In order to improve the accuracy and efficiency of mid-term power load forecasting, a mid-term power load forecasting method of long short time memory network (LSTM), which combines weather factors, is proposed. Firstly, the influence of meteorological factors affecting the power load on the mid-time power load is analyzed. Secondly, the meteorological factors are used as the input factor of the LSTM model to predict the power load. Finally, compared with the Random forest, ARIMA, GBDT, the LSTM algorithm which is not fused with meteorological factors, through the analysis of the experimental data, the LSTM fusion of meteorological factors has a better prediction effect on the mid-term load forecasting.
CITATION STYLE
Su, X., Jiang, X. hua, Zhang, S. miao, & Chen, M. long. (2019). LSTM power mid-term power load forecasting with meteorological factors. In Smart Innovation, Systems and Technologies (Vol. 128, pp. 96–103). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-04585-2_12
Mendeley helps you to discover research relevant for your work.