Article: Multi-intersection traffic flow prediction control based on vehicle-road collaboration V2X and improved LSTM Journal: International Journal of Information and Communication Technology (IJICT) 2024 Vol.25 No.11 pp.52 - 68 Abstract: Traditional multi-intersection traffic flow prediction and control methods often lack real-time and adaptability, and are difficult to cope with complex and changing traffic environments. To solve these two problems, this paper proposes a multi-intersection traffic flow prediction and control method based on vehicle-to-guideway collaboration (V2X) and improved LSTM. Firstly, real-time information interaction between vehicles and roadside devices is achieved through V2X technology. Secondly, an improved LSTM model introducing a sliding time window update mechanism is applied to the collected data to achieve high-precision prediction of traffic flow. Finally, a multi-intersection cooperative adaptive control strategy is designed based on the prediction results. The experimental results show that this method proposed in this paper reduces the average vehicle delay time by 29.0% and improves the road network throughput by 14.6% under high traffic conditions. Meanwhile, the improved LSTM model reduces the computation time from 135 ms to 55 ms. Inderscience Publishers - linking academia, business and industry through research

Title: Multi-intersection traffic flow prediction control based on vehicle-road collaboration V2X and improved LSTM

Authors: Renyong Zhang; Shibiao He; Peng Lu

Addresses: Information and Communication Technology Research Center, Chongqing Institute of Engineering, Chongqing, 400056, China ' Information and Communication Technology Research Center, Chongqing Institute of Engineering, Chongqing, 400056, China ' Information and Communication Technology Research Center, Chongqing Institute of Engineering, Chongqing, 400056, China

Abstract: Traditional multi-intersection traffic flow prediction and control methods often lack real-time and adaptability, and are difficult to cope with complex and changing traffic environments. To solve these two problems, this paper proposes a multi-intersection traffic flow prediction and control method based on vehicle-to-guideway collaboration (V2X) and improved LSTM. Firstly, real-time information interaction between vehicles and roadside devices is achieved through V2X technology. Secondly, an improved LSTM model introducing a sliding time window update mechanism is applied to the collected data to achieve high-precision prediction of traffic flow. Finally, a multi-intersection cooperative adaptive control strategy is designed based on the prediction results. The experimental results show that this method proposed in this paper reduces the average vehicle delay time by 29.0% and improves the road network throughput by 14.6% under high traffic conditions. Meanwhile, the improved LSTM model reduces the computation time from 135 ms to 55 ms.

Keywords: V2X; LSTM; multi-intersection traffic flow prediction; cooperative adaptive control; CAC; intelligent transport system.

DOI: 10.1504/IJICT.2024.143411

International Journal of Information and Communication Technology, 2024 Vol.25 No.11, pp.52 - 68

Received: 16 Oct 2024
Accepted: 01 Nov 2024
Published online: 18 Dec 2024 *

Title: Multi-intersection traffic flow prediction control based on vehicle-road collaboration V2X and improved LSTM

Keep up-to-date