A Study on Multi-Antenna and Pertinent Technologies with AI/ML Approaches for B5G/6G Networks

Abstract

The quantum leap in mobile data traffic and high density of wireless electronic devices, coupled with the advancements in industrial radio monitoring and autonomous systems, have created great challenges for smooth wireless network operations. The fifth-generation and beyond (B5G) (also being referred to as sixth-generation (6G)) wireless communication technologies, due to their compatibility with the previous generations, are expected to overcome these unparalleled challenges. Accompanied by traditional and new techniques, the massive multiple input multiple output (mMIMO) approach is one of the evolving technologies for B5G/6G systems used to control the ever-increasing user stipulations and the emergence of new cases efficiently. However, the major challenges in deploying mMIMO systems are their high computational intricacy and high computing time latencies, as well as difficulties in fully exploiting the multi-antenna multi-frequency channels. Therefore, to optimize the current and B5G/6G wireless network elements proficiently, the use of the mMIMO approach in a HetNet structure with artificial intelligence (AI) techniques, e.g., machine learning (ML), distributed learning, federated learning, deep learning, and neural networks, has been considered as the prospective efficient solution. This work analyzes the observed problems and their AI/ML-enabled mitigation techniques in different mMIMO deployment scenarios for 5G/B5G networks. To provide a complete insight into the mMIMO systems with emerging antenna and propagation precoding techniques, we address and identify various relevant topics in each section that may help to make the future wireless systems robust. Overall, this work is designed to guide all B5G/6G stakeholders, including researchers and operators, aiming to understand the functional behavior and associated techniques to make such systems more agile for future communication purposes.

Toward Efficient 6G IoT Networks: A Perspective on Resource Optimization Strategies, Challenges, and Future Directions

“…The 6G network's resource optimization is summed up by automated network management deployment and advanced AI techniques, particularly the Explainable AI (XAI) approach [22,23]. They discussed the potential of XAI-powered 6G architecture.…”

A Survey of Resource Management in D2D Communication for B5G Networks

“…Besides, Integrating AI and Machine Learning (ML) is a crucial and promising technique for the B5G networks. AI and ML can aid network operators to overcome the resource management challenges of D2D communication by improving the QoS [198]. AI and ML enable the network operators to estimate the resource utilization, analyze the network traffic, and optimize the network parameters.…”

Security Concepts in Emerging 6G Communication: Threats, Countermeasures, Authentication Techniques and Research Directions

“…The solution executes a probabilistic secrecy analysis of mixed RF and optical communication through secret antenna selection to avoid eavesdroppers. However, the proposed scheme has a scope limited to eavesdropping attack MIMO technology, and, currently, the increased complexity due to AI-based implementations in MIMO has increased the vulnerabilities and security implementation issues [85]. The authors in [86] proposed a Bloom filter-based private set intersection mechanism to achieve conditional privacy preservation.…”