数据驱动下造纸过程短期电力负荷预测研究

Study on Short Term Power Load Forecasting of Papermaking Process Driven by Data

造纸过程中对于短期电力负荷量的设置,参考预测值结果,因此若发生实际负荷量大于预测结果的情况,则会导致造纸工作任务的失败。为顺利实施造纸工作任务,针对数据驱动下的造纸过程短期电力负荷预测方法展开研究。按照数据驱动模型定义条件,设计电力等效电路,并以此为基础,求解短期电力负荷空间方程,完成数据驱动下的造纸过程短期电力负荷量预估。基于数据驱动模型,构建预测决策树组织,并根据短期电力负荷向量搜索结果,确定负荷值预测参数的实际取值范围,实现数据驱动下造纸过程短期电力负荷预测方法的设计。实验结果表明,依照数据驱动模型预测值设置短期电力负荷量,可以确保实际负荷量不超过预测结果,不会造成造纸工作任务失败的问题。

The setting of short-term power load in the papermaking process refers to the predicted value result,so if the actual load is greater than the predicted result,it will lead to the failure of the papermaking task.In order to implement the task of papermaking smoothly,a data-driven short-term power load forecasting method for papermaking process was studied.According to the definition conditions of the data-driven model,the power equivalent circuit is designed,and based on this,the short-term power load space equation is solved to complete the short-term power load prediction of the paper making process under the data-driven model.Based on the data-driven model,the prediction decision tree is constructed,and the actual value range of the load prediction parameters is determined according to the search results of the short-term power load vector,and the data-driven short-term power load prediction method is designed.The experimental results show that setting the short-term power load according to the predicted value of the data-driven model can ensure that the actual load does not exceed the predicted result,and will not cause the failure of papermaking task.