Short-Term Load Forecasting Based on Maximal Information Coefficient Correlation Analysis and LSTM Optimization

Abstract

Accurate load forecasting plays a vital role in ensuring the economic, safe and reliable operation of power system. Power load forecasting is affected by many meteorological factors. In order to fully excavate the temporal characteristics of power load data and improve the accuracy of power load forecasting, a short-term power load forecasting method based on maximum information coefficient correlation analysis and LSTM optimization is proposed in this paper. Firstly, the maximum information coefficient is used to analyze the correlation between meteorological factors and load, the non-essential meteorological factors are removed. according to the analysis results, and a human comfort evaluation index is introduced. Secondly, the filtered meteorological data combined with load data are used as the input of the model, and the short-term load forecasting model is established based on the long-term and short-term memory neural network, and the Bayesian optimization algorithm is used to optimize the hyperparameters of the network model. Through the example analysis of the actual data of Guangzhou in China, the comparison of different decomposition methods shows that the load forecasting method can effectively improve the prediction accuracy.