Predictive model based on graph convolutional neural network
Aiming at the problems of low accuracy and poor stability of the existing electricity load forecasting models, an improvement based on Graph Convolutional Network (GCN) and Niche Immune Lion Algorithm (NILA) is proposed. Prediction model. First, niche immunity is used to limit the excessive repetiti...
Saved in:
Published in | 2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC) Vol. 6; pp. 479 - 483 |
---|---|
Main Authors | , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
04.03.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Aiming at the problems of low accuracy and poor stability of the existing electricity load forecasting models, an improvement based on Graph Convolutional Network (GCN) and Niche Immune Lion Algorithm (NILA) is proposed. Prediction model. First, niche immunity is used to limit the excessive repetition of similar individuals, so as to ensure the population diversity of the lion algorithm and significantly improve the optimization performance of the lion algorithm. Then, the lion algorithm is used to search for the optimal weights and thresholds of the convolutional neural network. The experimental results show that the NILA-GCN model in this study has good accuracy in the charge load forecasting. |
---|---|
ISSN: | 2693-289X |
DOI: | 10.1109/ITOEC53115.2022.9734716 |