Title: Efficient data collection for self-organising traffic signal systems based on vehicular sensor networks
Authors: Bartłomiej Płaczek
Addresses: Institute of Computer Science, University of Silesia, Będzińska 39, 41-200 Sosnowiec, Poland
Abstract: The development of traffic signal systems based on vehicular sensor networks (VSNs) requires new methods to enable real-time collection and processing of the data registered by sensor-equipped vehicles. Owing to the large amounts of sensor readings, there is a necessity of selecting the data that have to be transferred to control nodes. Moreover, the control nodes need an appropriate algorithm to effectively utilise the information which is delivered from individual vehicles. This paper presents an approach, which enables efficient collection and utilisation of the detailed data from VSN for controlling traffic signals in a road network. A self-organising control strategy is used in the analysed system. The amount of transmitted data is reduced by taking into account uncertainties estimated at control nodes. Results of simulation experiments show that the proposed approach outperforms state-of-the-art methods in terms of data transfers and average vehicle delay.
Keywords: VSNs; vehicular sensor networks; vehicular ad hoc networks; traffic signal control; data collection; self-organising systems; traffic model.
DOI: 10.1504/IJAHUC.2017.085720
International Journal of Ad Hoc and Ubiquitous Computing, 2017 Vol.26 No.1, pp.56 - 69
Received: 06 May 2014
Accepted: 17 Apr 2015
Published online: 10 Aug 2017 *