Refine
Language
- English (11) (remove)
Has Fulltext
- yes (11)
Keywords
- Optimierung (7)
- Modellierung (5)
- Mehrkriterielle Optimierung (3)
- Optimization (3)
- Simulation (3)
- Soft Computing (3)
- Co-Kriging (2)
- Evolutionärer Algorithmus (2)
- Genetic Programming (2)
- Globale Optimierung (2)
- Kriging (2)
- Multi-Criteria Optimization (2)
- Multiobjective Optimization (2)
- Sequential Parameter Optimization (2)
- Sequentielle Parameter Optimierung (2)
- Surrogat-Modellierung (2)
- Surrogate Modeling (2)
- Adaptive Schrittweite (1)
- Biogas (1)
- Biogas Plant (1)
- Board Games (1)
- Computational Intelligence (1)
- Cyclone Dust Separator (1)
- Datenanalyse (1)
- Design of Experiments (1)
- Ensemble Methods (1)
- Entstauber (1)
- Event Detection (1)
- Evolutionary Algorithms (1)
- Evolutionäre Algorithmen (1)
- Expected Improvement (1)
- Fehlende Daten (1)
- Genetische Programmierung (1)
- Imputation (1)
- Maschinelles Lernen (1)
- Metaheuristik (1)
- Metamodel (1)
- Missing Data (1)
- Mixed Models (1)
- Mixed-Effects Models (1)
- Modelling (1)
- Modelllernen (1)
- Multi-criteria Optimization (1)
- Multi-fidelity (1)
- N-tuple Systems (1)
- Online Adaptation (1)
- Optimierungsproblem (1)
- Prognose (1)
- R (1)
- Reinforcement Learning (1)
- Simulationsmodell (1)
- Software (1)
- Statistics (1)
- Statistische Versuchsplanung (1)
- Surrogate Models (1)
- Surrogate Optimization (1)
- Surrogate-Model-Based Optimization (1)
- System Identification (1)
- Systemidentifikation (1)
- Temporal Difference Learning (TDL) (1)
- Time-series (1)
- Unsicherheit (1)
- Varianzanalyse (1)
- Versuchsplanung (1)
- Vorverarbeitung (1)
- Water Quality Monitoring (1)
- Zeitreihe (1)
- Zeitreihenanalyse (1)
- Zylon Enstauber (1)
Institute
- Fakultät 10 / Institut für Informatik (11) (remove)
Formerly, multi-criteria optimization algorithms were often tested using tens of thousands function evaluations. In many real-world settings function evaluations are very costly or the available budget is very limited. Several methods were developed to solve these cost-extensive multi-criteria optimization problems by reducing the number of function evaluations by means of surrogate optimization. In this study, we apply different multi-criteria surrogate optimization methods to improve (tune) an event-detection software for water-quality monitoring. For tuning two important parameters of this software, four state-of-the-art methods are compared: S-Metric-Selection Efficient Global Optimization (SMS-EGO), S-Metric-Expected Improvement for Efficient Global Optimization SExI-EGO, Euclidean Distance based Expected Improvement Euclid-EI (here referred to as MEI-SPOT due to its implementation in the Sequential Parameter Optimization Toolbox SPOT) and a multi-criteria approach based on SPO (MSPOT). Analyzing the performance of the different methods provides insight into the working-mechanisms of cutting-edge multi-criteria solvers. As one of the approaches, namely MSPOT, does not consider the prediction variance of the surrogate model, it is of interest whether this can lead to premature convergence on the practical tuning problem. Furthermore, all four approaches will be compared to a simple SMS-EMOA to validate that the use of surrogate models is justified on this problem.