Distributed reactive power optimization method and device for electric power system load prediction

Abstract

The invention discloses a distributed reactive power optimization method and device for power system load prediction, and the method comprises the steps: dividing the power load information, meteorological information and holiday information of a prediction place into a test set of a plurality of input neurons and one output sample; establishing an initial LSTM network, and substituting the training set into the initial LSTM network for forward calculation and back propagation training; inputting neuron information required to be used by a prediction day through the trained LSTM network so asto perform load prediction on each time point; analyzing reactive compensation characteristics of the distributed power supply, and collecting target parameters of the distributed power supply to establish a reactive model of the distributed power supply; establishing a power grid reactive power optimization model taking minimum network loss as an objective function; and performing distributed optimization control calculation according to the reactive average utilization rate and the instantaneous communication topology matrix so as to realize distributed reactive optimization. According to the method, rapid and accurate load prediction can be obtained.

Description

technical field [0001] The invention relates to the technical field of power grid operation and distribution, in particular to a distributed reactive power optimization method and device for power system load forecasting. Background technique [0002] Power system load forecasting technology is a research that started a long time ago. Generally speaking, researchers will divide load forecasting into three categories: short-term, medium-term, and long-term forecasting. Neural network forecasting technology is often used in long-term load forecasting. [0003] Neural Network (Neural Network), also known as ANN (Aritificial Neural Networks, artificial neural network), abbreviated, used to distinguish it from Biological Neural Networks (Biological Neural Networks), is a general term for a series of models. It is generally believed that the artificial neural network is inspired by the biological neural network. The biological neural network generally refers to the network compo...

AI Technical Summary

Problems solved by technology

If the control and reactive power compensation of distributed power sources are not coordinated, a series of problems will arise: voltage changes, transient stability problems and even voltage collapse

Images