检索结果-内蒙古大学图书馆

Forte: An Interactive Visual Analytic Tool for Trust-Augmented Net Load Forecasting

学校读者我要写书评

暂无评论

Forte: An Interactive Visual Analytic Tool for Trust-Augment...

2024 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2024

ISBN: (纸本)9798350313604

Accurate net load forecasting is vital for energy planning, aiding decisions on trade and load distribution. However, assessing the performance of forecasting models across diverse input variables, like temperature and humidity, remains challenging, particularly for eliciting a high degree of trust in the model outcomes. In this context, there is a growing need for data-driven technological interventions to aid scientists in comprehending how models react to both noisy and clean input variables, thus shedding light on complex behaviors and fostering confidence in the outcomes. In this paper, we present Forte, a visual analytics-based application to explore deep probabilistic net load forecasting models across various input variables and understand the error rates for different scenarios. With carefully designed visual interventions, this web-based interface empowers scientists to derive insights about model performance by simulating diverse scenarios, facilitating an informed decision-making process. We discuss observations made using Forte and demonstrate the effectiveness of visualization techniques to provide valuable insights into the correlation between weather inputs and net load forecasts, ultimately advancing grid capabilities by improving trust in forecasting models. © 2024 IEEE.

关键词： Decision making

Who Should I Trust? A Visual Analytics Approach for Comparing Net Load Forecasting Models

学校读者我要写书评

暂无评论

Who Should I Trust? A Visual Analytics Approach for Comparin...

Grid Edge Technologies Conference & Exposition (Grid Edge), IEEE PES

作者： Kaustav Bhattacharjee Soumya Kundu Indrasis Chakraborty Aritra Dasgupta Department of Data Science New Jersey Institute of Technology USA Optimization and Control Group Pacific Northwest National Laboratory USA Center for Applied Scientific Computing Lawrence Livermore National Laboratory USA

ISBN: (数字)9798350352528

ISBN: (纸本)9798350352535

关键词： Analytical models Load forecasting Biological system modeling Visual analytics Decision making Predictive models Data models Planning Forecasting Load modeling

Forte: An Interactive Visual Analytic Tool for Trust-Augmented Net Load Forecasting

学校读者我要写书评

暂无评论

Forte: An Interactive Visual Analytic Tool for Trust-Augment...

Innovative Smart Grid Technologies (ISGT)

关键词：

Who should I trust? A Visual Analytics Approach for Comparing Net Load Forecasting Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bhattacharjee, Kaustav Kundu, Soumya Chakraborty, Indrasis Dasgupta, Aritra Department of Data Science New Jersey Institute of Technology United States Optimization and Control Group Pacific Northwest National Laboratory United States Center for Applied Scientific Computing Lawrence Livermore National Laboratory United States

关键词： Visual analytics

Forte: An Interactive Visual Analytic Tool for Trust-Augmented Net Load Forecasting

学校读者我要写书评

暂无评论

arXiv 2023年

关键词： Decision making

Quality Control in Particle Precipitation via Robust optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kuchlbauer, Martina Dienstbier, Jana Muneer, Adeel Hedges, Hanna Stingl, Michael Liers, Frauke Pflug, Lukas Optimization under Uncertainty and Data Analysis Departement of Data Science Cauerstraße 11 Erlangen91058 Germany Cauerstraße 11 Erlangen91058 Germany Central Institute for Scientific Computing Martensstr. 5a Erlangen91058 Germany

We propose a robust optimization approach to mitigate the impact of uncertainties in particle precipitation. Our model of particle synthesis incorporates, as partial differential equations, nonlinear and nonlocal population balance equations. The optimization goal is to design products with desired size distributions. Recognizing the impact of uncertainties, we extend the model to robustly hedge against them to ensure tailored particle sizes. For the robust problem, we enhance an adaptive bundle framework for nonlinear robust optimization integrating the exact method of moments approach for the population balance equations. Computational experiments focus on uncertainties in precursor inflow rates, which greatly influence the resulting product’s quality. Using realistic parameter values for quantum dot synthesis, we demonstrate the algorithm’s efficiency and find that unprotected processes fail to achieve desired particle sizes, even for small uncertainties, highlighting the need for robust processes. The latter outperforms the unprotected process concerning the product’s quality in perturbed scenarios. © 2023, CC BY.

关键词： optimization

Kernel Neural Operators (KNOs) for Scalable, Memory-efficient, Geometrically-flexible Operator Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lowery, Matthew Turnage, John Morrow, Zachary Jakeman, John D. Narayan, Akil Zhe, Shandian Shankar, Varun Kahlert School of Computing University of Utah UT United States Department of Mathematics University of Utah UT United States Scientific Machine Learning Sandia National Laboratories United States Optimization and Uncertainty Quantification Sandia National Laboratories United States Institute Department of Mathematics University of Utah UT United States

This paper introduces the Kernel Neural Operator (KNO), a novel operator learning technique that uses deep kernel-based integral operators in conjunction with quadrature for function-space approximation of operators (maps from functions to functions). KNOs use parameterized, closed-form, finitely-smooth, and compactly-supported kernels with trainable sparsity parameters within the integral operators to significantly reduce the number of parameters that must be learned relative to existing neural operators. Moreover, the use of quadrature for numerical integration endows the KNO with geometric flexibility that enables operator learning on irregular geometries. Numerical results demonstrate that on existing benchmarks the training and test accuracy of KNOs is higher than popular operator learning techniques while using at least an order of magnitude fewer trainable parameters. KNOs thus represent a new paradigm of low-memory, geometricallyflexible, deep operator learning, while retaining the implementation simplicity and transparency of traditional kernel methods from both scientific computing and machine learning. © 2024, CC BY-NC-ND.

关键词： Learning algorithms

Enhanced prairie dog optimization with Levy flight and dynamic opposition-based learning for global optimization and engineering design problems

学校读者我要写书评

暂无评论

Neural computing and Applications 2024年第19期36卷 11137-11170页

作者： Biswas, Saptadeep Shaikh, Azharuddin Ezugwu, Absalom El-Shamir Greeff, Japie Mirjalili, Seyedali Bera, Uttam Kumar Abualigah, Laith Department of Mathematics National Institute of Technology Agartala Tripura Agartala India Unit for Data Science and Computing North-West University 11 Hoffman Street Potchefstroom2520 South Africa Faculty of Natural and Agricultural Sciences School of Computer Science and Information Systems North-West University Vanderbijlpark South Africa Centre for Artificial Intelligence Research and Optimization Torrens University Australia Fortitude Valley BrisbaneQLD4006 Australia Research Center University of Tabuk Tabuk71491 Saudi Arabia Computer Science Department Al al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Applied Science Research Center Applied Science Private University Amman11931 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia College of Engineering Yuan Ze University Taoyuan32003 Taiwan MEU Research Unit Middle East University Amman11831 Jordan

This study proposes a new prairie dog optimization algorithm version called EPDO. This new version aims to address the issues of premature convergence and slow convergence that were observed in the original PDO algorithm. To improve performance, several modifications are introduced in EPDO. First, a dynamic opposite learning strategy is employed to increase the diversity of the population and prevent premature convergence. This strategy helps the algorithm avoid falling into local optima and promotes global optimization. Additionally, the Lévy dynamic random walk technique is utilized in EPDO. This modified Lévy flight with random walk reduces the algorithm’s running time for the test function’s ideal value, accelerating its convergence. The proposed approach is evaluated using 33 benchmark problems from CEC 2017 and compared against seven other comparative techniques: GWO, MFO, ALO, WOA, DA, SCA, and RSA. Numerical results demonstrate that EPDO produces good outcomes and performs well in solving benchmark problems. To further validate the results and assess reliability, the authors employ average rank tests, the measurement of alternatives, and ranking according to the compromise solution (MARCOS) method, as well as a convergence report of EPDO and other algorithms. Furthermore, the effectiveness of the EPDO algorithm is demonstrated by applying it to five design problems. The results indicate that EPDO achieves impressive outcomes and proves its capability to address practical issues. The algorithm performs well in solving benchmark and practical design problems, as supported by the numerical results and validation methods used in the study. © The Author(s) 2024.

关键词： Global optimization

Democratizing Uncertainty Quantification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Seelinger, Linus Reinarz, Anne Lykkegaard, Mikkel B. Akers, Robert Alghamdi, Amal M.A. Aristoff, David Bangerth, Wolfgang Bénézech, Jean Diez, Matteo Frey, Kurt Jakeman, John D. Jørgensen, Jakob S. Kim, Ki-Tae Kent, Benjamin M. Martinelli, Massimiliano Parno, Matthew Pellegrini, Riccardo Petra, Noemi Riis, Nicolai A.B. Rosenfeld, Katherine Serani, Andrea Tamellini, Lorenzo Villa, Umberto Dodwell, Tim J. Scheichl, Robert Scientific Computing Center Karlsruhe Institute of Technology Karlsruhe Germany Department of Computer Science Durham University Durham United Kingdom digiLab Exeter United Kingdom UK Atomic Energy Authority Oxford United Kingdom Lyngby Denmark Department of Mathematics Colorado State University Fort CollinsCO United States Department of Mathematics Department of Geosciences Colorado State University Fort CollinsCO United States Centre for Integrated Materials Processes and Structures Department of Mechanical Engineering University of Bath Bath United Kingdom National Research Council Institute of Marine Engineering Rome Italy Institute for Disease Modeling Global Health Division Bill & Melinda Gates Foundation United States Optimization and Uncertainty Quantification Sandia National Laboratories AlbuquerqueNM United States University of California Merced United States National Research Council-Institute for Applied Mathematics and Information Technologies "E. Magenes" Pavia Italy Solea Energy ThetfordVT United States Copenhagen Imaging ApS Herlev Denmark The University of Texas Austin United States Heidelberg University Germany

Uncertainty Quantification (UQ) is vital to safety-critical model-based analyses, but the widespread adoption of sophisticated UQ methods is limited by technical complexity. In this paper, we introduce UM-Bridge (the UQ and Modeling Bridge), a high-level abstraction and software protocol that facilitates universal interoperability of UQ software with simulation codes. It breaks down the technical complexity of advanced UQ applications and enables separation of concerns between experts. UM-Bridge democratizes UQ by allowing effective interdisciplinary collaboration, accelerating the development of advanced UQ methods, and making it easy to perform UQ analyses from prototype to High Performance computing (HPC) scale. In addition, we present a library of ready-to-run UQ benchmark problems, all easily accessible through UM-Bridge. These benchmarks support UQ methodology research, enabling reproducible performance comparisons. We demonstrate UM-Bridge with several scientific applications, harnessing HPC resources even using UQ codes not designed with HPC support. © 2024, CC BY-NC-ND.

关键词： Application programs