ML-Based Radio Resource Management in 5G and Beyond Networks: A Survey

In this survey, a comprehensive study is provided, regarding the use of machine learning (ML) algorithms for effective resource management in fifth-generation and beyond (5G/B5G) wireless cellular networks. The ever-increasing user requirements, their diverse nature terms performance metrics various novel technologies, such as millimeter wave transmission, massive multiple-input-multiple-output configurations non-orthogonal multiple access, render multi-constraint radio (RRM) problem. context, ML mobile edge computing (MEC) constitute promising framework to provide improved quality service (QoS) end users, since they can relax RMM-associated computational burden. our work, state-of-the-art analysis ML-based RRM algorithms, categorized type potential applications well MEC implementations,is presented, define best-performing solutions sub-problems. To demonstrate capabilities efficiency RRM, we apply compare different approaches throughput prediction, an indicative task. We investigate problem, either classification or regression one, using corresponding each occasion. Finally, open issues, challenges limitations concerning AI/ML 5G B5G networks, are discussed detail.