User-Centric Association in Ultra-Dense mmWave Networks via Deep Reinforcement Learning
نویسندگان
چکیده
For ultra-dense networks, user-centric architecture is regarded as a promising candidate to offer mobile users better quality of service. One the main challenges exploring efficient scheme for user association in network. In this letter, we study dynamic (UCA) problem millimeter wave (mmWave) networks provide reliable connectivity and high achievable data rate. We consider time-varying network environments propose deep Q-network based UCA find optimal policy on historical experience. Simulation results are presented verify performance gain our proposed scheme.
منابع مشابه
Deep Reinforcement Learning for Improving Downlink mmWave Communication Performance
We propose a method to improve the DL SINR for a single cell indoor base station operating in the millimeter wave frequency range using deep reinforcement learning. In this paper, we use the deep-Q reinforcement learning models to arrive at optimal sequences of actions to improve the cellular network SINR value from a starting to a feasible target value. While deep reinforcement learning has be...
متن کاملUser-Centric Joint Transmission in Virtual-Cell-Based Ultra-Dense Networks
In ultra-dense networks (UDNs), distributed radio access points (RAPs) are configured into small virtual cells around mobile users for fair and high-throughput services. In this correspondence, we evaluate the performance of user-centric joint transmission (JT) in a UDN with a number of virtual cells. In contrast to existing cooperation schemes, which assume constant RAP transmit power, we cons...
متن کاملReinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملReinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملUser Association and Resource Allocation in Unified Non-Orthogonal Multiple Access Enabled Heterogeneous Ultra Dense Networks
Heterogeneous ultra dense networks (HUDNs) and non-orthogonal multiple access (NOMA) have been identified as two proposing techniques for the fifth generation (5G) mobile communication systems due to their great capabilities to enhance spectrum efficiency. This article investigates the application of NOMA techniques in HUDNs to support massive connectivity in 5G systems. Particularly, a unified...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Communications Letters
سال: 2021
ISSN: ['1558-2558', '1089-7798', '2373-7891']
DOI: https://doi.org/10.1109/lcomm.2021.3108013