Refine
Year of publication
Document Type
- Report (17)
- Working Paper (16)
- Article (8)
- Preprint (5)
- Book (4)
- Conference Proceeding (1)
- Doctoral Thesis (1)
Language
- English (52) (remove)
Has Fulltext
- yes (52)
Keywords
- Optimierung (15)
- Optimization (13)
- Benchmarking (5)
- Modellierung (5)
- Simulation (5)
- Globale Optimierung (4)
- Soft Computing (4)
- Disaster Risk Reduction (3)
- Evolutionärer Algorithmus (3)
- Kriging (3)
Institute
- Fakultät für Informatik und Ingenieurwissenschaften (F10) (26)
- Fakultät 10 / Institut für Informatik (11)
- Fakultät 09 / Institut für Rettungsingenieurwesen und Gefahrenabwehr (4)
- Fakultät 02 / Köln International School of Design (2)
- Fakultät 04 / Institut für Versicherungswesen (2)
- Fakultät 10 / Institut für Data Science, Engineering, and Analytics (2)
- Fakultät 08 / Institut für Fahrzeugtechnik (1)
- Institut für Technologie und Ressourcenmanagement in den Tropen und Subtropen (ITT) (1)
When researchers and practitioners in the field of
computational intelligence are confronted with real-world
problems, the question arises which method is the best to
apply. Nowadays, there are several, well established test
suites and well known artificial benchmark functions
available.
However, relevance and applicability of these methods to
real-world problems remains an open question in many
situations. Furthermore, the generalizability of these
methods cannot be taken for granted.
This paper describes a data-driven approach for the
generation of test instances, which is based on
real-world data. The test instance generation uses
data-preprocessing, feature extraction, modeling, and
parameterization. We apply this methodology on a classical
design of experiment real-world project and generate test
instances for benchmarking, e.g. design methods, surrogate
techniques, and optimization algorithms. While most
available results of methods applied on real-world
problems lack availability of the data for comparison,
our future goal is to create a toolbox covering multiple
data sets of real-world projects to provide a test
function generator to the research community.
The performance of optimization algorithms relies crucially on their parameterizations. Finding good parameter settings is called algorithm tuning. Using
a simple simulated annealing algorithm, we will demonstrate how optimization algorithms can be tuned using the Sequential Parameter Optimization Toolbox (SPOT). SPOT provides several tools for automated and interactive tuning. The underlying concepts of the SPOT approach are explained. This includes key techniques such as exploratory fitness landscape analysis and response surface methodology. Many examples illustrate
how SPOT can be used for understanding the performance of algorithms and gaining insight into algorithm behavior. Furthermore, we demonstrate how SPOT can be used as an optimizer and how a sophisticated ensemble approach is able to combine several meta models via stacking.
Social learning enables multiple robots to share learned experiences while completing a task. The literature offers examples where robots trained with social learning reach a higher performance compared to their individual learning counterparts. No explanation has been advanced for that observation. In this research, we present experimental results suggesting that a lack of tuning of the parameters in social learning experiments could be the cause. In other words: the better the parameter settings are tuned, the less social learning can improve the system performance.
We propose to apply typed Genetic Programming (GP) to the problem of finding surrogate-model ensembles for global optimization on compute-intensive target functions. In a model ensemble, base-models such as linear models, random forest models, or Kriging models, as well as pre- and post-processing methods, are combined. In theory, an optimal ensemble will join the strengths of its comprising base-models while avoiding their weaknesses, offering higher prediction accuracy and robustness. This study defines a grammar of model ensemble expressions and searches the set for optimal ensembles via GP. We performed an extensive experimental study based on 10 different objective functions and 2 sets of base-models. We arrive at promising results, as on unseen test data, our ensembles perform not significantly worse than the best base-model.
Computational intelligence methods have gained importance in several real-world domains such as process optimization, system identification, data mining, or statistical quality control. Tools are missing, which determine the applicability of computational intelligence methods in these application domains in an objective manner. Statistics provide methods for comparing algorithms on certain data sets. In the past, several test suites were presented and considered as state of the art. However, there are several drawbacks of these test suites, namely: (i) problem instances are somehow artificial and have no direct link to real-world settings; (ii) since there is a fixed number of test instances, algorithms can be fitted or tuned to this specific and very limited set of test functions; (iii) statistical tools for comparisons of several algorithms on several test problem instances are relatively complex and not easily to analyze. We propose amethodology to overcome these dificulties. It is based on standard ideas from statistics: analysis of variance and its extension to mixed models. This work combines essential ideas from two approaches: problem generation and statistical analysis of computer experiments.
To maximize the throughput of a hot rolling mill,
the number of passes has to be reduced. This can be achieved by maximizing the thickness reduction in each pass. For this purpose, exact predictions of roll force and torque are required. Hence, the predictive models that describe the physical behavior of the product have to be accurate and cover a wide range of different materials.
Due to market requirements a lot of new materials are tested and rolled. If these materials are chosen to be rolled more often, a suitable flow curve has to be established. It is not reasonable to determine those flow curves in laboratory, because of costs and time. A strong demand for quick parameter determination and the optimization of flow curve parameter with minimum costs is the logical consequence. Therefore parameter estimation and the optimization with real data, which were collected during previous runs, is a promising idea. Producers benefit from this data-driven approach and receive a huge gain in flexibility when rolling new
materials, optimizing current production, and increasing quality. This concept would also allow to optimize flow curve parameters, which have already been treated by standard methods. In this article, a new data-driven approach for predicting the physical behavior of the product and setting important parameters is presented.
We demonstrate how the prediction quality of the roll force and roll torque can be optimized sustainably. This offers the opportunity to continuously increase the workload in each pass to the theoretical maximum while product quality and process stability can also be improved.
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.
The use of surrogate models is a standard method to deal with complex, realworld
optimization problems. The first surrogate models were applied to continuous
optimization problems. In recent years, surrogate models gained importance
for discrete optimization problems. This article, which consists of three
parts, takes care of this development. The first part presents a survey of modelbased
methods, focusing on continuous optimization. It introduces a taxonomy,
which is useful as a guideline for selecting adequate model-based optimization
tools. The second part provides details for the case of discrete optimization
problems. Here, six strategies for dealing with discrete data structures are introduced.
A new approach for combining surrogate information via stacking
is proposed in the third part. The implementation of this approach will be
available in the open source R package SPOT2. The article concludes with a
discussion of recent developments and challenges in both application domains.
In this paper we present a comparison of different data driven modeling methods. The first instance of a data driven linear Bayesian model is compared with several linear regression models, a Kriging model and a genetic programming model.
The models are build on industrial data for the development of a robust gas sensor.
The data contain limited amount of samples and a high variance.
The mean square error of the models implemented in a test dataset is used as the comparison strategy.
The results indicate that standard linear regression approaches as well as Kriging and GP show good results,
whereas the Bayesian approach, despite the fact that it requires additional resources, does not lead to improved results.
Modelling Zero-inflated Rainfall Data through the Use of Gaussian Process and Bayesian Regression
(2018)
Rainfall is a key parameter for understanding the water cycle. An accurate rainfall measurement is vital in the development of hydrological models. By means of indirect measurement, satellites can nowadays estimate the rainfall around the world. However, these measurements are not always accurate. As a first approach to generate a bias-corrected rainfall estimate using satellite data, the performance of Gaussian process and Bayesian regression is studied. The results show Gaussian process as the better option for this dataset but leave place to improvements on both modelling strategies.
An essential task for operation and planning of biogas plants is the optimization of substrate feed mixtures. Optimizing the monetary gain requires the determination of the exact amounts of maize, manure, grass silage, and other substrates. Accurate simulation models are mandatory for this optimization, because the underlying chemical processes are very slow. The simulation models themselves may be time-consuming to evaluate, hence we show how to use surrogate-model-based approaches to optimize biogas plants efficiently. In detail, a Kriging surrogate is employed. To improve model quality of this surrogate, we integrate cheaply available data into the optimization process. Doing so, Multi-fidelity modeling methods like Co-Kriging are employed. Furthermore, a two-layered modeling approach is employed to avoid deterioration of model quality due to discontinuities in the search space. At the same time, the cheaply available data is shown to be very useful for initialization of the employed optimization algorithms. Overall, we show how biogas plants can be efficiently modeled using data-driven methods, avoiding discontinuities as well as including cheaply available data. The application of the derived surrogate models to an optimization process is shown to be very difficult, yet successful for a lower problem dimension.
Learning board games by self-play has a long tradition in computational intelligence for games. Based on Tesauro’s seminal success with TD-Gammon in 1994, many successful agents use temporal difference learning today. But in order to be successful with temporal difference learning on game tasks, often a careful selection of features and a large number of training games is necessary. Even for board games of moderate complexity like Connect-4, we found in previous work that a very rich initial feature set and several millions of game plays are required. In this work we investigate different approaches of online-adaptable learning rates like Incremental Delta Bar Delta (IDBD) or Temporal Coherence Learning (TCL) whether they have the potential to speed up learning for such a complex task. We propose a new variant of TCL with geometric step size changes. We compare those algorithms with several other state-of-the-art learning rate adaptation algorithms and perform a case study on the sensitivity with respect to their meta parameters. We show that in this set of learning algorithms those with geometric step size changes outperform those other algorithms with constant step size changes. Algorithms with nonlinear output functions are slightly better than linear ones. Algorithms with geometric step size changes learn faster by a factor of 4 as compared to previously published results on the task Connect-4.
Cyclone separators are popular devices used to filter dust from the emitted flue gases. They are applied as pre-filters in many industrial processes including energy production and grain processing facilities.
Increasing computational power and the availability of 3D printers provide new tools for the combination of modeling and experimentation, which necessary for constructing efficient cyclones. Several simulation tools can be run in parallel, e.g., long running CFD simulations can be accompanied by experiments with 3D printers. Furthermore, results from analytical and data-driven models can be incorporated. There are fundamental differences between these modeling approaches: some models, e.g., analytical models, use domain knowledge, whereas data-driven models do not require any information about the underlying processes.
At the same time, data-driven models require input and output data, whereas analytical models do not. Combining results from models with different input-output structure is of great interest. This combination inspired the development of a new methodology. An optimization via multimodel simulation approach, which combines results from different models, is introduced.
Using cyclonic dust separators (cyclones) as a real-world simulation problem, the feasibility of this approach is demonstrated. Pros and cons of this approach are discussed and experiences from the experiments are presented.
Furthermore, technical problems, which are related to 3D-printing approaches, are discussed.
Increasing computational power and the availability of 3D printers provide new tools for the combination of modeling and experimentation. Several simulation tools can be run independently and in parallel, e.g., long running computational fluid dynamics simulations can be accompanied by experiments with 3D printers. Furthermore, results from analytical and data-driven models can be incorporated. However, there are fundamental differences between these modeling approaches: some models, e.g., analytical models, use domain knowledge, whereas data-driven models do not require any information about the underlying processes.
At the same time, data-driven models require input and output data, but analytical models do not. Combining results from models with different input-output structures might improve and accelerate the optimization process. The optimization via multimodel simulation (OMMS) approach, which is able to combine results from these different models, is introduced in this paper.
Using cyclonic dust separators as a real-world simulation problem, the feasibility of this approach is demonstrated and a proof-of-concept is presented. Cyclones are popular devices used to filter dust from the emitted flue gases. They are applied as pre-filters in many industrial processes including energy production and grain processing facilities. Pros and cons of this multimodel optimization approach are discussed and experiences from experiments are presented.
An important class of black-box optimization problems relies on using simulations to assess the quality of a given candidate solution. Solving such problems can be computationally expensive because each simulation is very time-consuming. We present an approach to mitigate this problem by distinguishing two factors of computational cost: the number of trials and the time needed to execute the trials. Our approach tries to keep down the number of trials by using Bayesian optimization (BO) –known to be sample efficient– and reducing wall-clock times by parallel execution of trials. We compare the performance of four parallelization methods and two model-free alternatives. Each method is evaluated on all 24 objective functions of the Black-Box-Optimization- Benchmarking (BBOB) test suite in their five, ten, and 20-dimensional versions. Additionally, their performance is investigated on six test cases in robot learning. The results show that parallelized BO outperforms the state-of-the-art CMA-ES on the BBOB test functions, especially for higher dimensions. On the robot learning tasks, the differences are less clear, but the data do support parallelized BO as the ‘best guess’, winning on some cases and never losing.
Many black-box optimization problems rely on simulations to evaluate the quality of candidate solutions. These evaluations can be computationally expensive and very time-consuming. We present and approach to mitigate this problem by taking into consideration two factors: The number of evaluations and the execution time. We aim to keep the number of evaluations low by using Bayesian optimization (BO) – known to be sample efficient– and to reduce wall-clock times by executing parallel evaluations. Four parallelization methods using BO as optimizer are compared against the inherently parallel CMA-ES. Each method is evaluated on all the 24 objective functions of the Black-Box-Optimization-Benchmarking test suite in their 20-dimensional versions. The results show that parallelized BO outperforms the state-of-the-art CMA-ES on most of the test functions, also on higher dimensions.
Recovery after extreme events - Lessons learned and remaining challenges in Disaster Risk Reduction
(2017)
Disasters such as the Indian Ocean Tsunami 2004, but also other extreme events such as cyclones, earthquakes and tsunami substantially affect the lives of many thousands of people - they are events radically and abruptly changing local circumstances and needs. At the same time they can significantly reshape global paradigms of Disaster Risk Reduction (DRR). Such events also bring to light the challenges in coordinating assistance from the “global community” with all the intended and un-intended effects. Two of the most pressing questions therefore are whether the different actors have learned from the disaster and whether processes of DRR and livelihood improvements have been implemented successfully.
This volume gathers selected papers addressing the following key questions:
- Lessons learned: Which lessons have been learned in a way that a difference can be seen today for the livelihoods and resilience of local people in the regions affected?
- Lessons to be Learned: Despite the body of knowledge created and reflected in a good number of lessons learned studies – what is still unsolved or needs to be emphasized?
- Monitoring and evaluation: Which DRR measures have been perpetuated and how can they be monitored and evaluated scientifically?
- Resilience effects and (unintended) side-effects: Which coping, recovery and adaptation measures are
supported by the resilience paradigm and which other areas are side-lined, neglected or even contrary to the intended effects?
- Dynamics in risk: In which cases has resilience building taken place? In which cases have ulnerabilities
been shifted internally or new vulnerabilities been created?
- Relocation/resettlement: How did the relocation/resettlement process of displaced people take place and what are its long-term effects?
- Urban-rural divide: How have DRR measures in urban vs. rural areas differed and which linkages but also rifts in rehabilitation and reconstruction initiatives can be observed between the two?
- Early warning: What is the future of Early Warning and how can important top-down information chains benefit from or be balanced with bottom-up feedback of users and affected people?
It appears that extreme disaster events spark a plethora of actions in academia, civil society, media, policy, private sector and other organisations. Tragic, as such disasters are, they offer incentives for learning, locally and globally. Lately, disaster impacts have in many cases been detracted through the application of knowledge and experience gained from previous events. However, there are still a number of challenges with regards to learning from past disasters
Architecural aproaches are considered to simplify the generation of re-usable building blocks in the field of data warehousing. While SAP’s Layer Scalable Architecure (LSA) offers a reference model for creating data warehousing infrastructure based on SAP software, extented reference models are needed to guide the integration of SAP and non-SAP tools. Therefore, SAP’s LSA is compared to the Data Warehouse Architectural Reference Model (DWARM), which aims to cover the classical data warehouse topologies.
A pension system is resilient if it able to absorb external (temporal) shocks and if it is able to adapt to (longterm) shifts of the socio-economic environment. Defined benefit (DB) and defined contribution pension plans behave contrastingly with respect to capital market shocks and shifts: while DB-plan benefits are not affected by external shocks they totally lack adaptability with respect to fundamental changes; DC-plans automatically adjust to a changing environment but any external shock has a direct impact on the (expected) pensions. By adding a collective component to DC-plans one can make these collective DC (CDC)-plans shock absorbing - at least to a certain degree. In our CDC pension model we build a collective reserve of assets that serves as a buffer to capital market shocks, e.g. stock market crashes. The idea is to transfer money from the collective reserve to the individual pension accounts whenever capital markets slump and to feed the collective reserve whenever capital market are booming. This mechanism is particular valuable for age cohorts that are close to retirement. It is clear that withdrawing assets from or adding assets to the collective reserve is essentially a transfer of assets between the age cohorts. In our near reality model we investigate the effect of stock market shocks and interest rate (and mortality) shifts on a CDC- pension system. We are particularly interested in the question, to what extend a CDC-pension system is actually able to absorb shocks and whether the intergenerational transfer of assets via the collective reserve can be regarded as fair.