基于Elman神经网络的甘肃电网负荷预测模型

为提高甘肃电网负荷预测精度,提出了一种基于神经网络的负荷预测方法。针对甘肃电力系统负荷数据的非线性和动态特性,在多层前向BP网络中引入特殊关联层,形成有“记忆”能力的Elman神经网络,从而可以映射系统的非线性和动态特性。在网络训练算法中,采用自适应学习速率动量梯度下降反向传播算法,显著提高了网络的训练速率,有效地抑制了网络陷入局部极小点。文中分别采用El-man神经网络与BP神经网络建立模型,对甘肃电网实际历史数据进行仿真预测,经分析比较,证明前者具有收敛速度快、预测精度高的特点。这表明利用Elman回归神经网络建模对甘肃电网负荷进行预测是可行的,能有效提高负荷预测精度,在负荷预测领域有着较好的应用前景。

Load Forecasting Model for Gansu Electric Power Network Based on Elman Neural Network

In order to improve the precision of load forecasting of Gansu electric power network, an artificial neural network (ANN) approach for load forecasting is proposed For the nonlinear and dynamic behaviors of load of Gansu electric power system, a special correlation layer is appended to hidden layer of BP network to form an Elman neural network with memorial ability, with which the nonlinearity and the dynamic behavior of the system can be mapped. In the training algorithm of the network, a back-propagation algorithm with adaptive learning speed and momentum gradient-falling is used, which can obviously improve the training speed of the network and effectively prevent the network to trap in local minimum. The forecasting model tested by actual data from Gansu electric network is established by using both Elman neural network and BP neural network. By analyzing and comparing, the former features quick convergence speed and high forecasting precision. The simulation results show that the method is feasible, which can effectively improve the precision of load forecasting and have bright prospect in load forecasting field.