Machine learning and data driven approaches have recently received much attention as a key enabler for future 5G and beyond wireless networks. Yet, the evolution towards learning-based data driven networks is still in its infancy, and much of the realization of the promised benefits requires thorough research and development. Fundamental questions remain as to where and how ML can really complement the well-established, well-tested communication systems designed over the last 4 decades. Moreover, adaptation of machine learning methods is likely needed to realize their full potential in the wireless context. This is particularly challenging for the lower layers of the protocol stack, where the constraints, problem formulation, and even the objectives may fundamentally differ from the typical scenarios to which machine learning has been successfully applied in recent years. In addition, a deep understanding of the fundamental performance limits is also essential in order to establish quality-of-service guarantees that are common in communication system design. All such research challenges lie at the core of this special issue. In order to address these problems, the issue solicits original research papers that address the following non-exhaustive list of topics:
Neural networks for wireless communication links (incl. autoencoders, generative adversarial networks etc)
Data-driven optimization of wireless networks
Distributed machine learning for wireless communications
Deep reinforcement learning for wireless communications
Machine learning based testbeds and experimental evaluations
Machine learning for network orchestration
Machine learning for video caching, delivery and streaming over wireless networks
Machine learning for resource allocation in wireless networks