Predictive Handover Management in 6G and Beyond: A Deep and Transfer Learning Approach for Optimizing Network Performance
A deep and transfer learning-based algorithm that accurately predicts the optimal target cell for handover in 6G and beyond networks, enabling dynamic optimization of handover decisions and seamless integration of new network elements like UAV base stations.
Optimizing Wireless Resource Allocation in Hybrid Semantic and Bit Communication Networks
The core message of this paper is to propose an optimal resource management strategy for user association, mode selection, and bandwidth allocation in a hybrid semantic/bit communication network to maximize the overall message throughput, while considering the unique characteristics of semantic communication and practical system constraints.
Network-Assisted Full-Duplex Cell-Free mmWave Networks: Hybrid MIMO Processing and Multi-Agent DRL-Based Power Allocation
This paper proposes a hybrid MIMO processing framework to eliminate cross-link interference in network-assisted full-duplex (NAFD) cell-free millimeter-wave (mmWave) networks, and develops a collaborative multi-agent deep reinforcement learning (MADRL) algorithm to optimize the bidirectional power allocation.
Safe Deep Reinforcement Learning for Energy Efficient Federated Learning in Wireless Communication Networks
The author proposes a Safe Deep Reinforcement Learning solution to minimize energy consumption in Federated Learning processes, ensuring model performance. By introducing penalty functions and synchronization methods, the approach aims to reduce overall energy consumption and communication overhead.
© 2024 by Linnk AI