Deep Recurrent Reinforcement Learning for Partially Observable User Association in a Vertical Heterogenous Network

To ensure ubiquitous connectivity and meet increasing users’ demands in next-generation wireless networks, we investigate user association in a three-layer network consisting of a terrestrial base station (TBS), a high-altitude platform station (HAPS), and a satellite. To maintain scalability and reduce frequent channel state information (CSI) exchanges across layers, we assume only the CSI of previously associated links is available. To address our partially observable user association problem, we propose the action-specific deep recurrent Q-network (ADRQN) method. This involves incorporating a long short-term memory (LSTM) layer alongside fully connected layers, utilizing both observation and action vectors in the policy network. We compare our proposed ADRQN method to the exhaustive search, deep Q-network, deep recurrent Q-network, and convex optimization methods and demonstrate the necessity of using the action vector. Finally, we consider the absence of perfect CSI and show that our ADRQN agent outperforms the convex optimization method in this scenario.