Short-term reactive load prediction method and system

Abstract

The invention relates to a short-term reactive load prediction method and system, and the method comprises the steps: building a sample matrix of each node of a power system at a prediction moment according to the observation information of each node of the power system at each historical prediction moment before the prediction moment; and determining short-term reactive load prediction data of each node of the power system at the prediction moment by utilizing an attention mechanism according to the sample matrix of each node of the power system at the prediction moment. According to the technical scheme provided by the invention, the accuracy and effectiveness of reactive load prediction are improved.

Description

technical field [0001] The invention relates to the field of grid load forecasting, in particular to a short-term reactive load forecasting method and system. Background technique [0002] With the deepening of the reform of the power industry system and the development of the national economy, accurate forecasting of future power loads is becoming more and more important. Power load forecasting is a basic tool to ensure power quality, especially short-term load forecasting for one or several days in the future, which is the basis of power plant's daily power generation plan. The main influencing factors to be considered in short-term load forecasting are: 1) the type of working day, the load level on weekends is lower than that on working days; 2) weather conditions, mainly including temperature, precipitation, wind force, humidity, etc.; 1. For major festivals and manufacturers such as National Day and New Year’s Day, the load pattern is different from the normal situatio...

AI Technical Summary

Problems solved by technology

In the past, when some researchers were doing load analysis, they simply converted the reactive power directly through the active power and power fa

Images