User-Centric Association in Ultra-Dense mmWave Networks via Deep Reinforcement Learning

For ultra-dense networks, user-centric architecture is regarded as a promising candidate to offer mobile users better quality of service. One of the main challenges of user-centric architecture is exploring efficient scheme for user association in the ultra-dense network. In this letter, we study dynamic user-centric association (UCA) problem for ultra-dense millimeter wave (mmWave) networks to provide reliable connectivity and high achievable data rate. We consider time-varying network environments and propose a deep Q-network based UCA scheme to find the optimal association policy based on the historical experience. Simulation results are presented to verify the performance gain of our proposed scheme.

Automated summary

User-centric architecture is considered a promising option for providing better quality of service in ultra-dense networks, with one main challenge being to explore efficient user association schemes. This letter investigates the dynamic user-centric association problem for ultra-dense millimeter wave networks and proposes a deep Q-network based scheme to find the optimal association policy, demonstrating performance gain through simulation results.