@unpublished{63530,
  abstract     = {{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 167%, while generalizing effectively across different network scenarios. These results indicate that data-driven approaches can significantly improve cell (re)selection configurations and enhance mobile network performance.}},
  author       = {{Illian, Marvin and Khalili, Ramin and Rocha, Antonio A. de A. and Wang, Lin}},
  booktitle    = {{arXiv:2601.04083}},
  title        = {{{Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning}}},
  year         = {{2026}},
}

@inproceedings{65013,
  author       = {{Illian, Marvin and Khalili, Ramin and A. de A. Rocha, Antonio and Wang, Lin}},
  booktitle    = {{2026 24th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)}},
  publisher    = {{IFIP}},
  title        = {{{Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning}}},
  year         = {{2026}},
}

@inproceedings{61256,
  author       = {{Illian, Marvin and Luchterhandt, Björn and Wang, Lin}},
  booktitle    = {{Proceedings of the 20th Workshop on Mobility in the Evolving Internet Architecture (MobiArch)}},
  location     = {{Hong Kong, China}},
  title        = {{{Band Switching for Mobile Energy Optimization in 5G Networks and Beyond}}},
  doi          = {{10.1145/3737897.3767294}},
  year         = {{2025}},
}

@inproceedings{56671,
  author       = {{Illian, Marvin and Zinda, Christopher and Schlangenotto, Darius}},
  booktitle    = {{2024 IEEE International Conference on Industrial Technology (ICIT)}},
  publisher    = {{IEEE}},
  title        = {{{Data Store Architectures: Balancing Functionality and Performance}}},
  doi          = {{10.1109/icit58233.2024.10540811}},
  year         = {{2024}},
}

@inproceedings{51262,
  abstract     = {{The manufacturing domain is exposed to a continuous change of the requirements towards the IT infrastructure and the flexibility in Industry 4.0. In order to achieve a highly reliable production system, predictive maintenance and additive sensing have been implemented and will be complemented by further applications such as Augmented Reality. As the applications may be required ad-hoc at any time, the dynamic resource utilization of networking and computational resources needs to be managed. In the long-term, the planning of the infrastructure affects the available resources and thus the efficiency and reliability of the short-term resource management. This paper suggests an architecture that combines short- and long-term aspects of the resource utilization and previews how the infrastructure and opportunity costs can be optimized by the joint approach.}},
  author       = {{Neumann, Arne and Illian, Marvin and Hardes, Tobias and Martenvormfelde, Lukas and Wisniewski, Lukasz and Jasperneite, Jürgen}},
  booktitle    = {{18th IEEE International Workshop on Factory Communication Systems (WFCS)}},
  location     = {{Virtual}},
  publisher    = {{IEEE}},
  title        = {{{An Architecture Concept for Short- and Long-term Resource Planning in the Industry 4.0 Environment}}},
  doi          = {{10.1109/WFCS53837.2022.9779161}},
  year         = {{2022}},
}

@inproceedings{16726,
  author       = {{Razzaghi Kouchaksaraei, Hadi and Shivarpatna Venkatesh, Ashwin Prasad and Churi, Amey and Illian, Marvin and Karl, Holger}},
  booktitle    = {{European Conference on Networks and Communications (EUCNC 2020)}},
  title        = {{{Dynamic Provisioning of Network Services on Heterogeneous Resources}}},
  year         = {{2020}},
}

@inproceedings{61260,
  author       = {{Illian, Marvin and Althoff, Simon and Karl, Holger}},
  booktitle    = {{2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)}},
  publisher    = {{IEEE}},
  title        = {{{A Process to Develop Lean Big-Data Platform Architectures for Industrial Manufacturing Contexts}}},
  doi          = {{10.1109/etfa46521.2020.9212006}},
  year         = {{2020}},
}

@inproceedings{30859,
  author       = {{Ghosh Chowdhury, Arnab and Illian, Marvin and Wisniewski, Lukasz and Jasperneite, Jurgen}},
  booktitle    = {{2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)}},
  publisher    = {{IEEE}},
  title        = {{{An Approach for Data Pipeline with Distributed Query Engine for Industrial Applications}}},
  doi          = {{10.1109/etfa46521.2020.9212050}},
  year         = {{2020}},
}

@inproceedings{24185,
  abstract     = {{In this poster, we present the first experimental results of our OFDM-based Vehicular VLC (V-VLC) prototype. Our Bit Error Rate (BER) measurements show that for lower Modulation and Coding Schemes (MCS), the performance of our hardware-setup roughly behaves the same as it does in simulation for AWGN channel. However, for higher order MCS with high PAPR, the BER performance gets degraded due to non-linear behavior of LEDs, and deviates further from AWGN performance as the MCS order is increased. The obtained results suggest that unlike RF-Communications, where the focus is usually towards linearity of the amplifiers, for V-VLC, linearity within the whole system is required to achieve optimal performance.}},
  author       = {{Koepe, Jörn and Kaltschmidt, Christian and Illian, Marvin and Puknat, Robert and Kneuper, Pascal and Wittemeier, Steffen and Memedi, Agon and Tebruegge, Claas and Amjad, Muhammad Sohaib and Kruse, Stephan and Kress, Christian and Scheytt, Christoph and Dressler, Falko}},
  booktitle    = {{2018 IEEE Vehicular Networking Conference (VNC)}},
  publisher    = {{IEEE}},
  title        = {{{First Performance Insights on Our Noval OFDM-based Vehicular VLC Prototype}}},
  doi          = {{10.1109/VNC.2018.8628322}},
  year         = {{2018}},
}

@inproceedings{30858,
  author       = {{Dräxler, Sevil and Peuster, Manuel and Illian, Marvin and Karl, Holger}},
  booktitle    = {{2018 4th IEEE Conference on Network Softwarization and Workshops (NetSoft)}},
  publisher    = {{IEEE}},
  title        = {{{Generating Resource and Performance Models for Service Function Chains: The Video Streaming Case}}},
  doi          = {{10.1109/netsoft.2018.8460029}},
  year         = {{2018}},
}

@proceedings{61268,
  editor       = {{Dräxler, Sevil and Peuster, Manuel and Illian, Marvin and Karl, Holger}},
  location     = {{Darmstadt, Germany}},
  title        = {{{Towards Predicting Resource Demands and Performance of Distributed Cloud Services}}},
  year         = {{2018}},
}