当前位置: X-MOL 学术J. Electr. Eng. Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Short-Term Load Forecasting Based on Deep Neural Networks Using LSTM Layer
Journal of Electrical Engineering & Technology ( IF 1.6 ) Pub Date : 2020-05-11 , DOI: 10.1007/s42835-020-00424-7
Bo-Sung Kwon , Rae-Jun Park , Kyung-Bin Song

Short-term load forecasting (STLF) is essential for power system operation. STLF based on deep neural network using LSTM layer is proposed. In order to apply the forecasting method to STLF, the input features are separated into historical and prediction data. Historical data are input to long short-term memory (LSTM) layer to model the relationships between past observed data. The outputs of the LSTM layer are incorporated with outputs of fully-connected layer in which prediction data, for instance weather information for forecasting day, are input. The optimal parameters of the proposed forecasting method are selected following several experiment. The proposed method is expected to contribute to stable power system operation by providing a precise load forecasting.

中文翻译:

使用LSTM层基于深度神经网络的短期负荷预测

短期负荷预测 (STLF) 对电力系统运行至关重要。提出了基于使用LSTM层的深度神经网络的STLF。为了将预测方法应用于 STLF,将输入特征分为历史数据和预测数据。历史数据被输入到长短期记忆 (LSTM) 层,以模拟过去观察到的数据之间的关系。LSTM 层的输出与全连接层的输出相结合,其中输入预测数据,例如预测日的天气信息。所提出的预测方法的最佳参数是通过几个实验来选择的。所提出的方法有望通过提供精确的负荷预测来促进电力系统的稳定运行。
更新日期:2020-05-11
down
wechat
bug