Paper
25 September 2023 Power system load prediction model based on dual attentionmechanism gate recurrent unit neural network
Jian Liu, Tiantian Liang
Author Affiliations +
Abstract
This paper proposes a dual attention mechanism gate recurrent unit (DAGRU) neural network model for predicting the overload of the power system load. Based on the GRU neural network, the dual attention mechanism of feature and time is introduced to dig the potential correlation between the output and input characteristics of the power system load. Among which, the feature attention is utilized to analyze the relationship between historical information and input, and then timing attention is utilized to automatically extract the historical information of key points in GRU network to improve the stability of time series prediction. The simulation results show that compared with GRU and LSTM networks, the proposed DAGRU network model improves the prediction accuracy of electrical load.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Jian Liu and Tiantian Liang "Power system load prediction model based on dual attentionmechanism gate recurrent unit neural network", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 127885F (25 September 2023); https://doi.org/10.1117/12.3004251
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Education and training

Neural networks

Systems modeling

Data modeling

Deep learning

Performance modeling

Intelligence systems

Back to Top