In the history of computing, the pendulum has faithfully swung every 10 to 15 years between centralized and distributed models. However, given the sheer volume of networked devices going forward, we need a smarter edge because it simply isn’t feasible to send all data directly to the cloud.
The articles within this issue of Methods talk about latency, bandwidth, and security as key technical reasons for a smarter edge. However, there’s a big kicker— the “total lifecycle cost” of data. People that start with cloud-centric analytics often quickly realize that it gets expensive fast when chatty IoT devices hit public-cloud application-programming interfaces (APIs).
The majority of IoT data is “perishable,” meaning if you don’t create an alert or take action based on the data at the moment, it’s not going to do you much good later. A smarter edge will enable a combination of taking action, storing, forwarding, and scrapping data on the spot.
In this issue, read these articles from technical experts:
- A View from the Edge: An Introduction to the Smarter Edge
- Making the Case for a Smarter Edge: The Six Vs of IoT Data
- AI at the Edge Requires Balance of Capable, Flexible Hardware
- AI Processing for IoT: Where Clouds Give Way to a Smart Edge
- Could the Edge End the Connectivity Wars?
- Network Design: Intermediate Interface Nodes for Critical IoT Network Applications
- How AI at the Edge Will Change Engineering
- Device Security in a Larger Edge-Cloud Model