Power load prediction method based on improved long-term and short-term memory network

Abstract

The invention discloses a power load prediction method based on an improved long-term and short-term memory network. The method comprises steps of the characteristic of historical load being preliminarily screened by adopting the maximum information coefficient; the influence caused by load related factors being considered; and further screening the historical load by adopting a maximum correlation minimum redundancy algorithm, taking the screened feature set as the input of the model, carrying out power load prediction by adopting an improved long-short memory network, and verifying the obtained prediction result and the actual power grid load to prove the practicability of the model. According to the forecasting method (H-ILSTM) provided by the invention, the power load and related factors influencing the load are accurately considered, precision of power load forecasting is effectively improved, and safety and economy of power grid operation are improved to a certain extent.

Description

Technical field [0001] The present invention relates to the field of electricity load prediction, and more particularly to a power load prediction method based on an improved long-term memory network. Background technique [0002] Electricity load prediction plays a key role in the operation of the grid, and the accurate short-term load can greatly improve the safety and economy of the grid operation. In addition, it is also important for the optimal combination of the unit, economic scheduling, optimal trend, and electricity market transactions. The higher the accuracy of the electric power load forecast, the better the utilization of the power generation equipment, the better the economic scheduling. However, power load is very sensitive to external factors, such as climate change, date type, and social activities. These uncertainties increase the randomness of the load sequence. Therefore, how to identify the strong correlation factors of extracting loads from many influencing...

AI Technical Summary

Problems solved by technology

[0007] (1) There are many factors that affect the power load, and these factors cannot be reasonably considered in the load forecasting problem

[0008] (2) Existing feature selection for power load forecasting mostly considers the influence of a certain feature on its power load, and does not consider the effect of the combination of features and features on it

[0009] (3) Due to the large number of factors in the input of the forecasting model, the traditional machine learning method cannot achieve high accuracy in forecasting the power load

The traditional LSTM can achieve better prediction results, but due to its intricate structure, it takes a long time to train, which is inconvenient in practical application

Images