基于Markov-GNNM的煤炭需求量预测模型研究

Research on forecasting model of coal demand based on Markov-GNNM

煤炭资源在我国能源消费总量中仍然占据主导地位,准确预测煤炭的需求量对我国经济发展和产业结构升级有着重大意义,针对传统煤炭需求量预测单一预测方法的缺陷,建立了组合灰色神经网络模型,为进一步提高模型精度,选用马尔科夫模型缩小预测残差范围来修正组合模型,进而建立了Markov—GNNM组合模型,旨在为准确预测煤炭需求量提供模型依据。选取2000—2018年我国煤炭需求量数据进行实证分析,预测结果表明该模型预测精度高,适用于煤炭需求量预测。

Coal still occupy a dominant position in China’s total energy consumption,and accurate prediction of coal demand is of great significance to economic development and industrial structure upgrade in China.In view of the shortcomings of the traditional coal demand forecasting single forecast method,a combined gray neural network model was established.In order to further improve the accuracy of the model,the Markov model was selected to narrow the prediction residual range to modify the combined model,and then the Markov-GNNM combined model was established to provide a model basis for accurately predicting coal demand.The data of coal demand from 2000 to 2018 in China is selected for empirical analysis,and the prediction results show that the model has high prediction accuracy and is suitable for coal demand forecasting.