The sixth generation (6G), unlike any of the previous generations, is envisioned by 2030 to connect everything. Moreover, in addition to the new use cases 6G is expected to support, it will need to provide a superior performance over 5G. The global connectivity, large network dimensions, users heterogeneity, extremely low-power consumption, high throughput, ultrahigh reliability, efficient network operation and maintenance, and lowlatency requirements to be met by future networks inevitably necessitate the autonomy of 6G. Intelligence, facilitated mainly by the advancement of artificial intelligence (AI) techniques, is a key to achieve autonomy. In this paper, we provide a bird'seye view of 6G, its vision, progress, and objectives. Furthermore, we present some technologies that would be mainly enabling intelligent globally connected world. In addition to discussing the role of AI for future wireless communications, we, unlike any other review papers, provide our original results which give early evidence for the viability of achieving 6G networks autonomy through leveraging AI advances. Furthermore, we, very importantly, identify 6G implementation challenges and key innovative techniques that promise to solve them. This article serves as a starting point for learners to acquire more knowledge about 6G and also for researchers to promote more development to the field.

No abstract

Unmanned aerial vehicle (UAV) has recently attracted a lot of attention as a candidate to meet the 6G ubiquitous connectivity demand and boost the resiliency of terrestrial networks. Thanks to the high spectral efficiency and low latency, non-orthogonal multiple access (NOMA) is a potential access technique for future communication networks. In this paper, we propose to use the UAV as a moving base station (BS) to serve multiple users using NOMA and jointly solve for the 3D-UAV placement and resource allocation problem. Since the corresponding optimization problem is non-convex, we rely on the recent advances in artificial intelligence (AI) and propose Adapt-Sky, a deep reinforcement learning (DRL)-based framework, to efficiently solve it. To the best of our knowledge, AdaptSky is the first framework that optimizes NOMA power allocation jointly with 3D-UAV placement using both sub-6GHz and millimeter wave mmWave spectrum. Furthermore, for the first time in NOMA-UAV networks, AdaptSky integrates the dueling network (DN) architecture to the DRL technique to improve its learning capabilities. Our findings show that AdaptSky does not only exhibit a fast-adapting learning and outperform the state-ofthe-art baseline approach in data rate and fairness, but also it generalizes very well.

No abstract