User Association and Load Balancing for Massive MIMO through Deep Learning
It addresses load balancing in wireless networks for improved efficiency, but it is incremental as it applies an existing deep learning method to a known problem.
This work tackles user cell association for sum-rate maximization in Massive MIMO networks by using deep learning to approach the optimal rule with reduced computational complexity, enabling real-time updates based on user mobility patterns, and numerical results show it matches the performance of traditional optimization methods.
This work investigates the use of deep learning to perform user cell association for sum-rate maximization in Massive MIMO networks. It is shown how a deep neural network can be trained to approach the optimal association rule with a much more limited computational complexity, thus enabling to update the association rule in real-time, on the basis of the mobility patterns of users. In particular, the proposed neural network design requires as input only the users' geographical positions. Numerical results show that it guarantees the same performance of traditional optimization-oriented methods.