Short-term passenger flow prediction under passenger flow control using a dynamic radial basis function network

Short-term passenger flow prediction and passenger flow control are essential for managing congestion in metros. This paper proposes a new dynamic radial basis function (RBF) neural network to forecast outbound passenger volumes and improve passenger flow control. First, we adopt a train timetable to model passenger flow propagation and identify potential stations that substantially impact the outbound volumes of the target stations. As a result, we incorporate inbound volume, outbound volume, and the train timetable to avoid overfitting. Second, passenger flow control is considered to improve the prediction accuracy by adding passenger flow control coefficients to our model, which then attempts to specify the true influence of these potential stations during crowded times. Finally, we construct a dynamic input radial basis function neural network whose performance is illustrated by the following three scenarios: large passenger flow under passenger flow control during morning peak hours, evening peak hours under passenger flow control, and normal passenger flow without passenger flow control. Compared with the backpropagation neural network, the wavelet support vector machine and the K-nearest neighbor, the proposed method achieves the best prediction performance at a half-hour prediction time lag. The proposed method can also identify crucial stations and time periods 30 min in advance, which contributes when considering proactive passenger flow control to alleviate congestion during peak hours in metro networks. •Passenger flow demand under congestion is predicted with big data.•A radial basis function neural network with dynamic input layer is introduced.•The proposed method outperforms other models illustrated by three scenarios.