Multi-agent Reinforcement Learning with Graph Q-Networks for Antenna Tuning
This work addresses the problem of efficient antenna tuning for mobile network operators, but it is incremental as it builds on existing multi-agent reinforcement learning methods with specific architectural enhancements.
The paper tackles the challenge of optimizing antenna parameters in large-scale mobile networks by proposing a new multi-agent reinforcement learning algorithm that uses a value decomposition approach and graph neural networks to enable global optimization. The algorithm is empirically demonstrated on antenna tilt tuning and joint tilt and power control problems in a simulated environment, showing performance improvements.
Future generations of mobile networks are expected to contain more and more antennas with growing complexity and more parameters. Optimizing these parameters is necessary for ensuring the good performance of the network. The scale of mobile networks makes it challenging to optimize antenna parameters using manual intervention or hand-engineered strategies. Reinforcement learning is a promising technique to address this challenge but existing methods often use local optimizations to scale to large network deployments. We propose a new multi-agent reinforcement learning algorithm to optimize mobile network configurations globally. By using a value decomposition approach, our algorithm can be trained from a global reward function instead of relying on an ad-hoc decomposition of the network performance across the different cells. The algorithm uses a graph neural network architecture which generalizes to different network topologies and learns coordination behaviors. We empirically demonstrate the performance of the algorithm on an antenna tilt tuning problem and a joint tilt and power control problem in a simulated environment.