Daily power consumption prediction method based on VMD decomposition and LSTM network

Abstract

The invention relates to a daily power consumption prediction method based on VMD decomposition and an LSTM network. The method comprises the steps: carrying out variational modal decomposition on preprocessed data, wherein a modal number K is optimized through a Bayesian optimization algorithm; expanding related influence factors of the electricity consumption sequence data, wherein mapping parameters between the original data and the mapping data are obtained through optimization of a Bayesian optimization algorithm; dividing the expanded data of the related influence factors into a training set, a verification set and a test set; training each sub-mode through an LSTM model, and calculating a root-mean-square error through comparison of the test set and the verification set; reconstructing and reversely normalizing the prediction result, and determining whether a termination condition is met or not; and inputting the optimized mapping parameters into an LSTM model, using the training set and the verification set as new training data, performing reconstruction and reverse normalization on test data, and outputting a prediction result. The relation between the key factors and the power consumption sequence can be accurately described, and the daily power consumption prediction precision is improved.

Description

technical field [0001] The invention belongs to the technical field of power consumption forecasting, and in particular relates to a daily power consumption forecasting method based on VMD decomposition and LSTM network. Background technique [0002] The forecast of daily electricity consumption is a complex problem, and the complexity is mainly manifested in: (1) affected by the type of power user, the fluctuation of electricity consumption is large and shows obvious time period; (2) the electricity consumption is affected by Influenced by factors such as weather factors, holiday factors, and economic conditions, the volatility is relatively large, that is, it has a greater correlation with meteorological factors, policy regulation date types, etc. Daily demand forecasting is to establish the functional relationship between load and these related factors by observing historical data and using reliable methods and means. There are many factors affecting the power load, and ...

AI Technical Summary

Problems solved by technology

There are many factors affecting the power load, and the selected factors themselves have uncertainties. The quantitative relationship between these factors and the power load also has certain uncertainties, so it is difficult for people to make a relatively clear quantification of demand forecasting.

Images