Click here to flash read.
To effectively process data across a fleet of dynamic and distributed
vehicles, it is crucial to implement resource provisioning techniques that
provide reliable, cost-effective, and real-time computing services. This
article explores resource provisioning for computation-intensive tasks over
mobile vehicular clouds (MVCs). We use undirected weighted graphs (UWGs) to
model both the execution of tasks and communication patterns among vehicles in
a MVC. We then study low-latency and reliable scheduling of UWG asks through a
novel methodology named double-plan-promoted isomorphic subgraph search and
optimization (DISCO). In DISCO, two complementary plans are envisioned to
ensure effective task completion: Plan A and Plan B.Plan A analyzes the past
data to create an optimal mapping ($\alpha$) between tasks and the MVC in
advance to the practical task scheduling. Plan B serves as a dependable backup,
designed to find a feasible mapping ($\beta$) in case $\alpha$ fails during
task scheduling due to unpredictable nature of the network.We delve into into
DISCO's procedure and key factors that contribute to its success. Additionally,
we provide a case study that includes comprehensive comparisons to demonstrate
DISCO's exceptional performance in regards to time efficiency and overhead. We
further discuss a series of open directions for future research.