PSO-GRU Based Short-Term Traffic Flow Prediction

Abstract

Abstract In order to further improve the accuracy of short-term traffic flow prediction, a short-term traffic flow prediction method based on particle swarm (PSO) optimised gated recurrent unit (GRU) is proposed. And PSO is used to find the optimal parameter combinations of the GRU, and the parameters to be optimised are the initial learning rate of the neural network, the learning descent factor and the number of neurons in the hidden layer. In order to verify the effectiveness of the proposed model, the traffic flow data provided by PEMS database is used for example verification. The results show that the prediction model proposed in this paper is able to describe the law of traffic flow changes well and has higher prediction accuracy than the traditional BP and SVM models.