针对微电网短期负荷预测精度不够的问题，论文提出了一种基于双向长短时记忆(bidirectional long short-term memory，Bi-LSTM)深度学习的负荷预测方法。将影响家庭和商业负荷分布形成的参数为输入变量，以微电网的家庭和商业总负荷分布为目标，利用输入变量对Bi-STM网络进行训练，通过识别微电网的消费模式，对微电网负荷进行时预测。利用相关系数(R)、均方误差(MSE)和均方根误差(RMSE)等性能评价指标对预测结果进行分析。结果表明，Bi-LSTM方法具有较高的相关系数。
Deep Learning-Assisted Short-Term Load Forecasting for Sustainable Management of Energy in Grid
Aiming at the problem of insufficient short-term load forecasting accuracy of microgrid,this paper proposes a load forecasting method based on bidirectional long short-term memory(BI-LSTM)deep learning.The parameters affecting the forma-tion of household and commercial load distributions are used as input variables,and the total household and commercial load distri-bution of the grid is taken as the target.The input variables are used to train the BI-STM network.By identifying the consumption patterns of the grid,the grid load on-going is forecasted.Correlation coefficient(R),mean square error(MSE)and root mean square error(RMSE)and other performance evaluation indicators are used to analyze the prediction results.The results show that the BI-LSTM method has a higher correlation coefficient.
power griddeep learningshort-term load forecasting
国家科技期刊平台
NSTL
万方数据
