检索结果-内蒙古大学图书馆

An Evaluation of Graph Algorithms for the Wind Farm Cable Layout Problem under Electrical Aspects

学校读者我要写书评

暂无评论

An Evaluation of Graph Algorithms for the Wind Farm Cable La...

International Universities Power Engineering Conference (UPEC)

作者： Sascha Gritzbach Hüseyin Çakmak Pascal Mehnert Torsten Ueckerdt Veit Hagenmeyer Institute of Theoretical Informatics Karlsruhe Institute of Technology Karlsruhe Germany Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany Karlsruhe Institute of Technology Karlsruhe Germany

The task of the Wind Farm Cable Layout Problem is to design a cable system between turbines and substations such that all turbine output can be transmitted to the substations. This problem can be modelled with different levels of complexity. While a higher level of complexity yields solutions that can be implemented in a real-world setting more readily, problem instances also become more difficult to solve or even remain intractable. More simplistic models are easier to solve but their usability could be inhibited. One such more simplistic model for installation cost minimization contains a network flow and a suitable minimum-cost flow algorithm provides good cable layouts on instances with up to 500 turbines within tens of seconds. The question remains whether those cable layouts are suitable for electrical implementation as well. We propose a workflow to evaluate the cable layouts generated from such algorithms under electrical aspects. This workflow converts the output of cable layout optimization algorithms to power flow models. The power flow models are simulated using the simulation framework eASiMOV. The evaluation of the power flow simulations under electrical metrics shows that output from the minimum-cost flow algorithm and from an approach solving a Mixed-Integer Linear Program perform very well under electrical aspects on a vast majority of input instances. For the remaining minority we are able to identify structures in the solutions that result in a worse performance. These observations can be used by the algorithm engineers as possible directions for future improvements.

关键词： Substations Power cables Layout Software algorithms Wind farms Power system stability Software

A Real-Time PHIL Implementation of a Novel Nonlinear Distributed Control Strategy for a Multi-Terminal DC Microgrid

学校读者我要写书评

暂无评论

A Real-Time PHIL Implementation of a Novel Nonlinear Distrib...

Power Tech Conference

作者： Ömer Ekin Filipe Perez Gilney Damm Veit Hagenmeyer Institute for Automation and Applied Informatics (IAI) Karlsruhe Institute of Technology (KIT) Karlsruhe Germany L2S Laboratory Paris-Saclay University Gif-sur-Y vette France IMSE Laboratory University Gustave Eiffel Marne-la-Vallee France

Multi-terminal DC Microgrids have great potential for integrating Renewable Energy Sources, Storage Technologies, and modern loads more efficiently because most of them operate on DC power. Besides the reduced conversion steps between the components, which avoids considerable losses, multi-terminal DC MicroGrids offer advantages due to the lack of skin effects and reactive power. Nevertheless, stabilizing such a DC network by controlling its power converters is a very challenging task in view of the fact that the classical solution, to use PI controllers based on linearized models, may lead to stable behavior only in a small region around the respective equilibrium point. In this paper, we present a real-time PHIL implementation of a novel nonlinear control scheme for a multi-terminal DC MicroGrid. The amount of needed capacitors is reduced significantly concerning previous approaches. The proposed nonlinear controller is compared with a cascaded PI controller based on a linearized model, the so-called vector control. Both approaches, nonlinear and linear, are implemented and validated on a real PHIL multi-terminal DC MicroGrid consisting of a battery, a PV, and two load ports. The real-time experimental results of PI-based and nonlinear control-based DC Microgrids are then compared. They show that the nonlinear control allows to better deal with disturbances and nonlinearities of the system, for several points of operation without re-tuning.

关键词：

Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei

学校读者我要写书评

暂无评论

Evaluation of semi-supervised learning using sparse labeling...

作者： Bruch, Roman Rudolf, Rüdiger Mikut, Ralf Reischl, Markus Institute of Molecular and Cell Biology Mannheim University of Applied Sciences Mannheim Germany Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany

The analysis of microscopic images from cell cultures plays an important role in the development of drugs. The segmentation of such images is a basic step to extract the viable information on which further evaluation steps are build. Classical image processing pipelines often fail under heterogeneous conditions. In the recent years deep neuronal networks gained attention due to their great potentials in image segmentation. One main pitfall of deep learning is often seen in the amount of labeled data required for training such models. Especially for 3D images the process to generate such data is tedious and time consuming and thus seen as a possible reason for the lack of establishment of deep learning models for 3D data. Efforts have been made to minimize the time needed to create labeled training data or to reduce the amount of labels needed for training. In this paper we present a new semisupervised training method for image segmentation of microscopic cell recordings based on an iterative approach utilizing unlabeled data during training. This method helps to further reduce the amount of labels required to effectively train deep learning models for image segmentation. By labeling less than one percent of the training data, a performance of 90% compared to a full annotation with 342 nuclei can be achieved. © 2020 by Walter de Gruyter Berlin/Boston 2020.

关键词： Deep learning

ALDI++: Automatic and parameter-less discord and outlier detection for building energy load profiles

学校读者我要写书评

暂无评论

Energy and Buildings 2022年 265卷 1页

作者： Quintana, Matias Stoeckmann, Till Park, June Young Turowski, Marian Hagenmeyer, Veit Miller, Clayton College of Design and Engineering National University of Singapore Singapore Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Germany Department of Civil Engineering University of Texas at Arlington United States

Data-driven building energy prediction is an integral part of the process for measurement and verification, building benchmarking, and building-to-grid interaction. The ASHRAE Great Energy Predictor III (GEPIII) machine learning competition used an extensive meter data set to crowdsource the most accurate machine learning workflow for whole building energy prediction. A significant component of the winning solutions was the pre-processing phase to remove anomalous training data. Contemporary pre-processing methods focus on filtering statistical threshold values or deep learning methods requiring training data and multiple hyper-parameters. A recent method named ALDI (Automated Load profile Discord Identification) managed to identify these discords using matrix profile, but the technique still requires user-defined parameters. We develop ALDI++, a method based on the previous work that bypasses user-defined parameters and takes advantage of discord similarity. We evaluate ALDI++ against a statistical threshold, variational auto-encoder, and the original ALDI as baselines in classifying discords and energy forecasting scenarios. Our results demonstrate that while the classification performance improvement over the original method is marginal, ALDI++ helps achieve the best forecasting error improving 6% over the winning's team approach with six times less computation time. © 2022 Elsevier B.V.

关键词： Matrix algebra

Analyzing Spatio-Temporal Dynamics of Dissolved Oxygen for the River Thames using Superstatistical Methods and Machine Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： He, Hankun Boehringer, Takuya Schäfer, Benjamin Heppell, Kate Beck, Christian Centre for Complex Systems Queen Mary University of London United Kingdom University College London United Kingdom Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Germany Chilterns National Landscape United Kingdom School of Geography Queen Mary University of London United Kingdom

By employing superstatistical methods and machine learning, we analyze time series data of water quality indicators for the River Thames (UK). The indicators analyzed include dissolved oxygen, temperature, electrical conductivity, pH, ammonium, turbidity, and rainfall, with a specific focus on the dynamics of dissolved oxygen. After detrending, the probability density functions of dissolved oxygen fluctuations exhibit heavy tails that are effectively modeled using q-Gaussian distributions. Our findings indicate that the multiplicative Empirical Mode Decomposition method stands out as the most effective detrending technique, yielding the highest log-likelihood in nearly all fittings. We also observe that the optimally fitted width parameter of the q-Gaussian shows a negative correlation with the distance to the sea, highlighting the influence of geographical factors on water quality dynamics. In the context of same-time prediction of dissolved oxygen, regression analysis incorporating various water quality indicators and temporal features identify the Light Gradient Boosting Machine as the best model. SHapley Additive exPlanations reveal that temperature, pH, and time of year play crucial roles in the predictions. Furthermore, we use the Transformer, a state-of-the-art machine learning model, to forecast dissolved oxygen concentrations. For long-term forecasting, the Informer model consistently delivers superior performance, achieving the lowest Mean Absolute Error and Symmetric Mean Absolute Percentage Error with the 192 historical time steps that we used. This performance is attributed to the Informer’s ProbSparse self-attention mechanism, which allows it to capture long-range dependencies in time-series data more effectively than other machine learning models. It effectively recognizes the half-life cycle of dissolved oxygen, with particular attention to critical periods such as morning to early afternoon, late evening to early morning, and key intervals between t

关键词： Aquatic ecosystems

A UNIVERSAL SYNTHETIC DATASET FOR MACHINE LEARNING ON SPECTROSCOPIC DATA

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Schuetzke, Jan Szymanski, Nathan J. Reischl, Markus Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany Department of Materials Science & Engineering UC Berkeley Lawrence Berkeley National Laboratory BerkeleyCA94720 United States

To assist in the development of machine learning methods for automated classification of spectroscopic data, we have generated a universal synthetic dataset that can be used for model validation. This dataset contains artificial spectra designed to represent experimental measurements from techniques including X-ray diffraction, nuclear magnetic resonance, and Raman spectroscopy. The dataset generation process features customizable parameters, such as scan length and peak count, which can be adjusted to fit the problem at hand. As an initial benchmark, we simulated a dataset containing 35,000 spectra based on 500 unique classes. To automate the classification of this data, eight different machine learning architectures were evaluated. From the results, we shed light on which factors are most critical to achieve optimal performance for the classification task. The scripts used to generate synthetic spectra, as well as our benchmark dataset and evaluation routines, are made publicly available to aid in the development of improved machine learning models for spectroscopic analysis. © 2022, CC BY.

关键词： Spectroscopic analysis

Analytical Uncertainty Propagation for Multi-Period Stochastic Optimal Power Flow

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bauer, Rebecca Mühlpfordt, Tillmann Ludwig, Nicole Hagenmeyer, Veit Institute for Automation und applied Informatics Karlsruhe Institute of Technology Germany Cluster of Excellence "Machine Learning: New Perspectives for Science" University of Tübingen Germany

The increase in renewable energy sources (RESs), like wind or solar power, results in growing uncertainty also in transmission grids. This affects grid stability through fluctuating energy supply and an increased probability of overloaded lines. One key strategy to cope with this uncertainty is the use of distributed energy storage systems (ESSs). In order to securely operate power systems containing renewables and use storage, optimization models are needed that both handle uncertainty and apply ESSs. This paper introduces a compact dynamic stochastic chance-constrained DC optimal power flow (CC-OPF) model, that minimizes generation costs and includes distributed ESSs. Assuming Gaussian uncertainty, we use affine policies to obtain a tractable, analytically exact reformulation as a second-order cone problem (SOCP). We test the new model on five different IEEE networks with varying sizes of 5, 39, 57, 118 and 300 nodes and include complexity analysis. The results show that the model is computationally efficient and robust with respect to constraint violation risk. The distributed energy storage system leads to more stable operation with flattened generation profiles. Storage absorbed RES uncertainty, and reduced generation cost. © 2022, CC BY-NC-ND.

关键词： Electric power transmission networks

Analytical Uncertainty Propagation for Multi-Period Stochastic Optimal Power Flow

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

The increase in renewable energy sources (RESs), like wind or solar power, results in growing uncertainty also in transmission grids. This affects grid stability through fluctuating energy supply and an increased probability of overloaded lines. One key strategy to cope with this uncertainty is the use of distributed energy storage systems (ESSs). In order to securely operate power systems containing renewables and use storage, optimization models are needed that both handle uncertainty and apply ESSs. This paper introduces a compact dynamic stochastic chance-constrained optimal power flow (CC-OPF) model, that minimizes generation costs and includes distributed ESSs. Assuming Gaussian uncertainty, we use affine policies to obtain a tractable, analytically exact reformulation as a second-order cone problem (SOCP). We test the new model on five different IEEE networks with varying sizes of 5, 39, 57, 118 and 300 nodes and include complexity analysis. The results show that the model is computationally efficient and robust with respect to constraint violation risk. The distributed energy storage system leads to more stable operation with flattened generation profiles. Storage absorbed RES uncertainty, and reduced generation cost. © 2022, The Authors. All rights reserved.

关键词： Acoustic generators

MLOps for Scarce Image Data: A Use Case in Microscopic Image Analysis

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sitcheu, Angelo Yamachui Friederich, Nils Baeuerle, Simon Neumann, Oliver Reischl, Markus Mikut, Ralf Institute for Automation and Applied Informatics Germany Institute of Biological and Chemical Systems Karlsruhe Institute of Technology Hermann-von-Helmholtz-Platz 1 Eggenstein-Leopoldshafen76344 Germany Robert Bosch GmbH Markwiesenstraße 46 Reutlingen72770 Germany

Nowadays, Machine Learning (ML) is experiencing tremendous popularity that has never been seen before. The operationalization of ML models is governed by a set of concepts and methods referred to as Machine Learning Operations (MLOps). Nevertheless, researchers, as well as professionals, often focus more on the automation aspect and neglect the continuous deployment and monitoring aspects of MLOps. As a result, there is a lack of continuous learning through the flow of feedback from production to development, causing unexpected model deterioration over time due to concept drifts, particularly when dealing with scarce data. This work explores the complete application of MLOps in the context of scarce data analysis. The paper proposes a new holistic approach to enhance biomedical image analysis. Our method includes: a fingerprinting process that enables selecting the best models, datasets, and model development strategy relative to the image analysis task at hand;an automated model development stage;and a continuous deployment and monitoring process to ensure continuous learning. For preliminary results, we perform a proof of concept for fingerprinting in microscopic image datasets. © 2023, CC BY.

关键词： Machine learning