With advances in end-user devices and other technologies, the demand for immersive experiences that seamlessly blend the digital and physical worlds will be significant by the end of the decade. To support these, 6G networks will need to deliver unprecedented capacity, low latency, energy efficiency, and cognitive capabilities to manage vast radio resources. The potential of artificial intelligence (AI) to enhance the physical layer and reach these goals has been demonstrated in previous works.
In this white paper, we explore the frontiers of machine learning (ML) to improve features beyond the physical layer (PHY) and further enhance the native AI air interface (AI-AI) envisioned for 6G. We survey recent research on AI-driven functions such as resource allocation, random access, adaptive modulation and coding (AMC), power control, protocol learning, channel state information (CSI) reporting, hybrid automatic repeat request (HARQ), and multi-RAT spectrum sharing (MRSS). We contend that while the fundamental duties of the 6G wireless medium access control (MAC) will remain consistent with prior generations, the integration of ML methodologies will instigate transformative changes across multiple MAC domains. This infusion of ML-driven strategies will open new avenues for development and maintenance and undergird future redesign efforts.
