Research on smart grid management and security guarantee of sports stadiums based on GCNN-GRU and self-attention mechanism

Abstract

Introduction: Smart grid management and security in sports stadiums have gained global attention as significant topics in the field of deep learning. This paper proposes a method based on the Graph Convolutional Neural Network (GCNN) with Gated Recurrent Units (GRU) and a self-attention mechanism. The objective is to predict trends and influencing factors in smart grid management and security of sports stadiums, facilitating the formulation of optimization strategies and policies. Methods: The proposed method involves several steps. Firstly, historical data of sports stadium grid management and security undergo preprocessing using the GCNN and GRU networks to extract time series information. Then, the GCNN is utilized to analyze smart grid data of sports stadiums. The model captures spatial correlations and temporal dynamics, while the self-attention mechanism enhances focus on relevant information. Results and discussion: The experimental results demonstrate that the proposed method, based on GCNN-GRU and the self-attention mechanism, effectively addresses the challenges of smart grid management and security in sports stadiums. It accurately predicts trends and influencing factors in smart grid management and security, facilitating the formulation of optimization strategies and policies. These results also demonstrate that our method has achieved outstanding performance in the image generation task and exhibits strong adaptability across different datasets.