A Method For Short-Term Traffic Flow Forecasting Based On GCN-LSTM
Daoguang Liu, Shen Hui, Li Li, Zhigui Liu, Zhiming Zhang
Abstract
The prediction about short-term traffic flow is a crucial research field in Intelligent Transportation Systems (ITS), which focuses on forecasting traffic data to provide data for optimal traffic scheduling to reduce congestion. This paper presents a new deep learning network based on the graph convolution network (GCN) and long short-term memory (LSTM) unit. The model was trained and tested by using local traffic data from the city of Mianyang. After introducing the new deep learning network, a data reduction method is also established in this paper which was select the relevant road links as model’s input based on time correlation. Finally, the proposed algorithm is compared with other popular methods, and better results can be obtained in the conventional 5-minute prediction test. At the same time, the performance of this GCN-LSTM model can be maintained in different time range from 5 minutes to 125 minutes by multi-step prediction, which is much better than other models.