期刊文献+

短期负荷预测神经网络方法比较

The Comparison of Neural Network Methods for Short- term Load Forecasting
下载PDF
导出
摘要 以某地区购网有功功率的负荷数据为背景,建立了三个BP神经网络负荷预测模型——SDBP、LMBP及BRBP模型进行短期负荷预测工作,并对其结果进行比较。针对传统的BP算法具有训练速度慢,易陷入局部最小点的缺点,采用具有较快收敛速度及稳定性的L—M优化算法进行预测,使平均相对误差有了很大改善,具有良好的应用前景。而采用贝叶斯正则化算法可以解决网络过度拟合,提高网络的推广能力,使平均相对误差和每日峰值相对误差降低,但收敛速度过慢(慢于SDBP模型),不适于在实际应用中采用。 Based on the load data of meritorious power of some area power system, three BP ANN models, SDBP, LMBP and BRBP Model, are established to carry out load forecasting work, and the results are compared. Since the traditional BP algorithm has some unavoidable disadvantages, such as slow training speed and possibility of local minimizing the optimized function, an optimized L- M algorithm, which can accelerate the training of neural network and improve the stability of the convergence, should be applied to forecasting to reduce of the mean relative error, and has a brightly applicable future. Bayesian regularization can overcome the over fitting and improve the generalization of an ANN, but it is not well in actual application because of its slow convergence rate.
作者 罗枚
出处 《陕西工业职业技术学院学报》 2009年第4期26-30,共5页 Journal of Shaanxi Polytechnic Institute
关键词 短期负荷预测 人工神经网络 L—M算法 贝叶斯正则化算法 优化算法 Short- Term Load Forecasting (STLF) ANN Levenberg - Marquardt algorithm Bayesian regularization algorithm optimized algorithms
  • 相关文献

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部