Building tomorrow’s telecommunications network today

Building tomorrow’s telecommunications network today

So it’s an important part of the mission and we’re thinking about network design and architecture. It really isn’t for the next three years either. We are thinking about the next 20 and 50 years. Investments in the network take a long time, and we want to make these investments with the economy in mind, but also to a large extent by ensuring the most reliable network offer.

Laurel: You mentioned artificial intelligence and machine learning in the previous answer. In what ways does AT&T use artificial intelligence and ML or is it considering the use of artificial intelligence?

Paradise: Great question and very timely. As a company, we have researchers working on AI for many years. With the advent of much more computing power and much finer data, the opportunity has really opened up in the last, I would say, five years. She plays a very important role in AT&T. Again, we approached AI in an evolutionary way about how we enter 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. Here come the many possibilities of machine learning. We’ve invested in a lot of big data management capabilities over the past few years, ensuring they’re well exposed to our AI engines. Our Chief Data Officer in particular has worked very hard to establish a democratized ecosystem for both data and AI capabilities. Here there is a function of steps in complexity as the amount of data increases, especially with 5G, and we get some finer visibility and we have much smarter controls for implementing decisions. So we are taking those steps in that evolutionary way.

Internally we have many use cases, including how we can use AI for planning, functions, AI for design decisions, but also in real time to help our customers as well as the network, under different scenarios to provide better efficiency, better user experience, security discovery threats, threat analytics, and how to use feedback loops for continuous network optimization. So, many cases of use during the life cycle.

Laurel: I’m talking about that focus on security, which is at the forefront today for most executives. But not only security, artificial intelligence and automation also play an important role for 5G functionality. In what other ways is this now possible with 5G capabilities?

Paradise: Again, this is a very timely and very active area of ​​work. Let me give you some context on how we are structured. When we think of 5G, we think of it as day zero, day one, day two. Zero day are planning and forecasting activities. I see some natural ways in which AI and machine learning can help you predict. There is your first day, which is actually building and designing your network. You want to achieve maximum efficiency. Again, feedback and enhance learning help you, as well as using deep learning technology to analyze maps and geospatial data, determine where you want to have buried optical fibers and where you want to place a small cell relative to a macro cell. So there is a lot of civil engineering in which we rely heavily on AI, deep learning and neural networks.

Then there is the life cycle, which we call day two. There are possibilities in that, things like energy saving where we try to optimize the energy footprint of our equipment. Again, both a corporate priority and a social priority in terms of carbon footprint. We see great opportunities for the economy, but also for helping the planet.



Source link

Leave a Reply