Open Access

REVIEW

A Comprehensive Survey on AI-Assisted Multiple Access Enablers for 6G and beyond Wireless Networks

Kinzah Noor¹, Agbotiname Lucky Imoize^2,*, Michael Adedosu Adelabu³, Cheng-Chi Lee^4,5,*

1 Office of Research Innovation and Commercialization, University of Management and Technology, Lahore, 54770, Pakistan
2 Department of Electrical and Electronics Engineering, Faculty of Engineering, University of Lagos, Akoka, Lagos, 100213, Nigeria
3 Electrical and Electronic Engineering Department, School of Science and Technology, Pan-Atlantic University, Ibeju-Lekki, Lagos, 105101, Nigeria
4 Department of Library and Information Science, Fu Jen Catholic University, New Taipei City, 242062, Taiwan
5 Department of Computer Science and Information Engineering, Asia University, Taichung City, 413305, Taiwan

* Corresponding Authors: Agbotiname Lucky Imoize. Email: ; Cheng-Chi Lee. Email:

(This article belongs to the Special Issue: Artificial Intelligence for 6G Wireless Networks)

Computer Modeling in Engineering & Sciences 2025, 145(2), 1575-1664. https://doi.org/10.32604/cmes.2025.073200

Received 12 September 2025; Accepted 24 October 2025; Issue published 26 November 2025

Abstract

The envisioned 6G wireless networks demand advanced Multiple Access (MA) schemes capable of supporting ultra-low latency, massive connectivity, high spectral efficiency, and energy efficiency (EE), especially as the current 5G networks have not achieved the promised 5G goals, including the projected 2000 times EE improvement over the legacy 4G Long Term Evolution (LTE) networks. This paper provides a comprehensive survey of Artificial Intelligence (AI)-enabled MA techniques, emphasizing their roles in Spectrum Sensing (SS), Dynamic Resource Allocation (DRA), user scheduling, interference mitigation, and protocol adaptation. In particular, we systematically analyze the progression of traditional and modern MA schemes, from Orthogonal Multiple Access (OMA)-based approaches like Time Division Multiple Access (TDMA) and Frequency Division Multiple Access (FDMA) to advanced Non-Orthogonal Multiple Access (NOMA) methods, including power domain-NOMA, Sparse Code Multiple Access (SCMA), and Rate Splitting Multiple Access (RSMA). The study further categorizes AI techniques—such as Machine Learning (ML), Deep Learning (DL), Reinforcement Learning (RL), Federated Learning (FL), and Explainable AI (XAI)—and maps them to practical challenges in Dynamic Spectrum Management (DSM), protocol optimization, and real-time distributed decision-making. Optimization strategies, including metaheuristics and multi-agent learning frameworks, are reviewed to illustrate the potential of AI in enhancing energy efficiency, system responsiveness, and cross-layer RA. Additionally, the review addresses security, privacy, and trust concerns, highlighting solutions like privacy-preserving ML, FL, and XAI in 6G and beyond. By identifying research gaps, challenges, and future directions, this work offers a structured resource for researchers and practitioners aiming to integrate AI into 6G MA systems for intelligent, scalable, and secure wireless communications.

---

Graphic Abstract

---

Keywords

---