Power load prediction method and device, terminal and storage medium

Abstract

The invention provides a power load prediction method and device, a terminal and a storage medium. The method comprises the steps that variation factors and cross factors in a differential evolution algorithm are improved according to preset historical power load data, the improved differential evolution algorithm is obtained, an optimal solution is obtained, and the optimal solution is target power load data obtained through the historical power load data and the improved differential evolution algorithm; determining network parameters of a long short-term memory (LSTM) neural network model according to the historical power load data and the optimal solution; training the LSTM model through the historical power load data and the optimal solution to obtain an LSTM prediction model; and performing power load prediction according to the LSTM prediction model to obtain a prediction result. According to the invention, the accuracy of power load prediction can be improved.

Description

technical field [0001] The present invention relates to the technical field of power load forecasting, and in particular, to a power load forecasting method, device, terminal and storage medium. Background technique [0002] Power dispatch is an indispensable role in the operation of the power system, and accurate power load forecasting will reduce resource waste and power costs. Accurate short-term load forecasting can effectively improve the effectiveness of power dispatching. [0003] For the research on short-term power load forecasting, the main methods at home and abroad are statistical forecasting methods and machine learning methods. Statistical methods are divided into multiple linear regression models and time series models. Machine learning methods include expert systems (ES), support vector machines, and artificial neural networks (ANNs). Machine learning methods can solve the inability of statistical methods to deal with the influence of nonlinear factors on ...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a power load forecasting method, device, terminal and storage medium to solve the problem of low accuracy in short-term power load forecasting

Images