Abstract:
Fog computing consists of modest capability fog nodes located close
to the data generation sources. These nodes are ideal for executing
small interactive tasks with a low latency requirement. Tasks that
are larger and more latency tolerant may be executed at the cloud
data center. A popular use case for fog computing is smart vehicles,
which consist of numerous sensors and actuators that automate
various tasks, such as traffic monitoring, braking and entertainment.
We propose a fog computing based framework for pushing over the
air (OTA) updates to smart vehicles. This allows the car manufacturers to push updates directly to the vehicles, without requiring a
visit to the dealership. To this end, we propose a Software Update
(SU ) algorithm that pushes OTA updates directly from fog nodes
to the vehicles. Further, we propose a Mobility Management (MM)
algorithm that takes into account the mobility of smart vehicles. In
order to reduce the number of handovers, an ILP formulation has
been proposed. Our experiments evaluate the impact of software
size, vehicle mobility, number of vehicles and data transmission
rate on OTA update performance. The experimental results using
dynamic fog nodes offer an improvement of approximately 37% in
OTA update time compared to updates using cloud data centers.
