FogFlow: Easy Programming of IoT Services Over Cloud and Edges for Smart Cities

Gürkan Solmaz

Abstract:

Smart city infrastructure is forming a large scale
Internet of Things (IoT) system with widely deployed IoT devices,
such as sensors and actuators that generate a huge volume of
data. Given this large scale and geo-distributed nature of such
IoT systems, fog computing has been considered as an affordable and sustainable computing paradigm to enable smart city
IoT services. However, it is still a major challenge for developers to program their services to leverage benefits of fog
computing. Developers have to figure out many details, such
as how to dynamically configure and manage data processing
tasks over cloud and edges and how to optimize task allocation
for minimal latency and bandwidth consumption. In addition,
most of the existing fog computing frameworks either lack service programming models or define a programming model only
based on their own private data model and interfaces; therefore, as a smart city platform, they are quite limited in terms
of openness and interoperability. To tackle these problems, we
propose a standard-based approach to design and implement a
new fog computing-based framework, namely FogFlow, for IoT
smart city platforms. FogFlow’s programming model allows IoT
service developers to program elastic IoT services easily over
cloud and edges. Moreover, it supports standard interfaces to
share and reuse contextual data across services. To showcase
how smart city use cases can be realized with FogFlow, we
describe three use cases and implement an example application
for anomaly detection of energy consumption in smart cities. We
also analyze FogFlow’s performance based on microbenchmarking results for message propagation latency, throughput, and
scalability.