Traffic Network Resilience Analysis Based On The GCN-RNN Prediction Model

Traffic network will inevitably appear to be congested. Once congestion occurs, the ability of the traffic network to quickly return to its original state to avoid affecting expansion will be critical. This work employs an efficient Graph Convolutional Network- Recurrent Neural Networks (GCN-RNN) prediction model to analysis the resilience of traffic network. Then, we trained the model by millions of GPS data. The result shows that the model can predict the trend of the state change of the road network well. At last, based on GCN-RNN model, we analyze the resilience of traffic network qualitatively and quantitatively, which has certain reference value for the resilience design of traffic network and the selection of network operation strategies.