Fog computing brings cloud capabilities closer to the
Internet of Things (IoT) devices. IoT devices generate a tremendous amount of stream data towards the cloud via hierarchical
fog nodes. To process data streams, many Stream Processing
Engines (SPEs) have been developed. Without the fog layer, the
stream query processing executes on the cloud, which forwards
much traffic toward the cloud. When a hierarchical fog layer is
available, a complex query can be divided into simple queries to
run on fog nodes by using distributed stream processing. In this
paper, we propose an approach to assign stream queries to fog
nodes using container technology. We name this approach Stream
Queries Placement in Fog (SQPF). Our goal is to minimize end-to-end delay to achieve a better quality of service. At first, in
the emulation step, we make docker container instances from
SPEs and evaluate their processing delay and throughput under
different resource configurations and queries with varying input
rates. Then in the placement step, we assign queries among fog
nodes by using a genetic algorithm. The practical approach used
in SQPF achieves a near-the-best assignment based on the lowest
application deadline in real scenarios, and evaluation results are
evidence of this goal.
Evaluation of Load Prediction Techniques for Distributed Stream Processing
