CAJ | 학술논문

为了提高风电功率的预测精度，在分析其主要影响因素的基础上，针对T-S模糊神经网络收敛速度慢、计算量大等缺点，提出了一种改进型T-S模糊神经网络风电功率预测模型。首先采用椭圆基函数作为隶属函数，扩展其接收域；其次利用模糊C-均值聚类确定其中心值；然后引入惯性项加快网络的收敛速度；最后分别对四季短期风电功率进行预测。仿真结果表明，改进型T-S模糊神经网络有效地提高了短期风电功率的预测精度，具有一定的实用价值。
위료제고풍전공솔적예측정도，재분석기주요영향인소적기출상，침대T-S모호신경망락수렴속도만、계산량대등결점，제출료일충개진형T-S모호신경망락풍전공솔예측모형。수선채용타원기함수작위대속함수，확전기접수역；기차이용모호C-균치취류학정기중심치；연후인입관성항가쾌망락적수렴속도；최후분별대사계단기풍전공솔진행예측。방진결과표명，개진형T-S모호신경망락유효지제고료단기풍전공솔적예측정도，구유일정적실용개치。
In order to improve the prediction accuracy of wind power, on the basis of analyzing the major influencing factors, and to overcome the disadvantages of T-S fuzzy neural network, e. g. , slow convergence speed and huge amount of computation, the wind power prediction model based on improved T-S fuzzy neural network is proposed. Firstly the elliptic basis function ( EBF) is used as membership function to expand its receptive field;then fuzzy C-means clustering is used to determine the center value, and the convergence speed of the network is accelerated by introducing inertia term;finally the short term wind power in four seasons is predicted respectively. The simulation results show that the accuracy of wind power prediction for four seasons can be effectively enhanced by improved T-S fuzzy neural network, this method possesses certain practical value.