地区电网用电特性分析及年用电量预测

Annual Electricity Demand Forecasting in Local Power Systems Based on Gray-RAN Neural Network

利用灰色预测原理简单、建模数据少和运算方便的优点,结合神经网络非线性函数逼近能力强的特性,在此基础上提出了灰色-神经网络预测方法,并对哈尔滨市用电量进行了的仿真预测。

The gray-neural network combination forecasting method is presented to predict city electricity demand. At first, the gray GM （ 1,1 ） model applied on basis of the different history data to forecast city electricity demand. Secondly, the gray GM （ 1,1 ） model is modified by revised parameter method, original data pro- cessed mean method and the equal-dimension new signal method to get the forecasting values from above modified forecasting methods. Furthermore, the weighted forecasting method on gray related degree is used to get different forecasting values from above modified forecasting methods. At last, the national economy development is considered to the forecasting model by using artificial neural network, which makes the combination method more practical and reasonable. Applying the presented forecasting method to Haerbin power network shows and proves the high precision and more adoption.