基于CEEMDAN SE和DBN南网发电侧燃料量预测研究

Prediction of Fuel at Power Plant of South Grid Based on CEEMDAN-SE and DBN

基于发电侧燃料量大数据建立南方电网发电侧燃料量预测模型.为提高预测精度,提出一种基于噪声自适应完全集合经验模态分解样本熵(CEEMDAN SE)和深度信念网络的发电侧煤电燃料量预测模型.利用CEEMDAN SE方法,将原始燃料量信号序列分解为多个特征互异的子序列,计算各个子序列的样本熵值,根据熵值将子序列重组简化,提高预测精度、减小计算规模;重组后的序列分别构建深度信念网络预测模型,叠加得到最终预测模型.利用该预测模型对南方电网2020年发电侧煤电燃料量数据进行预测,通过与实际值比较,表明该组合预测模型具有较高的预测精度,为预测发电侧燃煤库存提供了有效手段,进一步提高了电网安全性.

Based on the big data of power generation side fuel inventory,a prediction model for power generation side fuel inventory of South grid is established.In order to improve the prediction accuracy,this paper proposes a coal,electricity and fuel inventory prediction model at the power generation side based on adaptive noise complete set empirical mode decomposition(CEEMDAN)-sample entropy(SE)and deep belief network(DBN).CEEMDAN sample entropy is used to decompose the original inventory signal sequence into multiple sub sequences with different characteristics.The sub sequences with similar entropy are reorganized and simplified by sample entropy,which reduces the impact of the original non-stationary sequence on the prediction accuracy and reduces the calculation scale.Different DBN prediction models are constructed for each new sequence.Finally,the prediction results are superimposed to obtain the final prediction value.The prediction model is used to predict the coal and electricity fuel quantity data on the power generation side of the South Power Grid in 2020.Compared with the actual value,it shows that the combined prediction model has high prediction accuracy,providing an effective means for power grid dispatching to predict the coal inventory on the power generation side,and further improving the security of the power grid.