| Popis: |
Satellite network traffic is spatially and temporally dependent. Traditional network traffic prediction models are unable to extract the spatial and temporal characteristics of network traffic effectively. In this paper, a network traffic prediction model combined with graph convolutional neural network (GCN) and gated recursive unit (GRU) is proposed. On the basis of using GCN model to learn the topology of the satellite network and extract the spatial characteristics of the satellite network traffic, the data with spatial characteristics is used as the input of GRU model to learn the time change rule of satellite node attributes, and then extract the temporal characteristics of the satellite network traffic, and finally make the prediction through the full connection layer. The simulation experiment shows that compared with the single GRU model, the RMSE is reduced by 3.5% and 3% respectively under the prediction time step of 15min and 30min, indicating that the prediction model proposed in this paper can obtain the spatial correlation characteristics and obtain higher prediction accuracy from the satellite network traffic data. |
