Building tomorrow’s telecommunications network today

So that’s an important part of the mission and we’re thinking about network design and architecture. It really isn’t even for the next three years. We are thinking about the next 20 and 50 years. Network investments take a long time, and we want to make those investments economically, but also ensure the most reliable network offerings.

Laurel: You mentioned Artificial Intelligence and Machine Learning in the previous answer. What are some of the ways AT&T is using AI and ML or thinking about using artificial intelligence?

Raj: Great question and also very timely. As a company, we have had researchers working on AI for many years. With the advent of much more compute power and much more finer grain data, I would say, with five years, the opportunity is really open. It plays a very important role in AT&T. Again, we have evolutionarily approached AI on how we infuse it.

First, we think of AI as an engine, and fuel is data. It starts with how we want to collect data and learn from it. That’s where a lot of machine learning capabilities come in. We’ve been investing in a lot of big data management capabilities over the last few years, making sure it’s in close touch with our AI engines. Our Chief Data Officer has worked very hard to establish a democratic ecosystem, especially for both data and AI capabilities. The complexity here is a step-by-step task as the amount of data increases, especially with 5G, and we get some kind of fine-grained visibility, and then we have many more intelligent controls to apply the decisions. Therefore, we are taking those steps in that evolutionary way.

Internally we have many cases of use, including how we can use AI for planning, tasks, design decisions, but also helping our customers as well as the network in real time under different conditions to provide better functionality, better customer experiences. Can. , Security risks, threat analysis, as well as how to use feedback loops to constantly optimize the network. Therefore, many cases of use throughout the life cycle.

Laurel: I’m talking about focusing on security, which is the top of mind for most officers these days. But not only security, but also AI and automation are playing a really important role for 5G functionality. What are the other ways to get into the game right now with 5G capabilities?

Raj: Again, this is a very timely and very active workspace. Let me give you a little reference on how our composition is done. When thinking about 5G, we think of it as day zero, day one, day two. Day Zero is planning activities and forecasting. I can see some natural ways where AI and machine learning can help you with your predictions. This is your first day of actually building and designing your network. You want the most efficiency. Again, feedback loops and reinforcement learning types help you do that as well as use deep learning technology to analyze maps and geospatial data, to determine where you want to bury fiber optics and where you want to place a small cell. Macro cell. So, there is a lot of building engineering where we rely heavily on AI, deep learning and neural networks.

Then there is a life cycle, which we call day two. In it, there are opportunities, things like energy saving where we are trying to optimize the energy footprint of our equipment. Again, both are corporate priorities, but also social priorities on the carbon footprint. We are looking for great opportunities for economics but also helping the planet.

Similar Posts

Leave a Reply

Your email address will not be published.