Artificial Intelligence and Machine Learning in 6G

The demand for connectivity in our society is ever on the rise. Internet traffic has been growing at an annual rate of about 26%, from 122 exabytes per month in 2017 to 396 exabytes per month by 2022. As 5G deployments are rolling out publicly worldwide, the industry and academia are already gearing up for the next leap forward. With the scarcity of available communication spectrum in the wireless domain, the most efficient use of resources is paramount to achieving connectivity, latency, and reliability targets. The future networks present us with a unique set of challenges characterized by harsh propagation conditions in the newly opened-up spectrum coupled with increasing demands on all fronts including user connection density, peak data rates, ubiquitous network availability, and imperceptible latency. At the same time, it is imperative to ensure backward compatibility and harmonious co-existence through techniques such as spectrum sharing.