Electric power medium-and-long-term load prediction method based on a long-and-short-term memory model

Abstract

The invention discloses an electric power medium and long term load prediction method based on a long-and-short-term memory model, and relates to the technical field of electric power prediction. Themethod comprises the following steps of dividing regional loads in summer are into basic loads and cooling loads, and acquiring the load ratio by calculating the basic loads of different years; Selecting a high-temperature sequence fragment with the maximum probability of prediction years by utilizing a Markov model; Constructing a long-short-term memory model: summarizing and integrating the loadratio data and regional characteristic factors of the high-temperature sequence fragments so as to train and generate the long-short-term memory model for power load prediction; Performing model training and optimization; And predicting the power load of the time sequence segment of the future year. According to the method, the medium-and-long-term load of the electric power is predicted based onthe long-and-short-term memory model, and the relevance between the load of the region in the summer of the attack peak and the external condition characteristics is found, so that the regional loadunder different external conditions in the future is predicted, and the operation stability of a regional power grid is improved.

Description

technical field [0001] The invention belongs to the technical field of electric power forecasting, in particular to a medium and long-term electric power load forecasting method based on a long-short-term memory model. Background technique [0002] Power grid planning is the basis and prerequisite for power grid construction. The quality of planning will seriously affect the construction investment cost of the power grid and the safe operation of the power grid. The medium and long-term load forecasting is the theoretical basis of power grid planning, and the accuracy of the forecasting algorithm directly affects the planning scheme. credibility. Most of the current load forecasting algorithms are based on the relationship between power and regional economy, such as elastic coefficient method, output value unit consumption method, etc., or simple mathematical models, such as linear regression model, gray model, etc. The advantage of the above algorithm is that it is relativ...

AI Technical Summary

Problems solved by technology

The advantage of the above algorithm is that it is relatively intuitive and easy to use; the disadvantage is that the complexity of the algorithm is limited, the adaptability to changes is weak, and the prediction accuracy is limited

Images