基于GRU门控单元网络的电力负荷预测研究

Research on power load forecasting based on GRU gated unit network

准确预测电力负荷,有利于提高电力系统供需平衡,为提高电力负荷预测精度,提出一种基于迁移学习的电力负荷预测模型。该模型以门控循环单元模型(GRU)为基础模型,通过设定最大均值差异算法阈值,从而选择迁移学习的模型,最终实现电力负荷雨预测。仿真结果表明,所提模型可准确预测电力负荷数据,相较于BPNN模型和LSTM模型,所提出模型的MAPE值更低,为17.5%,分别降低了15%和7.5%,具有更高的预测准确度,可用于电力负荷预测实际应用中。

Accurate prediction of power load is conducive to improving the balance between supply and demand in the power system.In order to improve the accuracy of power load forecasting,a power load prediction model based on transfer learning was proposed.Based on the gated recurrent unit model(GRU),the correlation between the data of the source domain and the target domain was measured by the maximum mean difference algorithm(MMD),and the transfer learning model was selected and adjusted according to the correlation to realize the power load prediction.The simulation results showed that the proposed model could accurately predict power load data.Compared to the BPNN model and LSTM model,the proposed model had a lower MAPE value of 17.5%,which was reduced by 15%and 7.5%,respectively.It had higher prediction accuracy and could be used in practical applications of power load forecasting.