基于灰色离散Verhulst模型理论的电力中长期负荷预测研究

Middle and long term power load forecasting based on grey discrete Verhulst model’s theory

针对传统GM(1,1)模型对呈"S型"规律增长的负荷序列建模预测时误差大的缺点,提出了灰色离散Verhulst模型。该模型借鉴了非齐次指数的离散灰色模型的建模机理,避免了经典灰色Verhulst预测模型由于参数估计采用离散方程而模拟和预测采用连续方程所带来的系统误差。给出了所提出的灰色离散Verhulst模型的递推解的形式。根据灰色预测理论的预测特点,采用等维灰数递补预测法对灰色离散Verhulst模型进行改进。通过实例证明,所提出的方法是正确和有效的。

This paper puts forward discrete grey Verhulst model to overcome the shortage that traditional GM （1, 1） model shows great error when it is used to forecast the ＂S＂ type sequence. This model is based on the theory of non-homogeneous index discrete grey model. It avoids the system error of the classical grey Verhulst forecasting models, in which the parameter estimation adopts discrete equations, but simulation and forecasting uses continuous equation. Then, the recursive solution representation of the discrete grey Verhulst model is presented. According to the characteristics of grey forecasting theory, equal-dimension grey number addition forecasting method is used to improve the precision of grey discrete Verhulst model. The example shows that the proposed method is correct and effective.