden-Fletcher-Goldfarb-Shanno algorithm.Secondly,the RNN is optimized to reduce a non-differentiable cost function using simulated annealing(RNN-SA),namely mean absolute error(MAE).Estimation ofWS vertically at 50 m height is done by training RNN-SA with the actualWS data a 10–40 m heights.The estimatedWS at height of 50 m and the measured WS at 10–40 heights are further used to train RNN-SA to obtain WS at 60 m height.This procedure is repeated continuously until theWS is estimated at a height of 180 m.The RNN-SA performance is compared with the standard RNN,Multilayer Perceptron(MLP),Support Vector Machine(SVM),and state of the art methods like convolutional neural networks(CNN)and long short-term memory(LSTM)networks to extrapolate theWS vertically.The estimated values are also compared with realWS dataset acquired using LiDAR and tested using four error metrics namely,mean squared error(MSE),mean absolute percentage error(MAPE),mean bias error(MBE),and coefficient of determination(R2).The numerical experimental results show that the MSE values between the estimated and actualWS at 180mheight for the RNN-SA,RNN,MLP,and SVM methods are found to be 2.09,2.12,2.37,and 2.63,respectively.
基金supported by Ningxia Natural Science Foundation Project(2023AAC02088)Liangshan Prefecture 2023 Annual Science and Technology Planning Project(23ZDYF0182).
文摘Under the context of global climate change,the frequent occurrence of strong winds in Guyuan has significantly hindered the development of local facility agriculture.Using hourly meteorological data from the Sanying National Station and the Guyuan Greenhouse Station between April 2024 and April 2025,this study employed machine learning methods to develop wind speed prediction models based on BP neural network,support vector machine,and random forest(referred to as BP,SVM,and RF models),aiming to provide references for local disaster prevention and mitigation.The results indicate that:1)Wind speed at the Guyuan Greenhouse Station exhibits the strongest correlation with that at the National Station(0.489-0.595),followed by temperature and 24-hour precipitation(0.116-0.336).2)The mean absolute error(MAE)of the BP,RF,and SVM models at all heights is below 1.5 m/s,the root mean square error(RMSE)is under 2.1 m/s,and the forecast accuracy(FA)exceeds 75%,indicating satisfactory model performance.Compared to 3 m,the MAE and RMSE of 0.5 m are larger,while the FA is smaller.This indicates that the wind speed of 0.5 m is close to the ground,and is more affected by surface roughness and turbulence effects,resulting in greater randomness and making the model more difficult.3)Based on case analyses of May 10 and May 1,2024,the overall simulation performance ranks as“RF model>SVM model>BP model”;however,the SVM model demonstrates higher accuracy in simulating strong wind events.
