Title: Study on internet of vehicles traffic congestion detection algorithm based on big data

Authors: Minglei Song; Lihua Liu; Rongrong Li; Binghua Wu

Addresses: School of Civil and Transportation Engineering, Henan University of Urban Construction, Pingdingshan, Henan 467036, China ' School of Civil and Transportation Engineering, Henan University of Urban Construction, Pingdingshan, Henan 467036, China ' School of Civil and Transportation Engineering, Henan University of Urban Construction, Pingdingshan, Henan 467036, China ' School of Civil and Transportation Engineering, Henan University of Urban Construction, Pingdingshan, Henan 467036, China

Abstract: In order to improve the traffic congestion detection capability of the vehicle network, a vehicle network congestion detection algorithm based on big data is proposed. The algorithm uses the Small-World model to construct a traffic distributed internet, and uses RFID tag reading technology to sample and fuse big data in the vehicle network, and to extract the inherent modal feature quantity of the vehicle traffic big data internet, and the road traffic network. The overall state information is reorganised; according to the modal feature extraction results inherent in the vehicle traffic data interconnection network, the vehicle path is optimally scheduled, and according to the big data analysis result, the linear traffic planning algorithm is used to detect the vehicle traffic congestion network. The simulation results show that the proposed method has higher accuracy in vehicle traffic jam detection, and the detection time is below 10 s, and the efficiency is higher. The method can improve the anti-congestion capability of the vehicle and has a strong traffic diversion capability, thereby effectively improving the traffic effect of the vehicle in the network environment.

Keywords: big data; internet of vehicles; traffic; congestion detection.

DOI: 10.1504/IJVICS.2019.101502

International Journal of Vehicle Information and Communication Systems, 2019 Vol.4 No.2, pp.91 - 105

Received: 20 Oct 2018
Accepted: 05 Dec 2018
Published online: 11 Aug 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article