Improving Performance of Recurrent Neural Networks Using Simulated Annealing for Vertical Wind Speed Estimation

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.

An estimation method of soil wind erosion in Inner Mongolia of China based on geographic information system and remote sensing

Studies of wind erosion based on Geographic Information System（GIS） and Remote Sensing（RS） have not attracted sufficient attention because they are limited by natural and scientific factors.Few studies have been conducted to estimate the intensity of large-scale wind erosion in Inner Mongolia,China.In the present study,a new model based on five factors including the number of snow cover days,soil erodibility,aridity,vegetation index and wind field intensity was developed to quantitatively estimate the amount of wind erosion.The results showed that wind erosion widely existed in Inner Mongolia.It covers an area of approximately 90×104 km2,accounting for 80% of the study region.During 1985–2011,wind erosion has aggravated over the entire region of Inner Mongolia,which was indicated by enlarged zones of erosion at severe,intensive and mild levels.In Inner Mongolia,a distinct spatial differentiation of wind erosion intensity was noted.The distribution of change intensity exhibited a downward trend that decreased from severe increase in the southwest to mild decrease in the northeast of the region.Zones occupied by barren land or sparse vegetation showed the most severe erosion,followed by land occupied by open shrubbery.Grasslands would have the most dramatic potential for changes in the future because these areas showed the largest fluctuation range of change intensity.In addition,a significantly negative relation was noted between change intensity and land slope.The relation between soil type and change intensity differed with the content of Ca CO3 and the surface composition of sandy,loamy and clayey soils with particle sizes of 0–1 cm.The results have certain significance for understanding the mechanism and change process of wind erosion that has occurred during the study period.Therefore,the present study can provide a scientific basis for the prevention and treatment of wind erosion in Inner Mongolia.

Wind Estimation for UAV Based on Multi-sensor Information Fusion

Aiming at the requirements of accurate target positioning and autonomous capability for adapting to the environmental changes of unmanned aerial vehicle(UAV),a new method for wind estimation and airspeed calibration is proposed.The method is implemented to obtain both wind speed and wind direction based on the information from a GPS receiver,an air data computer and a magnetic compass,combining with the velocity vector triangle relationships among ground speed,wind speed and air speed.Considering the installation error of Pitot tube,cubature Kalman filter(CKF)is applied to determine proportionality calibration coefficient of true airspeed,thus improving the accuracy of wind field information further.The entire autonomous flight simulation is performed in a constant 2-D wind using a digital simulation platform for UAV.Simulation results show that the wind speed and wind direction can be accurately estimated both in straight line and in turning segment during the path tracking by using the proposed method.The measurement accuracies of the wind speed and wind direction are 0.62 m/s and2.57°,respectively.

The Identification of the Wind Parameters Based on the Interactive Multi-Models

The wind as a natural phenomenon would cause the derivation of the pesticide drops during the operation of agricultural unmanned aerial vehicles(UAV).In particular,the changeable wind makes it difficult for the precision agriculture.For accurate spraying of pesticide,it is necessary to estimate the real-time wind parameters to provide the correction reference for the UAV path.Most estimation algorithms are model based,and as such,serious errors can arise when the models fail to properly fit the physical wind motions.To address this problem,a robust estimation model is proposed in this paper.Considering the diversity of the wind,three elemental time-related Markov models with carefully designed parameterαare adopted in the interacting multiple model(IMM)algorithm,to accomplish the estimation of the wind parameters.Furthermore,the estimation accuracy is dependent as well on the filtering technique.In that regard,the sparse grid quadrature Kalman filter(SGQKF)is employed to comprise the computation load and high filtering accuracy.Finally,the proposed algorithm is ran using simulation tests which results demonstrate its effectiveness and superiority in tracking the wind change.

Wind and Actuator Fault Estimation for a Quadrotor UAV Based on Two-Stage Particle Filter

This paper investigates the problems of wind and actuator fault estimation for a quadrotor unmanned aerial vehicle(UAV).To e®ectively assess the safety and reliability of a quadrotor UAV in the presence of unknown wind disturbances,a two-stage particle filter(TSPF)scheme is proposed to obtain the simultaneous estimation of winds and actuator faults that may degrade the performance of the vehicle.In this scheme,the first-stage particle filter is used to estimate the states of the quadrotor UAV,and the second-stage particle filter is designed to produce estimates of unknown parameters,including the wind disturbances and actuator faults.To mitigate the degeneracy and impoverishment issues,the second-stage particle filter admits a parallel implementation of increased particle samplings for the wind and actuator fault estimation.Finally,simulation results are presented to demonstrate the e®ectiveness of the proposed scheme.

Charging-rate-based Battery Energy Storage System in Wind Farm and Battery Storage Cooperation Bidding Problem

Wind power has been proven to have the ability to participate in the frequency modulation(FM)market.Using batteries to improve wind power stability can better aid wind farms participating in the FM market.Battery energy storage system(BESS)has a promising future in applying regulation and load management in the power grid.For regulation services,normally,the regulation power prediction is estimated based on the required maximum regulation capacity;the power needed for the specific regulation service is unknown to the BESS owner.However,this information is needed in the regulation model when formulating the linearised BESS model with a constraint on the state of charge(SoC).This compromises the accuracy of the model greatly when it is applied for regulation service.Moreover,different control strategies can be employed by BESS.However,the current depth of discharge(DoD)based models have difficulties in being used in a linearization problem.Due to the consideration of the control strategy,the model becomes highly nonlinear and cannot be solved.In this paper,a charging rate(C-rate)based model is introduced,which can consider different control strategies of a BESS for cooperation with wind farms to participate in wind farm estimation error compensation,load management,energy bid,and regulation bid.First,the limitation of conventional BESS models are listed,and a new C-rate-based model is introduced.Then the C-rate-based BESS model is adopted in a wind farm and BESS cooperation scheme.Finally,experimental studies are carried out,and the DoD model and C-rate model optimization results are compared to prove the rationality of the C-rate model.

Efficient method for wind velocity estimation and power-extraction maximization using a fourth-order Luenberger observer in a wind-energy-conversion system

This paper proposes an advanced method for estimating numerous parameters in a wind-energy-conversion system with high precision,especially in a transient state,including the rotation speed and mechanical torque of the turbine as well as wind velocity.The suggested approach is designed into two parts.First,a fourth-order Luenberger observer is proposed to take into account the significant fluctuations of the mechanical torque that can be caused by wind gusts.This observer provides an accurate estimate of speed and mechanical torque in all weather conditions and especially when the wind is gusting.At the same time,the wind velocity is calculated using the Luenberger observer outputs and a model of the mechanical power generated by the turbine.Second,these estimated parameters are exploited as input in a maximum-power-point tracking(MPPT)algorithm using the tip-speed ratio(TSR)to improve the sensorless strategy control.Simulation results were performed using MATLAB®/Simulink®for both wind gust and real wind profiles.We have verified that for wind gusts with jumps ranging from 3 to 7 m/s,the new observer manages to better follow the rotation speed and the torque of the turbine compared to a usual observer.In addition,we demonstrated that by applying the proposed estimator in the improved TSR-MPPT strategy,it is possible to extract 3.3%more energy compared to traditional approaches.

APPLICATION OF MEM SPECTRAL ESTIMATION TO MU RADAR OBSERVATION

Preliminary results of the wind velocity estimation using the Maximum Entropy Method (MEM) to MU radar observation data sets are presented. The comparison of the results from the periodogram method and the MEM shows that the MEM estimation is reliable, and has higher accuracy, resolution and detectability than the estimation from periodogram method. The high accuracy power spectrum obtained by the MEM is very useful to studying the atmospheric turbulence structure. However. the MEM needs the longer computing time for obtaining the high accuracy spectrum. Particularly, the estimation of MEM will bring serious devia- tion at lower signal-to-noise ratio.