Microgrid load prediction method based on deep learning

Abstract

The invention discloses a microgrid load prediction method based on deep learning. The microgrid load prediction method comprises the steps: collecting the historical load data of a plurality of different types of microgrids according to a set sampling time interval, wherein the historical load data comprises a load value and corresponding time information; performing feature conversion on the historical load data to obtain an input feature vector, and taking the input feature vector as a training set; inputting the training set into a deep neural network comprising a basic network module anda residual error network module for training to obtain a microgrid load prediction model; and inputting the historical load data of the to-be-predicted microgrid into the trained microgrid load prediction model to obtain a load prediction result of the to-be-predicted microgrid. According to the microgrid load prediction method, potential features of historical load data are fully mined by utilizing relatively high nonlinear mapping capability of the deep neural network, so that high-precision prediction of future loads is realized; and meanwhile, cross-regional micro-grid load prediction of different types is realized.

Description

technical field [0001] The invention belongs to the field of power system load forecasting, and more specifically, relates to a microgrid load forecasting method based on deep learning. Background technique [0002] The development of micro-grid can fully develop and utilize renewable energy and distributed power, and become an indispensable and powerful supplement to the large power grid. Microgrid is a self-controlling system that can help users realize self-management of power quality and energy efficient application. Microgrid load forecasting is related to the safe and economical operation of microgrids and stable system regulation, and at the same time provides an important support for the safe operation of large power grids. For residents' lives, the stability and safety of power systems directly affect people's quality of life. [0003] From the early 1960s to the present, many experts at home and abroad have done a lot of work in the field of load forecasting, and ...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the prior art, the purpose of the present invention is to provide a micro-grid load forecasting method based on deep learning, which aims to solve the problem that different types of micro-grid load forecasts need to independently perform model training and forecasting, resulting in a large number of forecasting models and a The problem of large storage space

Images