检索结果-内蒙古大学图书馆

An Explainable Framework for Machine learning-Based Reactive Power Optimization of Distribution Network

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liao, Wenlong Schäfer, Benjamin Qin, Dalin Zhang, Gonghao Wang, Zhixian Yang, Zhe Lausanne Switzerland Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Department of Electrical Engineering The Hong Kong Polytechnic University Hong Kong

To reduce the heavy computational burden of reactive power optimization of distribution networks, machine learning models are receiving increasing attention. However, most machine learning models (e.g., neural networks) are usually considered as black boxes, making it challenging for power system operators to identify and comprehend potential biases or errors in the decision-making process of machine learning models. To address this issue, an explainable machine-learning framework is proposed to optimize the reactive power in distribution networks. Firstly, a Shapley additive explanation framework is presented to measure the contribution of each input feature to the solution of reactive power optimizations generated from machine learning models. Secondly, a model-agnostic approximation method is developed to estimate Shapley values, so as to avoid the heavy computational burden associated with direct calculations of Shapley values. The simulation results show that the proposed explainable framework can accurately explain the solution of the machine learning model-based reactive power optimization by using visual analytics, from both global and instance perspectives. Moreover, the proposed explainable framework is model-agnostic, and thus applicable to various models (e.g., neural networks). © 2023, CC BY-NC-ND.

关键词： Electric power distribution

Adaptive Feedforward Control for DC/DC Converters in Microgrids - A Power Hardware in the Loop Study

学校读者我要写书评

暂无评论

Adaptive Feedforward Control for DC/DC Converters in Microgr...

International Smart Grid Workshop and Certificate Program (ISGWCP)

作者： Jan Wachter Lutz Gröll Veit Hagenmeyer Institute for Automation and Applied Informatics (IAI) Karlsruhe Institute of Technology Karlsruhe Germany

This paper presents the application of an adaptive feedforward control approach based on radial basis functions for grid-tied Ćuk converters. A stability analysis provides a theoretical foundation for the expected stable operating range as well as bounds for the control signal at the operating points. With a power hardware in the loop implementation of the approach the feasibility for real-time application is shown, which is further illustrated by operating scenarios. Further, practical experience concerning the choice of the control parameters is presented along with the resulting advantages and limitations of the approach.

关键词： Microgrids Hardware Stability analysis Real-time systems Smart grids

Understanding electricity prices beyond the merit order principle using explainable AI

学校读者我要写书评

暂无评论

Energy and AI 2023年第3期13卷 149-159页

作者： Julius Trebbien Leonardo Rydin Gorjao Aaron Praktiknjo Benjamin Schafer Dirk Witthaut Forschungszentrum Julich Institute for Energy and Climate Research–Systems Analysis and Technology Evaluation(IEK-STE)52428 JülichGermany University of Cologne Institute for Theoretical PhysicsZülpicher Str.7750937 CologneGermany Faculty of Science and Technology Norwegian University of Life Sciences1432 AsNorway Chair for Energy System Economics Institute for Future Energy Consumer Needs and Behavior(FCN)E.ON Energy Research CenterRWTH Aachen UniversityMathieustr.1052074 AachenGermany Institute for Automation and Applied Informatics Karlsruhe Institute of Technology76344 Eggenstein-LeopoldshafenGermany JARA-ENERGY 52074 AachenGermany

Electricity prices in liberalized markets are determined by the supply and demand for electric power,which are in turn driven by various external influences that vary strongly in *** perfect competition,the merit order principle describes that dispatchable power plants enter the market in the order of their marginal costs to meet the residual load,*** difference of load and renewable *** market models are based on this principle when attempting to predict electricity prices,yet the principle is fraught with assumptions and simplifications and thus is limited in accurately predicting *** this article,we present an explainable machine learning model for the electricity prices on the German day-ahead market which foregoes of the aforementioned assumptions of the merit order *** model is designed for an ex-post analysis of prices and builds on various external *** SHapley Additive exPlanation(SHAP)values we disentangle the role of the different features and quantify their importance from empiric data,and therein circumvent the limitations inherent to the merit order *** show that load,wind and solar generation are the central external features driving prices,as expected,wherein wind generation affects prices more than solar ***,fuel prices also highly affect prices,and do so in a nontrivial ***,large generation ramps are correlated with high prices due to the limited flexibility of nuclear and lignite ***,we offer a model that describes the influence of the main drivers of electricity prices in Germany,taking us a step beyond the limited merit order principle in explaining the drivers of electricity prices and their relation to each other.

关键词： Electricity prices Merit order principle Explainable artificial intelligence Machine learning Fuel prices Energy market

AI-based automated active learning for discovery of hidden dynamic processes: A use case in light microscopy

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Friederich, Nils Sitcheu, Angelo Yamachui Neumann, Oliver Eroğlu-Kayıkçı, Süheyla Prizak, Roshan Hilbert, Lennart Mikut, Ralf Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Hermann-von-Helmholtz-Platz 1 Eggenstein-Leopoldshafen76344 Germany Institute of Biological and Chemical Systems Karlsruhe Institute of Technology Hermann-von-Helmholtz-Platz 1 Eggenstein-Leopoldshafen76344 Germany Zoological Institute Karlsruhe Institute of Technology Fritz-Haber-Weg 4 Karlsruhe76131 Germany

In the biomedical environment, experiments assessing dynamic processes are primarily performed by a human acquisition supervisor. Contemporary implementations of such experiments frequently aim to acquire a maximum number of relevant events from sometimes several hundred parallel, non-synchronous processes. Since in some high-throughput experiments, only one or a few instances of a given process can be observed simultaneously, a strategy for planning and executing an efficient acquisition paradigm is essential. To address this problem, we present two new methods in this paper. The first method, Encoded Dynamic Process (EDP), is Artificial Intelligence (AI)-based and represents dynamic processes so as to allow prediction of pseudo-time values from single still images. Second, with Experiment automation Pipeline for Dynamic Processes (EAPDP), we present a Machine Learning Operations (MLOps)-based pipeline that uses the extracted knowledge from EDP to efficiently schedule acquisition in biomedical experiments for dynamic processes in practice. In a first experiment, we show that the pre-trained State-Of-The-Art (SOTA) object segmentation method Contour Proposal Networks (CPN) works reliably as a module of EAPDP to extract the relevant object for EDP from the acquired three-dimensional image stack. © 2023, CC BY.

关键词： Pipelines

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

arXiv 2022年

作者： Quintana, Matias Stoeckmann, Till Park, June Young Turowski, Marian Hagenmeyer, Veit Miller, Clayton Singapore Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Germany Department of Civil Engineering University of Texas 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, CC BY.

关键词： Matrix algebra

Classification of Bundle Branch Blocks with QRS Templates Extracted from 12-lead ECGs

学校读者我要写书评

暂无评论

Classification of Bundle Branch Blocks with QRS Templates Ex...

作者： Welle, Hannes Nagel, Claudia Loewe, Axel Mikut, Ralf Dössel, Olaf Institute of Biomedical Engineering KIT Fritz-Haber-Weg 1 Karlsruhe Germany Institute for Automation and Applied Informatics KIT Hermann-von-Helmholtz-Platz 1 Eggenstein-Leopoldshafen Germany

Being non-invasive, cheap and widely available, the 12-lead electrocardiogram (ECG) is a standard method to assess cardiac function. Still, its reliable interpretation requires specialized knowledge and experience, rendering a second opinion valuable. We evaluated the performance of machine learning based classification of 11,705 healthy and bundle branch block 12-lead ECGs from 3 open databases. For each lead of the ECG signal, a representative QRS-complex template was extracted automatically. Principal component analysis (PCA) was applied to the concatenated, normalized and rescaled QRS signals to reduce their dimensionality. Multilayer perceptron and support-vector machine classifiers were trained using the principal components of weighted and non-weighted QRS template signals as input data. Classifiers achieved F1 scores between 0.92 and 0.96 on the test set for different input configurations. Anomaly based weighting slightly improved the performance of the classifiers. Neither class-wise PCA for feature extraction nor adding information on sex, gender and electrical heart axis to the input data yielded considerable improvement of the F1 scores. The achieved classification accuracy is similar to deep learning classifier performances and should generalize robustly to other ECG datasets. Our results suggest that this simple and well interpretable approach based on morphological signal characteristics is suitable for automatically and non-invasively identifying bundle branch block pathologies in clinical or smart electronics contexts. © 2021 by Walter de Gruyter Berlin/Boston.

关键词： Electrocardiograms

Probabilistic Forecasting of Day-Ahead Electricity Prices and their Volatility with LSTMs

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Trebbien, Julius Pütz, Sebastian Schäfer, Benjamin Nygård, Heidi S. Gorjão, Leonardo Rydin Witthaut, Dirk Forschungszentrum Jülich Jülich Germany Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Eggenstein-Leopoldshafen Germany Faculty of Science and Technology Norwegian University of Life Sciences Ås Norway

Accurate forecasts of electricity prices are crucial for the management of electric power systems and the development of smart applications. European electricity prices have risen substantially and became highly volatile after the Russian invasion of Ukraine, challenging established forecasting methods. Here, we present a Long Short-Term Memory (LSTM) model for the German-Luxembourg day-ahead electricity prices addressing these challenges. The recurrent structure of the LSTM allows the model to adapt to trends, while the joint prediction of both mean and standard deviation enables a probabilistic prediction. Using a physics-inspired approach – superstatistics – to derive an explanation for the statistics of prices, we show that the LSTM model faithfully reproduces both prices and their volatility. Copyright © 2023, The Authors. All rights reserved.

关键词： Long short-term memory

Experimental validation of demand side response rates for frequency control

学校读者我要写书评

暂无评论

Experimental validation of demand side response rates for fr...

IEEE Electronic Power Grid (eGrid)

作者： Leo Casasola-Aignesberger Friedrich Wiegel Simon Waczowicz Veit Hagenmeyer Sergio Martinez Department of electrical engineering Escuela Técnica Superior de Ingenieros Industriales Universidad Politécnica de Madrid Madrid Spain Institute for Automation and Applied Informatics Karlsruhe Institute of Technology (KIT)

Renewable energy generation is replacing conventional synchronous generators in electrical power systems around the world. A side effect of this trend is a reduction in system inertia and the power available for frequency control. In this study, the authors investigate an island power system of interest under different conditions with varying levels of demand side response penetration and analyze its impact on frequency behavior. The obtained simulation results are then complemented with a series of experiments carried out using a combination of real hardware and Power-Hardware-In-the-Loop equipment, to test the validity and limitations of the simulation results. In summary, demand side response can notably improve the frequency response of an island power system, but excessive demand side response leads to unacceptable frequency oscillations.

关键词：

Data analytics in the electricity sector – A quantitative and qualitative literature review

学校读者我要写书评

暂无评论

Energy and AI 2020年第1期1卷 145-167页

作者： Frederik vom Scheidt Hana Medinova Nicole Ludwig Bent Richter Philipp Staudt Christof Weinhardt Institute for Information Systems and Marketing Karlsruhe Institute of TechnologyKaiserstr.8976133 KarlsruheGermany Institute for Automation and Applied Informatics Karlsruhe Institute of TechnologyHermann-von-Helmholtz-Platz 176344 Eggenstein-LeopoldshafenGermany

The rapid transformation of the electricity sector increases both the opportunities and the need for Data *** recent years,various new methods and fields of application have been *** research is growing and becoming more diverse and specialized,it is essential to integrate and structure the fragmented body of scientific *** therefore conduct a systematic review of studies concerned with developing and applying Data Analytics methods in the context of the electricity value ***,we provide a quantitative high-level overview of the status quo of Data Analytics research,and show historical literature growth,leading countries in the field and the most intensive international ***,we qualitatively review over 200 high-impact studies to present an in-depth analysis of the most prominent applications of Data Analytics in each of the electricity sector’s areas:generation,trading,transmission,distribution,and *** each area,we review the state-of-the-art Data Analytics applications and *** addition,we discuss used data sets,feature selection methods,benchmark methods,evaluation metrics,and model complexity and run *** the findings from the different areas,we identify best practices and what researchers in one area can learn from other ***,we highlight potential for future research.

关键词： Data analytics Electricity Machine learning Generation Price Transmission Distribution Consumption