@misc{12817, abstract = {{Sub-optimal control policies in intersection traffic signal controllers (TSC) contribute to congestion and lead to negative effects on human health and the environment. Reinforcement learning (RL) for traffic signal control is a promising approach to design better control policies and has attracted considerable research interest in recent years. However, most work done in this area used simplified simulation environments of traffic scenarios to train RL-based TSC. To deploy RL in real-world traffic systems, the gap between simplified simulation environments and real-world applications has to be closed. Therefore, we propose LemgoRL, a benchmark tool to train RL agents as TSC in a realistic simulation environment of Lemgo, a medium-sized town in Germany. In addition to the realistic simulation model, LemgoRL encompasses a traffic signal logic unit that ensures compliance with all regulatory and safety requirements. LemgoRL offers the same interface as the well-known OpenAI gym toolkit to enable easy deployment in existing research work. To demonstrate the functionality and applicability of LemgoRL, we train a state-of-the-art Deep RL algorithm on a CPU cluster utilizing a framework for distributed and parallel RL and compare its performance with other methods. Our benchmark tool drives the development of RL algorithms towards real-world applications.}}, author = {{Müller, Arthur and Rangras, Vishal and Ferfers, Tobias and Hufen, Florian and Schreckenberg, Lukas and Jasperneite, Jürgen and Schnittker, Georg and Waldmann, Michael and Friesen, Maxim and Wiering, Marco}}, booktitle = {{20th IEEE International Conference on Machine Learning and Applications (ICMLA)}}, editor = {{Wani, M. Arif and Sethi, Ishwar and Shi, Weisong and Qu, Guangzhi and Stan Raicu, Daniela and Jin, Ruoming }}, isbn = {{978-1-6654-4337-1}}, keywords = {{deep reinforcement learning, traffic signal control, intelligent transportation system, traffic simulation}}, location = {{Online}}, pages = {{507--514}}, publisher = {{IEEE}}, title = {{{Towards Real-World Deployment of Reinforcement Learning for Traffic Signal Control}}}, doi = {{10.1109/icmla52953.2021.00085}}, year = {{2022}}, } @misc{11803, abstract = {{Sub-optimal control policies in intersection traffic signal controllers (TSC) contribute to congestion and lead to negative effects on human health and the environment. Reinforcement learning (RL) for traffic signal control is a promising approach to design better control policies and has attracted considerable research interest in recent years. However, most work done in this area used simplified simulation environments of traffic scenarios to train RL-based TSC. To deploy RL in real-world traffic systems, the gap between simplified simulation environments and real-world applications has to be closed. Therefore, we propose LemgoRL, a benchmark tool to train RL agents as TSC in a realistic simulation environment of Lemgo, a medium-sized town in Germany. In addition to the realistic simulation model, LemgoRL encompasses a traffic signal logic unit that ensures compliance with all regulatory and safety requirements. LemgoRL offers the same interface as the well-known OpenAI gym toolkit to enable easy deployment in existing research work. To demonstrate the functionality and applicability of LemgoRL, we train a state-of-the-art Deep RL algorithm on a CPU cluster utilizing a framework for distributed and parallel RL and compare its performance with other methods. Our benchmark tool drives the development of RL algorithms towards real-world applications.}}, author = {{Müller, Arthur and Rangras, Vishal and Schnittker, Georg and Waldmann, Michael and Friesen, Maxim and Ferfers, Tobias and Schreckenberg, Lukas and Hufen, Florian and Jasperneite, Jürgen and Wiering, Marco}}, booktitle = {{20th IEEE International Conference on Machine Learning and Applications (ICMLA)}}, editor = {{Wani, M. Arif}}, keywords = {{deep reinforcement learning, traffic signal control, intelligent transportation system, traffic simulation}}, location = {{Pasadena, CA, USA }}, publisher = {{IEEE}}, title = {{{Towards Real-World Deployment of Reinforcement Learning for Traffic Signal Control}}}, doi = {{10.1109/ICMLA52953.2021.00085}}, year = {{2021}}, } @inproceedings{11145, abstract = {{Die vertikale und horizontale Integration von Automatisierungssystemen bilden das Funda- ment zukünftiger Automatisierungsstrukturen im Sinne von Industrie 4.0. Das bedeutet, dass die Kommunikation der Systemkomponenten nicht, wie bisher, auf bestimmte Bereiche be- schränkt, sondern bereichsübergreifend innerhalb eines Unternehmens und sogar über des- sen Grenzen hinweg stattfinden wird. Die damit einhergehende Problematik ist zum einen die fehlende Interoperabilität, und zum anderen die Angreifbarkeit dieser offenen Netzwerke durch mangelnde IT-Sicherheit. Einen wesentlichen Faktor für die Gewährleistung der In- teroperabilität stellen sogenannte Middleware-Protokolle dar. Eine Middleware liefert einen Software- und Hardware-unabhängigen Kommunikationsansatz [1]. Verschiedene Middle- ware-Lösungen verwenden dabei unterschiedliche Ansätze, um eine vertrauenswürdige Kommunikation sicherzustellen. Eine parallele Nutzung verschiedener Middleware-Lösungen ist in vielen Fällen nicht zu vermeiden, da unterschiedliche Lieferanten Komponenten mit unterschiedlichen Protokollen in Anlagen liefern werden. Die parallele Nutzung verschiede- ner Protokolle impliziert einen höheren organisatorischen Aufwand bezüglich der IT- Sicherheit. In diesem Beitrag werden die Middleware-Protokolle DDS, MQTT und OPC UA insbesondere in Bezug auf ihre IT-sicherheitsrelevanten Eigenschaften vorgestellt. Auf die- ser Grundlage und einer Analyse von IT-Sicherheitsanforderungen der Industrie, wird zu- nächst ein Ansatz für eine einheitliche Sicherheitsinfrastruktur auf Basis einer Public-Key- Infrastruktur für alle drei Protokolle konzipiert. Diese wird durch Attributzertifikate als zusätz- liche Autorisierungskomponente erweitert und evaluiert.}}, author = {{Tebbje, S. and Niemann, K.-H. and Friesen, Maxim and Karthikeyan, Gajasri and Heiss, Stefan and Jänicke, L. and Meyer, C. and Trsek, Henning}}, booktitle = {{Automation 2019 : 20. Leitkongress der Mess- und Automatisierungstechnik : autonomous systems and 5G in connected industries }}, isbn = {{978-3-18-092351-2}}, location = {{Baden-Baden}}, pages = {{505--516}}, publisher = {{VDI Verlag GmbH}}, title = {{{Entwicklung einer IT-Sicherheitsinfrastruktur für verteilte Automatisierungssysteme - Integraton verschiedener Middleware- Lösungen in eine durch Attributzertifikate erweiterte, PKI}}}, doi = {{10.51202/9783181023518-505}}, volume = {{2351}}, year = {{2019}}, } @inproceedings{4841, author = {{Elattar, Mohammad and Friesen, Maxim and Henneke, Dominik and Jasperneite, Jürgen}}, location = {{Imperia, Italy}}, title = {{{Reliability-oriented Multipath Communication for Internet-based Cyber-physical Systems}}}, year = {{2018}}, } @inproceedings{4842, author = {{Lang, Dorota and Friesen, Maxim and Ehrlich, Marco and Wisniewski, Lukasz and Jasperneite, Jürgen}}, location = {{Porto, Portugal}}, title = {{{Pursuing the Vision of Industrie 4.0: Secure Plug and Produce by Means of the Asset Administration Shell and Blockchain Technology}}}, year = {{2018}}, }