论文部分内容阅读
基于地铁供电系统短期负荷预测是电力系统短期负荷预测精细化研究的需要,本文对地铁供电系统短期负荷预测系统进行了设计。系统由负荷统计模块、负荷数据调用模块、负荷预测模块、预测误差统计模块、图形输出模块和数据输出模块等6个模块组成,在负荷预测模块中构造了基于脉冲神经网络的地铁供电系统短期负荷预测模型,用该预测模型对地铁供电系统短期负荷进行预测,并将预测结果与传统BP-NN预测模型进行对比。结果表明,脉冲神经网络预测模型的平均预测误差降低了2%以上,比BP-NN预测模型的平均预测误差明显降低,表明脉冲神经网络预测模型的预测精度明显优于BP-NN预测模型,从而验证了地铁供电系统短期负荷预测系统采用脉冲神经网络预测模型的可行性;并且脉冲神经网络预测模型具有较好的预测稳定性,1周的预测精度稳定在7.01%~7.80%区间内。该模型取得较为满意的预测精度,为地铁供电系统短期负荷预测系统的实际应用提供了理论依据。
Based on the short-term load forecasting of metro power supply system is the need of fine-tuning short-term load forecasting of power system, this paper designs the short-term load forecasting system of metro power supply system. The system consists of six modules: load statistics module, load data call module, load forecasting module, forecast error statistics module, graphic output module and data output module. In the load forecasting module, the short-term load of subway power supply system based on pulse neural network The forecast model is used to predict the short-term load of the subway power supply system. The prediction results are compared with the traditional BP-NN prediction model. The results show that the average prediction error of the BP neural network prediction model is reduced by more than 2%, which is significantly lower than that of the BP-NN prediction model. It shows that the prediction accuracy of the BP neural network prediction model is obviously superior to that of the BP-NN prediction model The feasibility of using the pulse neural network to predict the short-term load forecasting system of subway power supply system is verified. And the prediction model of the pulse neural network has good predictive stability. The prediction accuracy of one week is stable at 7.01% -7.80%. The model obtains a more satisfactory prediction accuracy and provides a theoretical basis for the practical application of the short-term load forecasting system of the subway power supply system.