论文部分内容阅读
该文研究了基于改进的BP神经网络短期电力负荷预测模型,并在OpenStack云计算平台上采用Python编码实现了模型算法;应用电力负荷预测模型得到的预测结果误差率在0.02%~4.5%之间,很好地满足了短期电力负荷预测的精度要求。该文所涉及的OpenStack云计算平台的电力负荷预测模型比较完善,与有序用电管理结合可以大大提升有序用电管理工作的精细化程度,对有序用电方案的制定与实施具有重要的参考价值。
In this paper, the short-term power load forecasting model based on improved BP neural network is studied and the model algorithm is implemented by using Python code in OpenStack cloud computing platform. The prediction error rate of power load forecasting model is 0.02% ~ 4.5% , Well to meet the short-term power load forecasting accuracy requirements. The OpenStack cloud computing platform involved in this paper has a perfect power load forecasting model. Combining with the orderly power management, it can greatly improve the refinement of the orderly power management and is important for the formulation and implementation of an ordered power plan The reference value.