Our paper titled "Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning" has been accepted to the 24th International Symposium on Modeling and Optimization in Mobile, Ad hoc, and Wireless Networks (WiOpt), to be held in Columbus, OH during June 3-6, 2026. This work was done by our PhD student Marvin Illian, in collaboration with Huawei Research in Germany and UFF in Brazil.
The paper tackles the cell selection problem in cellular networks, which aims to pick the most suitable cell for each user equipment (UE) during the idle mode. Cell selection is typically done with manual efforts where network experts set parameters based on their experience, which is tedious and often results in suboptimal performance. We propose to automate this process by incorporating machine learning. Specifically, we employ reinforcement learning to let the network figure out automatically the best configurations according to the real-time network conditions. We show that such a principled approach can significantly boost the network performance.
Here is the abstract of the paper:
The widespread deployment of 5G networks, together with the coexistence of 4G/LTE networks, provides mobile devices a diverse set of candidate cells to connect to. However, associating mobile devices to cells to maximize overall network performance, a.k.a. cell (re)selection, remains a key challenge for mobile operators. Today, cell (re)selection parameters are typically configured manually based on operator experience and rarely adapted to dynamic network conditions. In this work, we ask: Can an agent automatically learn and adapt cell (re)selection parameters to consistently improve network performance? We present a reinforcement learning (RL)-based framework called CellPilot that adaptively tunes cell (re)selection parameters by learning spatiotemporal patterns of mobile network dynamics. Our study with real-world data demonstrates that even a lightweight RL agent can outperform conventional heuristic reconfigurations by up to 147%, while generalizing effectively across different network scenarios.
Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning
Marvin Illian (Paderborn University), Ramin Khalili (Hauwei Research Munich), Antonio A. de A. Rocha (Fluminense Federal University, Brazil), Lin Wang (Paderborn University)
