Convergence of Manufacturing and Networking in Future Factories (2312.08708v1)
Abstract: The roll out of 5G has been mainly characterized by its distinct support for vertical industries, especially manufacturing. Leveraging synergies among these two worlds, namely production facilities and network systems, is a fundamental aspect to enable flexibility and economic viability in future factories. This work highlights the potential for intelligent networking and advanced machine learning-based solutions in 5G-and-beyond systems in the context of Industry 4.0 and flexible manufacturing. The intersection thereof allows to create versatile machines and dynamic communication networks that can adapt to changes in the manufacturing process, factory layout and communication environment, supporting real-time interaction between humans, machines, and systems. We present a vision and corresponding framework by introducing the network-aware and production-aware principles, outlining results achieved in this context and summarizing them into three key use cases. Finally, we discuss a selection of remaining open challenges in private networks as well as give an outlook on future 6G research directions.
- International Electrotechnical Commission (IEC), “Factory of the future,” 2015, [Accessed: 28-Apr-2023]. [Online]. Available: https://www.iec.ch/basecamp/factory-future
- 5G Alliance for Connected Industries and Automation (5G-ACIA), “Key 5G use cases and requirements,” 2020, [Accessed: 28-Apr-2023]. [Online]. Available: https://5g-acia.org/resources/whitepapers-deliverables/
- KICK Project. [Accessed: 28-Apr-2023]. [Online]. Available: https://kick-project.de/en/
- N. Marchenko, J. Ali-Tolppa, O. D. R. Cantor, P. Agostini, and R. Pries, “5G QoS prediction and application offloading,” in European Wireless, 2022.
- Q. Zhou, W. Jiang, D. Wang, and H. D. Schotten, “Performance evaluation over DL-based channel prediction algorithm on realistic CSI,” in IEEE Vehicular Technology Conference (VTC) Fall, 2022.
- M. Zambianco, A. Lieto, I. Malanchini, and G. Verticale, “A learning approach for production-aware 5G slicing in private industrial networks,” in IEEE International Conference on Communications (ICC), 2022, pp. 1542–1548.
- P. Agostini, E. Tohidi, M. Kasparick, and S. Stańczak, “Learning constrained network slicing policies for industrial applications,” in IEEE International Conference on Communications Workshops (ICC Workshops), 2022.
- T. Hu, Q. Liao, Q. Liu, and G. Carle, “Network slicing via transfer learning aided distributed deep reinforcement learning,” in IEEE Global Communications Conference (GLOBECOM), 2022.
- AIMFREE Project, [Accessed: 28-Apr-2023]. [Online]. Available: http://aimfree.wzl.rwth-aachen.de/en/default.html
- J. Calle-Sánchez, M. Molina-Garcia, J. I. Alonso, and A. F. Durán, “Suitability of indoor propagation models for fingerprint based positioning in femtocell networks,” in IEEE European Microwave Conference, 2012.
- R. Levie, C. Yapar, G. Kutyniok, and G. Caire, “RadioUNet: Fast radio map estimation with convolutional neural networks,” IEEE Transactions on Wireless Communications, vol. 20, no. 6, pp. 4001–4015, 2021.
- A. Martínez Alba and N. Michailow, “Uncertainty-boosted radiomap-based indoor positioning with RSSI fingerprints,” in IEEE Global Communications Conference Workshops (GLOBECOM Workshops), 2022.
- A. Lieto, S. Strzyz, P. Agostini, and T. Hu, “A joint industrial-network simulator for leveraging automation in 5G private networks,” in European Wireless, 2022.
- A. Lieto, Q. Liao, and C. Bauer, “A generative approach for production-aware industrial network traffic modeling,” in IEEE Global Communications Conference Workshops (GLOBECOM Workshops), 2022.
- Q. Liao, N. Marchenko, T. Hu, P. Kulics, and L. Ewe, “HARU: Haptic augmented reality-assisted user-centric industrial network planning,” in IEEE Global Communications Conference Workshops (GLOBECOM Workshops), 2022.