A Short-term Electric Load Forecasting Method Based on CNN-IPSO-GRU Hybrid Model

Abstract

The invention discloses a short-term power load forecasting method based on the CNN‑IPSO‑GRU hybrid model. Firstly, data such as power grid historical load, meteorological factors and date information are collected, and after data normalization processing is performed, a training set and a test set are divided. Using convolutional neural network technology to extract multi-dimensional feature vectors representing load changes, constructing time series as the input of the model; then building a gated recurrent unit network prediction model, and using the training set data to improve the gated recurrent unit network by improving the particle swarm optimization algorithm The prediction model is optimized to obtain two optimal prediction model parameters, and the obtained optimal prediction model parameters are used to re-establish the gated cyclic unit network model; finally, the short-term load prediction of the power grid is realized with the test set data. The method provided by the invention can accurately predict the short-term load change trend of the power grid, and further play an important role in reducing the loss of the generating set and ensuring the economical and reliable operation of the power grid.

Description

technical field [0001] The invention relates to a power load forecasting method, in particular to a short-term power load forecasting method based on a CNN-IPSO-GRU hybrid model. Background technique [0002] With the rapid development of my country's power market, efficient and accurate short-term load forecasting is an important part of power grid research. Accurate short-term load forecasting plays an important role in reducing the loss of generator sets and ensuring the economical and reliable operation of the power grid. Therefore, it is urgent to develop a new method to improve the accuracy of load forecasting and improve the economic benefits of the power grid. [0003] Over the years, many scholars at home and abroad have conducted a lot of research on short-term load forecasting, which can be summarized into three categories: statistical methods, model combination methods, and machine learning methods. Statistical methods mainly include time series models, fuzzy fo...

AI Technical Summary

Problems solved by technology

GRU is improved on the basis of LSTM structure. Compared with LSTM, its own structure is simpler, faster convergence speed and higher prediction accuracy. Because some parameters usually need to rely on traditional experience when using GRU model for prediction. selection, with uncertainty, leading to a decrease in the prediction efficiency and accuracy of the model

Particle swarm optimization (PSO) has the advantages of fewer adjustment parameters, simple iterative optimization ideas, and fast convergence speed. It is widely used in determining model parameters. However, PSO algorithm is easy to fall into local optimum during the optimization process. It leads to defects such as large error results, so an improved particle swarm optimization (IPSO) is proposed to enhance the optimization ability of model parameters

Images