Multi-factor short-term load prediction method based on PCA-DBILSTM

Abstract

The invention discloses a multi-factor short-term load prediction method based on PCA-DBILSTM (Principal Component Analysis-DBILSTM). Firstly, normalization and One hot encoding are carried out on original input data to obtain a multi-dimensional matrix, principal component extraction is carried out on the multi-dimensional matrix by utilizing a PCA method, and then prediction is carried out by utilizing a DBILSTM network prediction model. Compared with a traditional power load prediction method, the method has the advantages that the average absolute percentage error (MAPE) and the root-mean-square error (RMSE) are both reduced, and the result shows that the method has high prediction precision.

Description

technical field [0001] The invention relates to a multi-factor short-term load forecasting method based on PCA-DBILSTM. Background technique [0002] Load forecasting plays a leading role in power system planning, energy trading, and power system operation. Since the early 1990s, the monopoly-managed electricity sector has been reshaped by adding deregulated structures and introducing competitive markets. Short-term load forecasting is crucial to the reliable operation of power systems. Short-term load forecasting of electric power system is a method based on historical load data, fully considering weather, holidays and other factors to predict the load in the next few hours or days. The accuracy of load forecasting will directly affect the security and economy of the power system. In the smart grid environment, with the development of distributed power generation, energy storage devices, and electric vehicles, traditional power load forecasting methods can no longer meet...

AI Technical Summary

Problems solved by technology

However, for large-scale sample learning, the calculation time is high and the calculation efficiency is low.

In the literature, recurrent neural network (RNN) is used to solve the defect that the feedforward neural network cannot process sequence data, but the storage capacity of RNN is limited. As the interval between time series increases, the original hidden layer Some information will be overwritten, resulting in the lack of previous information, and it is easy to cause the gradient to disappear

Images