基于自组织映射网络的峰值负荷预测方法

Peak load forecasting using the self-organizing map

应用扩展自组织映射网络研究了电力系统峰值负荷预测问题。在传统的Kohonen自组织映射(SOM)网络的学习算法的基础上,为了提高电力系统峰值负荷预测的精度,进一步提出了一种扩展的自组织映射算法。在这个SOM网络中,除了权矩阵外,还有一个输入输出对的局部梯度(Jocobian)矩阵也被存储在神经元中。这样,在输出空间中梯度信息围绕输出权值产生了一个一阶扩展,便可得到一个输出的改进估计值。同时,提出了一个Jocobian矩阵的生成算法。最后采用纽约市的电力负荷数据为研究对象,证明了所提出方法的有效性。

The short-term load forecasting of electricity was studied by using an extended self-organizing map. A traditional Kohonen self-organizing map （SOM） was adopted to learn time-series load data with weather information as parameters. In order to improve the accuracy of the prediction, an extension of SOM algorithm based on error-correction learning rule was used, and the estimation of the peak load was achieved by averaging the output of all the neurons. As an implementation example, data of electricity demand from New York Independent System Operator （ISO） were used to verify the effectiveness of the learning and prediction for the proposed methods.