A Hotspot for the Edge of Nowhere

Since the founding of the Open Edge Computing Initiative in 2014, the Carnegie Mellon University Living Edge Lab has been working with industry to identify and reduce the barriers to adoption for edge computing. Since then, industry has embraced the idea of putting meaningful computing resources “close” to where users are and using those resources to provide valuable edge-native applications that take advantage of this nearness. Great progress has been made in deploying edge infrastructure and applications in a variety of public and private environments. But, there are still significant barriers for an edge-native application developer to serve customers in areas where edge infrastructure has not yet been built out.

To truly realize the value of edge computing, there are three important infrastructure requirements:

1. The availability of significant computing resources near application users.
2. A low latency, high bandwidth access network between application users and the edge computing resources.
3. Connection to all services and data that the application and its users need to work.

In a large-scale deployment, computing resources are built out by an edge data center provider, the access network is provided by a mobile network operator (or other telecom operator) and services and data are provided by both the edge and the cloud.

But, what about a small-scale, urgent, and temporary deployment? Imagine using drones to inspect bridges and electric grid towers, mounting a search and rescue operation for a child lost in the woods, hosting a backcountry ski event for a weekend, and providing critical communication and application capabilities for forward military operations -- these are just a few situations where there is a need to deploy a modern compute and communication infrastructure very rapidly in areas with poor network coverage. See the figure below for an example Search and Rescue use case. In this use case, an on-site command center operator, a drone pilot, and two first responders collaborate to rescue an injured climber in the mountains. The edge-native application that supports this must provide computer vision to find the climber and video and audio collaboration between the four actors and the drone feed to coordinate the rescue. Overall system operation must be monitored at the command center. There may be no connection from the command center to the outside world.

We believe there are many use cases that could benefit from what we refer to as a “Just-in-Time Cloudlet”. The JIT Cloudlet bundles a mobile access network and edge-native applications into a small form factor. Over the last year, we’ve been closely working with Arm to develop a reference architecture and a JIT Cloudlet prototype based on commercial off-the-shelf technologies, open-source software, and a “Cloud-native at the Edge” design paradigm. Our prototype is architected to meet the key design criteria shown below:

We recently published CMU Technical Report, “The Just-in-Time Cloudlet” and recorded an ARM Tech Talk  that describe the need, drivers, and enablers for the concept. The Tech Report also describes in detail the reference architecture and the prototype built around it. You can find out there our test results against the above criteria and how to build your own. Please join us next week (October 17-19^th, 2023) in the Arm booth at the Open Compute Platform Summit in San Jose, CA.

REFERENCES:

James Blakley, Marc Meunier*, Thomas Eiszler, Jan Harkes, Mahadev Satyanarayanan, “The Just-In-Time Cloudlet”, Carnegie Mellon University Technical Report, CMU-CS-23-138, October 2023.

”Build an Edge Platform with your own Private Mobile Network”, Voices on Arm Tech Talk, October 3, 2023.

Open Compute Platform Summit, October 17-19, 2023, San Jose, California.