The field of wireless networking is witnessing significant advancements in optimization and medium access control techniques. Recent developments focus on improving network performance, fairness, and efficiency in various scenarios, including mobile networks and heterogeneous wireless networks. Innovative approaches, such as fairness-differentiated handover schemes and fully decentralized multi-agent reinforcement learning, are being proposed to address the challenges of mobility and spectrum sharing. Additionally, data-driven optimization methods, including Bayesian optimization and transfer learning, are being applied to optimize network parameters and improve mobility management. The integration of artificial intelligence and machine learning techniques is also leading to the development of more efficient medium access control protocols, tailored to the needs of 6G wireless systems. Noteworthy papers include:
- A fairness-differentiated handover scheme that improves the performance of cell-free massive MIMO under mobility.
- A fully decentralized multi-agent reinforcement learning approach that achieves fairness in dynamic spectrum access without coordination.
- A data-driven optimization framework that uses Bayesian optimization and transfer learning to optimize 3GPP handover parameters.