Artificial Intelligence-Enabled Cellular Networks: A Critical Path to Beyond-5G and 6G

Abstract

Mobile Network Operators (MNOs) are in process of overlaying their conventional macro cellular networks with shorter range cells such as outdoor pico cells. The resultant increase in network complexity creates substantial overhead in terms of operating expenses, time, and labor for their planning and management. Artificial intelligence (AI) offers the potential for MNOs to operate their networks in a more organic and cost-efficient manner. We argue that deploying AI in 5G and Beyond will require surmounting significant technical barriers in terms of robustness, performance, and complexity. We outline future research directions, identify top 5 challenges, and present a possible roadmap to realize the vision of AIenabled cellular networks for Beyond-5G and 6G.

6G Ecosystem: Current Status and Future Perspective

“…AI will be used by 6G networks at all levels starting from the PHY for channel selection, MAC for achieving power efficiency, and at the application level for context awareness [13,42,47]. Moreover, AI will spread across various network entities in 6G ecosystem, such as the sensing, edge, and cloud devices, in a distributed way to manage the small data generated locally and big data to be processed centrally to minimize the latency to the minimal level [36,[60][61]72]. In addition, the authors at [13,34,42] have discussed various ML algorithms that would benefit from the 6G networks at the various operational levels of the network.…”

“…In [147], several novel concepts such as hybrid-radio optical networks, interactive VLC, optical IoT, and their challenges were discussed. [36,60,61,118,159] Artificial Intelligence: AI for Edge, and Machine Learning (ML)…”

Deep Learning Enabled Optimization of Downlink Beamforming Under Per-Antenna Power Constraints: Algorithms and Experimental Demonstration

“…However, DL holds great promises for further improvement by considering end-toend performance optimization. The third area of interest is to overcome the complexity of wireless networks [27] which is the focus of our paper. In this aspect, DL has found many exciting applications in wireless communications such as channel decoding [31], [32], MIMO detection [33], [34], channel estimation [35], [36].…”

The Role of Artificial Intelligence Driven 5G Networks in COVID-19 Outbreak: Opportunities, Challenges, and Future Outlook

“…In addition, self-organizing networks (SON) and artificial intelligence (AI) have been implemented in 5G networks to enable the network to function in an intelligent and autonomous manner (Aliu et al, 2013;Imran et al, 2014;Klaine et al, 2017). Even though AI has only been partially included in 5G, beyond 5G (B5G) networks will experience the full implementation of AI (Letaief et al, 2019;Shafin et al, 2019). AI in 5G networks will enable intelligent and autonomous operations which is of immense importance in the current and future pandemic situations due to the drastic changes in network service demands and operational procedures resulting from movement restrictions and remote working policies put in place by government and various organizations to curtail the spread of AI will enable proactive and dynamic resource allocation that will enable the network assign resources to locations that need them on a real time demand basis unlike the static resource allocation approach that is currently implemented in existing networks (Lee and Qin, 2019).…”

“…It should however be noted that since only a few AI-based solutions can be implemented in 5G, some of the AI solutions highlighted in this work would be implemented in B5G networks. Moreover, we wish to state that since a lot of review papers have been written on the application of AI and machine learning (ML) techniques in 5G and B5G networks (Mwanje et al, 2016;Li et al, 2017;Fu et al, 2018;Letaief et al, 2019;Shafin et al, 2019;Yao et al, 2019;Wang et al, 2020c;Zhang et al, 2020), as well as an in-depth analysis on the use of ML algorithms in both 5G and B5G networks (Fadlullah et al, 2017;Klaine et al, 2017;Chen et al, 2019;Morocho-Cayamcela et al, 2019;Sun et al, 2019;Wang et al, 2019Wang et al, , 2020Xiong et al, 2019), we do not intent to repeat what they have already done in this work. Our goal is to identify some specific networking challenges that existing networks are facing due to COVID-19 pandemic and to highlight some AI/ML-driven solutions that can help 5G and B5G networks handle such problems.…”