TY - CONF AB - Management and orchestration~(MANO) systems are the key components of future large-scale NFV environments. They will manage resources of hundreds or even thousands of NFV infrastructure installations, so called points of presence~(PoP). Such scenarios need to be automatically tested during the development phase of a MANO system. This task becomes very challenging because large-scale NFV testbeds are hard to maintain, too expensive, or simply not available. In this paper, we present a multi-PoP NFV infrastructure emulation platform that enables automated, large-scale testing of MANO stacks. We show that our platform can easily emulate hundreds of PoPs on a single physical machine and reduces the setup time of a test PoP by a factor of 232x compared to a DevStack-based test PoP installation. Further, we present a case study in which we test ETSI's Open Source MANO~(OSM) against our proposed system to gain insights about OSM's behaviour in large-scale NFV deployments. AU - Peuster, Manuel AU - Marchetti, Michael AU - Garcia de Blas, Gerado AU - Karl, Holger ID - 3347 T2 - European Conference on Networks and Communications (EuCNC) TI - Emulation-based Smoke Testing of NFV Orchestrators in Large Multi-PoP Environments ER - TY - JOUR AB - Automated machine learning (AutoML) seeks to automatically select, compose, and parametrize machine learning algorithms, so as to achieve optimal performance on a given task (dataset). Although current approaches to AutoML have already produced impressive results, the field is still far from mature, and new techniques are still being developed. In this paper, we present ML-Plan, a new approach to AutoML based on hierarchical planning. To highlight the potential of this approach, we compare ML-Plan to the state-of-the-art frameworks Auto-WEKA, auto-sklearn, and TPOT. In an extensive series of experiments, we show that ML-Plan is highly competitive and often outperforms existing approaches. AU - Mohr, Felix AU - Wever, Marcel Dominik AU - Hüllermeier, Eyke ID - 3510 JF - Machine Learning KW - AutoML KW - Hierarchical Planning KW - HTN planning KW - ML-Plan SN - 0885-6125 TI - ML-Plan: Automated Machine Learning via Hierarchical Planning ER - TY - CONF AU - Mohr, Felix AU - Wever, Marcel Dominik AU - Hüllermeier, Eyke ID - 3552 T2 - Proceedings of the Symposium on Intelligent Data Analysis TI - Reduction Stumps for Multi-Class Classification ER - TY - JOUR AB - Oblique propagation of semi-guided waves across slab waveguide structures with bent corners is investigated. A critical angle can be defined beyond which all radiation losses are suppressed. Additionally an increase of the curvature radius of the bends also leads to low-loss configurations for incidence angles below that critical angle. A combination of two bent corner systems represents a step-like structure, behaving like a Fabry-Perot interferometer, with two partial reflectors separated by the vertical height between the horizontal slabs. We numerically analyse typical high-index-contrast Si/SiO2 structures for their reflectance and transmittance properties. When increasing the curvature radius the resonant effect becomes less relevant such that full transmittance is reached with less critical conditions on the vertical distance or the incidence angle. For practical interest 3-D problems are considered, where the structures are excited by the fundamental mode of a wide, shallow rib waveguide. High transmittance levels can be observed also for these 3-D configurations depending on the width of the rib. AU - Ebers, Lena AU - Hammer, Manfred AU - Förstner, Jens ID - 3740 IS - 14 JF - Optics Express KW - tet_topic_waveguide TI - Oblique incidence of semi-guided planar waves on slab waveguide steps: effects of rounded edges VL - 26 ER - TY - CONF AB - In automated machine learning (AutoML), the process of engineering machine learning applications with respect to a specific problem is (partially) automated. Various AutoML tools have already been introduced to provide out-of-the-box machine learning functionality. More specifically, by selecting machine learning algorithms and optimizing their hyperparameters, these tools produce a machine learning pipeline tailored to the problem at hand. Except for TPOT, all of these tools restrict the maximum number of processing steps of such a pipeline. However, as TPOT follows an evolutionary approach, it suffers from performance issues when dealing with larger datasets. In this paper, we present an alternative approach leveraging a hierarchical planning to configure machine learning pipelines that are unlimited in length. We evaluate our approach and find its performance to be competitive with other AutoML tools, including TPOT. AU - Wever, Marcel Dominik AU - Mohr, Felix AU - Hüllermeier, Eyke ID - 3852 KW - automated machine learning KW - complex pipelines KW - hierarchical planning T2 - ICML 2018 AutoML Workshop TI - ML-Plan for Unlimited-Length Machine Learning Pipelines ER - TY - JOUR AB - To adapt to continuously changing workloads in networks, components of the running network services may need to be replicated (scaling the network service) and allocated to physical resources (placement) dynamically, also necessitating dynamic re-routing of flows between service components. In this paper, we propose JASPER, a fully automated approach to jointly optimizing scaling, placement, and routing for complex network services, consisting of multiple (virtualized) components. JASPER handles multiple network services that share the same substrate network; services can be dynamically added or removed and dynamic workload changes are handled. Our approach lets service designers specify their services on a high level of abstraction using service templates. JASPER automatically makes scaling, placement and routing decisions, enabling quick reaction to changes. We formalize the problem, analyze its complexity, and develop two algorithms to solve it. Extensive empirical results show the applicability and effectiveness of the proposed approach. AU - Dräxler, Sevil AU - Karl, Holger AU - Mann, Zoltan Adam ID - 3152 JF - IEEE Transactions on Network and Service Management TI - JASPER: Joint Optimization of Scaling, Placement, and Routing of Virtual Network Services ER - TY - CONF AB - In multinomial classification, reduction techniques are commonly used to decompose the original learning problem into several simpler problems. For example, by recursively bisecting the original set of classes, so-called nested dichotomies define a set of binary classification problems that are organized in the structure of a binary tree. In contrast to the existing one-shot heuristics for constructing nested dichotomies and motivated by recent work on algorithm configuration, we propose a genetic algorithm for optimizing the structure of such dichotomies. A key component of this approach is the proposed genetic representation that facilitates the application of standard genetic operators, while still supporting the exchange of partial solutions under recombination. We evaluate the approach in an extensive experimental study, showing that it yields classifiers with superior generalization performance. AU - Wever, Marcel Dominik AU - Mohr, Felix AU - Hüllermeier, Eyke ID - 2109 KW - Classification KW - Hierarchical Decomposition KW - Indirect Encoding T2 - Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2018, Kyoto, Japan, July 15-19, 2018 TI - Ensembles of Evolved Nested Dichotomies for Classification ER - TY - GEN AB - Predictive control of power electronic systems always requires a suitable model of the plant. Using typical physics-based white box models, a trade-off between model complexity (i.e. accuracy) and computational burden has to be made. This is a challenging task with a lot of constraints, since the model order is directly linked to the number of system states. Even though white-box models show suitable performance in most cases, parasitic real-world effects often cannot be modeled satisfactorily with an expedient computational load. Hence, a Koopman operator-based model reduction technique is presented which directly links the control action to the system's outputs in a black-box fashion. The Koopman operator is a linear but infinite-dimensional operator describing the dynamics of observables of nonlinear autonomous dynamical systems which can be nicely applied to the switching principle of power electronic devices. Following this data-driven approach, the model order and the number of system states are decoupled which allows us to consider more complex systems. Extensive experimental tests with an automotive-type permanent magnet synchronous motor fed by an IGBT 2-level inverter prove the feasibility of the proposed modeling technique in a finite-set model predictive control application. AU - Hanke, Sören AU - Peitz, Sebastian AU - Wallscheid, Oliver AU - Klus, Stefan AU - Böcker, Joachim AU - Dellnitz, Michael ID - 21634 T2 - arXiv:1804.00854 TI - Koopman Operator-Based Finite-Control-Set Model Predictive Control for Electrical Drives ER - TY - JOUR AU - Huang, Lingling AU - Zhang, Shuang AU - Zentgraf, Thomas ID - 1765 IS - 6 JF - Nanophotonics SN - 2192-8614 TI - Metasurface holography: from fundamentals to applications VL - 7 ER - TY - GEN AU - Wever, Marcel Dominik AU - Mohr, Felix AU - Hüllermeier, Eyke ID - 17713 TI - Automated Multi-Label Classification based on ML-Plan ER - TY - GEN AU - Mohr, Felix AU - Wever, Marcel Dominik AU - Hüllermeier, Eyke ID - 17714 TI - Automated machine learning service composition ER - TY - JOUR AB - The transverse dynamic spin susceptibility is a correlation function that yields exact information about spin excitations in systems with a collinear magnetic ground state, including collective spin-wave modes. In an ab initio context, it may be calculated within many-body perturbation theory or time-dependent density-functional theory, but the quantitative accuracy is currently limited by the available functionals for exchange and correlation in dynamically evolving systems. To circumvent this limitation, the spin susceptibility is here alternatively formulated as the solution of an initial-value problem. In this way, the challenge of accurately describing exchange and correlation in many-electron systems is shifted to the stationary initial state, which is much better understood. The proposed scheme further requires the choice of an auxiliary basis set, which determines the speed of convergence but always allows systematic convergence in practical implementations. AU - Schindlmayr, Arno ID - 18466 JF - Advances in Mathematical Physics SN - 1687-9120 TI - Exact formulation of the transverse dynamic spin susceptibility as an initial-value problem VL - 2018 ER - TY - CONF AB - Function integration is a key issue for an efficient and economic usage of Additive Manufacturing. An efficient heat transfer by topology optimized structures is a rarely considered approach which will be outlined with an exemplary electronic housing which has been newly designed. A commercial projector unit, whose electrical components in total produce 38 W, shall be integrated in the closed housing and passively cooled by natural convection. Topology optimized structures shall be generated in the inner part of the housing to transfer the heat homogenously from the projector components to the housing wall while simultaneously minimizing the mass. At the outside of the housing walls, lattice and rib structures are applied to increase the effective surface for heat transfer by natural convection and radiation. Furthermore, the housing geometry is optimized regarding a minimization of support structures to reduce the post-processing effort. Finally, the housing shall be built of AlSi10Mg by SLM. AU - Menge, Dennis AU - Delfs, Patrick AU - Töws, Marcel AU - Schmid, Hans-Joachim ID - 22183 T2 - 29th Annual International Solid Freeform Fabrication Symposium TI - Topology Optimized Heat Transfer Using the Example of an Electronic Housing VL - 29 ER - TY - CONF AB - Ein wichtiges Element der Digitalen Transformation ist die Digitalisierung der Prozesse in Unternehmen. Eine Herausforderung besteht hierbei in der systematischen Erkennung von Digitalisierungspotenzialen in Prozessen. Bestehende Ansätze benötigen Experten, welche Potenziale über ihre Erfahrung oder zeitaufwendig mithilfe von Musterkatalogen identifizieren. In diesem Artikel werden verschiedene Digitalisierungspotenziale klassifiziert und Muster für ein zukünftiges musterbasiertes Analyseverfahren zur automatisierten Identifikation von Digitalisierungspotenzialen in BPMN-Diagrammen beschrieben. Im Vergleich zu bestehenden Ansätzen erlaubt es Experten die Identifizierung von Digitalisierungspotenzialen effizienter und effektiver durchzuführen. AU - Rittmeier, Florian AU - Engels, Gregor AU - Teetz, Alexander ID - 2332 KW - Digitalisierungspotenziale KW - BPI KW - Digitale Transformation KW - Information Flow-Modellierung KW - Patterns KW - Requirements Engineering T2 - Joint Proceedings of the Workshops at Modellierung 2018 co-located with Modellierung 2018, Braunschweig, Germany, February 21, 2018. TI - Digitalisierungspotenziale in Geschäftsprozessen effizient und effektiv erkennen (Effective and Efficient Identification of Digitalization Potentials in Business Processes) VL - 2060 ER - TY - BOOK AU - Goller, Michael ID - 21817 KW - Bahnhofsmission KW - Survey Feedback KW - Monitoring SN - 978-3-946023-04-3 TI - Monitoring für die Bahnhofsmissionen: Ein datengestütztes Instrument zur Organisationsentwicklung. Projektbeschreibung und Ergebnisdarstellung ER - TY - CONF AU - Schumacher, Jan ID - 7766 T2 - Beiträge zum Mathematikunterricht 2018 TI - Semiotische Analyse von Sinnkonstruktionsprozessen bei einem innermathematischen Zugang zum Erlernen negativer Zahlen ER - TY - CONF AB - When responding to natural disasters, professional relief units are often supported by many volunteers which are not affiliated to humanitarian organizations. The effective coordination of these volunteers is crucial to leverage their capabilities and to avoid conflicts with professional relief units. In this paper, we empirically identify key requirements that professional relief units pose on this coordination. Based on these requirements, we suggest a decision model. We computationally solve a real-world instance of the model and empirically validate the computed solution in interviews with practitioners. Our results show that the suggested model allows for solving volunteer coordination tasks of realistic size near-optimally within short time, with the determined solution being well accepted by practitioners. We also describe in this article how the suggested decision support model is integrated in the volunteer coordination system which we develop in joint cooperation with a disaster management authority and a software development company. AU - Rauchecker, Gerhard AU - Schryen, Guido ID - 5675 KW - Coordination of spontaneous volunteers KW - volunteer coordination system KW - decision support KW - scheduling optimization model KW - linear programming T2 - Proceedings of the 15th International Conference on Information Systems for Crisis Response and Management TI - Decision Support for the Optimal Coordination of Spontaneous Volunteers in Disaster Relief ER - TY - CONF AU - Prester, Julian AU - Wagner, Gerit AU - Schryen, Guido ID - 5681 T2 - Proceedings of the 2018 International Conference on Information Systems (ICIS 2018) TI - Classifying the Ideational Impact of IS Review Articles: A Natural Language Processing Based Approach ER - TY - CONF AU - Peuster, Manuel AU - Karl, Holger ID - 6016 T2 - IEEE/IFIP 14th International Conference on Network and Service Management (CNSM) TI - Understand your chains and keep your deadlines: Introducing time-constrained profiling for NFV ER - TY - JOUR AU - Tünnermann, Jan AU - Scharlau, Ingrid ID - 6095 IS - 3 JF - Vision SN - 2411-5150 TI - Stuck on a plateau? A model-based approach to fundamental issues in visual temporal-order judgments VL - 2 ER -