Optimized traffic flow prediction model based on space-time diagram convolutional network

Abstract

The invention relates to an optimized traffic flow prediction model based on a space-time diagram convolutional network. Traffic flow prediction is defined as follows: for a specific road network structure, traffic flow data of several time steps in the future are predicted according to traffic flow data of several time steps recorded historically, wherein the model establishment comprises spatial correlation modeling; the structure of the graph is represented through a self-adaptive adjacency matrix obtained through model training; time correlation modeling is carried out, the calculation process of the gate and the hidden state of the GRU is full-connection operation, and GCN is used for replacing the gate and the hidden state of the GRU; a TPA mechanism is introduced; loss function is adopted, and the purpose of designing and training the model is to minimize an error between a model prediction value and a real value of a road node. According to the method, the accurate prediction precision of the short-time traffic flow is improved, the capability of the model for analyzing the data of the graph structure is enhanced, and the time-space dependence of the traffic flow can be fully mined, so that the prediction precision of the short-time traffic flow and the convergence speed of the model are improved.

Description

technical field [0001] The present invention relates to the technical field of traffic flow prediction, in particular to an optimized traffic flow prediction model based on spatio-temporal graph convolution network. Background technique [0002] Short-term traffic flow forecasting is a crucial part of the intelligent transportation system. Accurate short-term traffic flow forecasting can provide a strong basis for the decision-making of the traffic management department. pressure. However, the traffic flow prediction problem has always been a difficult problem due to the complex spatio-temporal dependence of traffic flow is difficult to analyze. [0003] With the development of deep learning, researchers began to try to use deep neural networks to solve the problem that the spatiotemporal dependence of traffic flow is difficult to analyze. Long-short-term memory network (LSTM) and gated recurrent unit (GRU) are all improved forms of cyclic neural network (RNN). They all in...

AI Technical Summary

Problems solved by technology

However, due to the complex spatio-temporal dependence of traffic flow is difficult to analyze, the problem of traffic flow prediction has always been a difficult problem

None of the above methods take into account the different influences of the output of different hidden layer nodes on the prediction results at all time steps.

[0007] Due to the difficulty of fully analyzing the spatio-temporal dependence of traffic flow, traditional methods have shown poor performance in forecasting tasks

Images