【摘要】 针对传统的负荷密度指标的求取方法通常采用经验法或简单类比法,难以满足精度要求这一不足,从负荷密度与其影响因素存在着某种非线性关系的角度出发,提出了一种新颖的、基于自适应神经模糊系统(ANFIS)的负荷密度指标求取新方法。该方法用熵权法对影响因素的输入值进行加权处理,运用Fletcher-Reeves共轭梯度法改进ANFIS默认的混合学习算法,建立改进型ANFIS预测模型来求取负荷密度,克服了传统方法输出结果不可量化和精度不高等缺点。通过一个实例验证了该方法的实用性和有效性。更多还原

【Abstract】 The traditional methods to obtain load density are often based on experience or simple comparison,and the results can hardly meet the accuracy requirements.So a novel method to obtain load density based on ANFIS for distribution network is proposed according to the non-linear relation between load density and its influencing factors.The methodology of entropy weight coefficient is firstly used to treat the input value of every influencing factor with its weight,then the improved forecasting model of ANFIS is established to forecast the load density through using Fletcher-Reeves learning algorithm to improve the conventional mixed algorithm,which overcomes the conventional methods’ faults such as measurelessness of prediction result and low forecasting accuracy of the prediction model.Finally,the applicability and effectiveness of the method are demonstrated by using a real case.更多还原