The price of carbon emission rights play a crucial role in carbon trading markets. Therefore, accurate prediction of the price is critical. Taking the Shanghai pilot market as an example, this paper attempted to design a carbon emission purchasing strategy for enterprises, and establish a carbon emission price prediction model to help them reduce the purchasing cost. To make predictions more precise, we built a hybrid deep learning model by embedding Generalized Autoregressive Conditional Heteroskedastic (GARCH) into the Gate Recurrent Unit (GRU) model, and compared the performance with those of other models. Then, based on the Iceberg Order Theory and the predicted price, we proposed the purchasing strategy of carbon emission rights. As a result, the prediction errors of the GARCH-GRU model with a 5-day sliding time window were the minimum values of all six models. And in the simulation, the purchasing strategy based on the GARCH-GRU model was executed with the least cost as well. The carbon emission purchasing strategy constructed by the hybrid deep learning method can accurately send out timing signals, and help enterprises reduce the purchasing cost of carbon emission permits.

翻译：碳排放权的价格在碳交易市场中发挥着关键作用。 因此,准确预测价格至关重要。 以上海试验市场为例,本文试图为企业设计碳排放采购战略,并试图建立碳排放价格预测模型,以帮助他们降低购买成本。 为了更精确的预测,我们建立了一个混合深层次学习模型,将通用自动递进条件性热血病(GARCH)模型嵌入门经常股(GRU)模型,并将该模型与其他模型的性能进行比较。 然后,根据冰山定律理论和预测价格,我们提出了碳排放权的购买战略。因此,GARCH-GRU模型5天滑动时间窗口的预测错误是所有6个模型的最低值。在模拟中,基于GARCH-GRU模型(GRCH-GRU)的采购战略也以最低成本执行。 混合深层次学习方法构建的碳排放采购战略可以准确地发送时间信号,帮助企业降低碳排放许可的购买成本。