Towards Semantic Communication Protocols for 6G: From Protocol Learning to Language-Oriented Approaches

TL;DR

This paper proposes a new categorization of data-driven MAC protocols for 6G, from neural reinforcement learning to language-oriented semantic protocols, highlighting their potential and challenges for future communication systems.

Contribution

It introduces a three-level framework for data-driven MAC protocols, integrating neural, symbolic, and language-oriented approaches, and analyzes their foundations and future prospects.

Findings

Categorizes data-driven MAC protocols into three levels.

Analyzes the foundational techniques and challenges of each level.

Provides insights into future research directions for 6G protocols.

Abstract

The forthcoming 6G systems are expected to address a wide range of non-stationary tasks. This poses challenges to traditional medium access control (MAC) protocols that are static and predefined. In response, data-driven MAC protocols have recently emerged, offering ability to tailor their signaling messages for specific tasks. This article presents a novel categorization of these data-driven MAC protocols into three levels: Level 1 MAC. task-oriented neural protocols constructed using multi-agent deep reinforcement learning (MADRL); Level 2 MAC. neural network-oriented symbolic protocols developed by converting Level 1 MAC outputs into explicit symbols; and Level 3 MAC. language-oriented semantic protocols harnessing large language models (LLMs) and generative models. With this categorization, we aim to explore the opportunities and challenges of each level by delving into their foundational techniques. Drawing from information theory and associated principles as well as selected case studies, this study provides insights into the trajectory of data-driven MAC protocols and sheds light on future research directions.