Cooperative social driving in smart cities

Abstract

Most of the world population lives in urban areas, and it is expected that the number of
inhabitants in cities will be 75% of the world's population by 2050. Thus, a wide range
of challenges have to be faced by the different city stakeholders in order to mitigate the
negative effects of a very fast growth of such urban areas. One of the main concerns in
modern cities is mobility. The vast increment in the volume of urban road traffic
experienced during the last decades causes serious issues that have be confronted
with new tools. Traffic jams bother the daily life of the population, mainly because traffic
congestion causes longer trip times and a larger associated pollution, not to mention
the economic losses due to delays and other transport problems. Thus, great efforts
are being made to develop Smart Mobility solutions.
Vehicular ad hoc networks (VANETs) are based on the spontaneous creation of a
wireless network for data exchange between vehicles, mainly. Wireless networking
technologies are used in VANETs, including short range radio and cellular. These
communication networks are leading the automotive industry today, as they have led to
the emergence of the connected vehicle and the Social Cooperative Driving (CSD).
CSD allow drivers and vehicles to access different data sources in order to increase
the knowledge about the current road traffic status. Besides, other types of
infotainment services and applications can be deployed using VANETs.
File transferring is always an essential service in VANETs since their ultimate purpose
is the exchange of information among the nodes. Thus, it is desirable to optimize the file transferring protocol to provide the applications with the best service possible. One
of the ways to get such an efficient protocols is to better fit their configuration
parameters to the VANETs specifications. This study proposes the application of
Computational Intelligence to obtain automatically optimal protocol configurations for
vehicular environments. The main idea is to define the protocol configuration as an
optimization problem and address it by using intelligent tools, such as metaheuristics,
and a realistic simulation procedure to evaluate the obtained solutions.
In this work, we have carried out a real world testbed at streets of Málaga in order to
study the performance of the analyzed file transfer protocol by exchanging information
between cars in a real urban. These experiments have confirmed the efficiency of
configuring VANET nodes with protocols improved by applying our methodology.