IoT has been spreading like wildfire: millions of small devices have been gathering an increasing amount of data to be computed to centralized data centers. Until now. That amount of data has become so massive to push networks to the limit.
Edge computing aims to solve this issue by processing the data close to where it is produced. This distributes data centers, moving them to the edge of the network and creating clusters of embedded devices. However, distributed computation opens up to a number of novel design, deployment, and communication challenges.
In this session, we’ll go through some of them with respect to a real-world cluster of ARM computers. We’ll reason about the applicability of messaging protocols to send both data and commands within the cluster and how to implement the need for asynchronicity.
Design, Communication and Deployment of a Cluster at the Edge - A case study
Objective of the presentation:
In this session, we will present a real-world application running on a cluster of Cortex ARM computers which raises all kinds of architectural and implementation trade-offs.
The main takeaway will be the practical experience and the lessons we learned while solving the issues we mentioned in a real-world cluster of ARM devices. In particular, the session will focus on the technologies and on the architecture we employed. The audience will also see how HTTP can be used to expose functionality to the users and to update the entire cluster. Additionally, they will see how messaging protocols (such as MQTT) were used in practice to send data and commands within the cluster. Lastly, we will explain how we managed to keep the state consistent, both locally to each device (node) and globally (at the cluster level).
Attendee pre-requisites - If none, enter "N/A":
N/A