FORLORN: A Framework for Comparing Offline Methods and Reinforcement Learning for Optimization of RAN Parameters
This work addresses the need for efficient network control in mobile systems, but it is incremental as it builds on existing RL and optimization techniques for a specific domain.
The paper tackles the problem of optimizing Radio Access Network (RAN) parameters in mobile networks by introducing a framework to benchmark Reinforcement Learning (RL) agents against offline methods, showing that RL can match offline optimization in static scenarios and adapt in dynamic ones to improve user experience.
The growing complexity and capacity demands for mobile networks necessitate innovative techniques for optimizing resource usage. Meanwhile, recent breakthroughs have brought Reinforcement Learning (RL) into the domain of continuous control of real-world systems. As a step towards RL-based network control, this paper introduces a new framework for benchmarking the performance of an RL agent in network environments simulated with ns-3. Within this framework, we demonstrate that an RL agent without domain-specific knowledge can learn how to efficiently adjust Radio Access Network (RAN) parameters to match offline optimization in static scenarios, while also adapting on the fly in dynamic scenarios, in order to improve the overall user experience. Our proposed framework may serve as a foundation for further work in developing workflows for designing RL-based RAN control algorithms.