Your submission was sent successfully! Close

You have successfully unsubscribed! Close

Thank you for signing up for our newsletter!
In these regular emails you will find the latest updates about Ubuntu and upcoming events where you can meet our team.Close

Edge AI in a 5G world – part 2: Why make cell towers smart?

This article was last updated 4 years ago.


This is part of a blog series on the impact that 5G and GPUs at the edge will have on the roll out of new AI solutions. You can read the other posts here.

Recap

In part 1 we talked about the industrial applications and benefits that 5G and fast compute at the edge will bring to AI products. In this part we will go deeper into how you can benefit from this new opportunity.

Photo by NASA

Embedded compute vs Cost

Decades of Moore’s Law have given us smartphones at a price we’re willing to pay but IoT devices need to be much cheaper than that. Adding today’s fastest CPUs or GPUs to IoT devices costs a significant amount which put a hard limit on what the market is currently willing to buy at scale.

The IoT devices that are currently on the market are usually underpowered and have limited connectivity. With 5G connectivity and shared compute resources at the Edge these constrained devices will soon be able to do much more.

For instance, adding a GPU to each IoT device for the purposes of AI model inference would mean a significant increase in the hardware bill of materials. This cost would be passed onto the consumer and because it is more expensive would drastically reduce the target audience. Instead, 5G allows for heavy computation to be offloaded to nearby shared GPUs and get a response with minimal latency.

We will dive into this approach in the next section.

AI training & ML operations

Creating a new AI product has two engineering aspects to it, namely; 

  1. Model training and
  2. Inference

Model training refers to the machine learning that is usually done with ‘labelled data’ or simulations. This has big data and compute requirements.

Once the model has been trained, the implementation and operations of the inference is where much of the complexity appears. This is where we will focus most on this post, and in particular on real-time AI solutions.

During this blog series we will keep these two in mind given that the input data of today needs to be kept for it to be used as the training data of tomorrow. 

To illustrate this further in the next blog we will do a gap analysis of the technical requirements for model training, AI operations, as well as new techniques available to overcome these.


kubernetes logo

What is Kubernetes?

Designed with economics in mind, Canonical's solutions for telecommunications ensure ROI, providing first class quality at the same time.
Save costs by operating your infrastructure and applications the smart way, ensuring full automation from day 0 to day N.

Learn more about Ubuntu for telco ›

Newsletter signup

Get the latest Ubuntu news and updates in your inbox.

By submitting this form, I confirm that I have read and agree to Canonical's Privacy Policy.

Related posts

Canonical accelerates AI Application Development with NVIDIA AI Enterprise

Charmed Kubernetes support comes to NVIDIA AI Enterprise Canonical’s Charmed Kubernetes is now supported on NVIDIA AI Enterprise 5.0. Organisations using...

Meet Canonical at Mobile World Congress Barcelona 2024

The world’s largest and most influential telecommunications exhibition event, Mobile World Congress (MWC), is taking place in Barcelona on 26-29 February...

Data Centre AI evolution: combining MAAS and NVIDIA smart NICs

It has been several years since Canonical committed to implementing support for NVIDIA smart NICs in our products. Among them, Canonical’s metal-as-a-service...