检索结果-内蒙古大学图书馆

2025 IEEE PES Grid Edge Technologies Conference and Exposition, Grid Edge 2025

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

ISBN: (纸本)9798350352528

Net load forecasting is crucial for energy planning and facilitating informed decision-making regarding trade and load distributions. However, evaluating forecasting models' performance against benchmark models remains challenging, thereby impeding experts' trust in the model's performance. In this context, there is a demand for technological interventions that allow scientists to compare models across various timeframes and solar penetration levels. This paper introduces a visual analytics-based application designed to compare the performance of deep-learning-based net load forecasting models with other models for probabilistic net load forecasting. This application employs carefully selected visual analytic interventions, enabling users to discern differences in model performance across different solar penetration levels, dataset resolutions, and hours of the day over multiple months. We also present observations made using our application through a case study, demonstrating the effectiveness of visualizations in aiding scientists in making informed decisions and enhancing trust in net load forecasting models. © 2025 IEEE.

关键词： AI/ML net load forecasting visual analytics

来源：评论

学校读者我要写书评

暂无评论

Re-evaluation in Dynamic Tree-Search with Backtracking from Known Solutions

Re-evaluation in Dynamic Tree-Search with Backtracking fro...

引用

19th International Conference on Computer Aided Systems Theory, EUROCAST 2024

作者： Fleck, Philipp Neuhauser, Philipp Leitner, Sebastian Wagner, Stefan Heuristic and Evolutionary Algorithms Laboratory University of Applied Sciences Upper Austria Wels Austria Josef Ressel Center for Adaptive Optimization in Dynamic Environments University of Applied Sciences Upper Austria Wels Austria

ISBN: (纸本)9783031829512

In dynamic environments, solutions may become invalid during or after the execution of an optimization algorithm due to changing circumstances, requiring the adaptation or creation of new solutions. This paper uses the hot-storage area of a steel processing plant as a dynamic environment, where the optimization task involves creating lot-assignments of steel slabs for efficient transportation. The lot-assignment problem is represented as a search tree, where slabs are gradually assigned to new or existing lots as the tree is traversed. Unforeseen events in the dynamic hot-storage area can render existing lot-assignments invalid or make them less effective. Instead of completely re-running a tree-search algorithm in response to such dynamic events, we propose a backtracking strategy that uses information from outdated solutions. This strategy involves constructing a backtracking chain to check the validity of the lot-assignments used to construct the outdated solution and to identifying potential restart points for partial search spaces. Through experiments, we show the performance and reliability of various tree-search algorithms under different runtime budgets, with and without backtracking-based restart strategies. Our results strongly suggest that using information from a previous solution significantly enhances algorithm performance to identify valid solutions compared to a complete rerun. Additionally, using backtracking within the same runtime budget as a complete rerun can also improve solution quality. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Update Strategies for Real-Time Production Environments

Machine Learning Update Strategies for Real-Time Production...

引用

19th International Conference on Computer Aided Systems Theory, EUROCAST 2024

作者： Neuhauser, Philipp Fleck, Philipp Leitner, Sebastian Wagner, Stefan Heuristic and Evolutionary Algorithms Laboratory University of Applied Sciences Upper Austria Wels Austria Josef Ressel Center for Adaptive Optimization in Dynamic Environments University of Applied Sciences Upper Austria Wels Austria

ISBN: (纸本)9783031838873

Modern application scenarios in the dynamic industrial, financial, and economic sectors increasingly require quick and agile machine learning solutions. Instead of waiting hours for batch processing systems to deliver results, these systems should ideally adapt and make decisions as soon as new data comes in. As the demand for real-time machine learning solutions using streaming data is steadily increasing, this paper explores a software architecture that efficiently combines the Apache Kafka ecosystem with Microsoft’s machine learning framework *** for reliable data processing and model adaptation. The research addresses the complexity of deciding when to re-train these models in an unbounded data stream context. Various update strategies, including periodic, and performance-based model training, are evaluated for effectiveness under different conditions. The goal of this paper is to propose a completely autonomous machine learning pipeline that is capable of keeping models updated while minimizing computational costs required for re-training and ensuring prediction accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Data streams

来源：评论

学校读者我要写书评

暂无评论

Incrementally Solving the Dynamic Stacking Problem

Incrementally Solving the Dynamic Stacking Problem

引用

19th International Conference on Computer Aided Systems Theory, EUROCAST 2024

作者： Leitner, Sebastian Wagner, Stefan Affenzeller, Michael Heuristic and Evolutionary Algorithms Laboratory University of Applied Sciences Upper Austria Hagenberg4232 Austria Josef Ressel Center for Adaptive Optimization in Dynamic Environments Hagenberg Austria

ISBN: (纸本)9783031838873

In this paper we tackle the dynamic stacking problem by introducing a framework for incremental online optimization. The dynamic stacking problem features continuous uncertain arrival and delivery of blocks via a crane controlled by the solver. The problem is implemented as a discrete event simulation and the solver runs asynchronously. We develop a framework that can use our existing offline solver for the dynamic stacking problem and turn it into an online solver capable of incrementally updating optimized plans. We test our framework by comparing to our previously published iterative approach as well as a rule based baseline solver on a diverse set of problem instances. Using the new framework, the solver improves our key performance indicators across the benchmark instances. We also investigate the reasons for the performance differences both in the aggregate as well as the level of individual simulation runs. The framework not only works well on this specific stacking problem, but is general enough to be used in many online dynamic optimization problems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Discrete event simulation

来源：评论

学校读者我要写书评

暂无评论

A New Dual-Population Evolutionary Algorithm Leveraging Objective-Constraint Relationships for Constrained Multi-Objective optimization

SSRN

引用

SSRN 2025年

作者： Ye, Jialu Tan, Chaogui Xia, Yizhang Hou, Zhanglu Liu, Yuan Zou, Juan Hunan Engineering Research Center of intelligent System Optimization and Security Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Hunan National Applied Mathematics Center China Xiangtan University China

Population co-evolution strategies are widely used to handle constrained multi-objective optimization problems (CMOPs). However, existing coevolutionary algorithms oversimplify population collaboration and are rigid in evolving the auxiliary population, ignoring the importance of maintaining population diversity, especially for CMOPs with irregular feasible regions. To tackle this issue, we propose a new dual-population evolutionary algorithm, denoted as AACMO, which attempts to mine the relational features between the unconstrained Pareto front (UPF) and the constrained Pareto front (CPF) to better adapt to CMOPs with various constraints. Specifically, the method is categorized into two phases: a learning phase and an evolving phase. First, the main population (MP) aims to quickly learn the relationships between the UPF and the CPF by leveraging the advantages of different operators, namely, genetic algorithm operators and differential evolution operators, during the learning phase. Secondly, two auxiliary strategies are designed to collaborate with the MP during the evolving phase. These strategies are capable of employing a more effective co-evolution method to assist the MP in maintaining diversity, based on the degree of alignment between the learned UPF and CPF at the end of the learning phase. The effectiveness of AACMO is confirmed through comparative analysis with eight state-of-the-art algorithms across four CMOP benchmark suites. © 2025, The Authors. All rights reserved.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Advancements on multi-fidelity random Fourier neural networks: application to hurricane modeling for offshore wind energy

Advancements on multi-fidelity random Fourier neural network...

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Davis, Owen Geraci, Gianluca Wentz, Jacqueline M. King, Ryan N. Cortiella, Alexandre Rybchuk, Alex Gomez, Miguel Sanchez Deskos, Georgios Motamed, Mohammad Optimization and Uncertainty Quantification Sandia National Laboratories AlbuquerqueNM United States Computational Data Science Sandia National Laboratories LivermoreCA United States National Wind Technology Center National Renewable Energy Laboratory GoldenCO United States Department of Applied Mathematics and Statistics University of New Mexico AlbuquerqueNM United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Multi-fidelity approaches are emerging as effective strategies in computational science to handle otherwise intractable tasks like Uncertainty Quantification (UQ), training of Machine Learning (ML) models, and optimization, for expensive high-fidelity applications in which the amount of available simulations or data is limited. The main idea is simple: large datasets generated for low-fidelity approximations of the problem at hand are fused with a much sparser dataset for the target (high-fidelity) system. In this paper, we build on our recent success in designing random Fourier Neural Networks (rFNNs) [1] to target problems arising in wind energy applications and in particular problems of interest for hurricane modeling. In this context, data for the high-fidelity models are limited and lower fidelity alternatives are needed. In this work, we introduce a novel multi-fidelity training approach for our rFNNs and demonstrate its use on a simple verification problem and on a hurricane modeling problem in which high-fidelity data are generated via Large-Eddy Simulations (LES), while low-fidelity data are given by a mesoscale model. Initial results demonstrate how the multi-fidelity training approach can improve the quality of the resulting surrogate. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Large eddy simulation

来源：评论

学校读者我要写书评

暂无评论

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

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

引用

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

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Algorithm Selection for a Multiprocessor Scheduling Problem

Learning-Based Algorithm Selection for a Multiprocessor Sc...

引用

19th International Conference on Computer Aided Systems Theory, EUROCAST 2024

作者： Braune, Roland University of Applied Sciences Upper Austria Operations Management Wels Austria Department of Business Decisions and Analytics University of Vienna Vienna Austria Josef Ressel Center for Adaptive Optimization in Dynamic Environments University of Vienna Vienna Austria

ISBN: (纸本)9783031838873

This paper addresses a multiprocessor scheduling problem with real-world-inspired constraints. A learning-based prediction approach is proposed to support an effective algorithm selection during problem-solving. Classifiers are trained to predict whether a particular solver should be employed. The core of the contribution is the selection and engineering of features based on the structural properties of problem instances. These features are used as predictors in several well-known binary classification approaches. Computational experiments based on randomly generated problem instances reveal accuracy scores of up to 90% and indicate the potential time savings when embedding the proposed classifiers into the overall solution procedure. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Online Machine Learning for the Estimation of Process Times in Dynamic Scheduling

Online Machine Learning for the Estimation of Process Tim...

引用

19th International Conference on Computer Aided Systems Theory, EUROCAST 2024

作者： Heckmann, Michael Werth, Bernhard Karder, Johannes Wagner, Stefan Josef Ressel Center for Adaptive Optimization in Dynamic Environments Heuristic and Evolutionary Algorithms Laboratory University of Applied Sciences Upper Austria Hagenberg4232 Austria Symbolic Artificial Intelligence Johannes Kepler University Linz4040 Austria

ISBN: (纸本)9783031838873

This paper presents a study on applying online machine-learning models to estimate the processing times of different production tasks for dynamic scheduling problems. Specifically, various machine-learning approaches and their impact on the schedule quality are evaluated. A discrete event simulation of a production process was created, with different functions determining processing time. This production simulation was optimized with the OERAPGA optimization algorithm. Based on the experiments, the performance of different machine learning models was assessed. Moreover, the speed and prediction quality of these models and their resulting optimization quality were evaluated. Results showed that the speed of evaluation plays a more significant role in optimization quality than prediction accuracy, as the optimizer seems to be focused on optimizing macroscopic aspects of the production schedule. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Computer control

来源：评论

学校读者我要写书评

暂无评论

Predicting the Processing Effort for Block Relocation Problems

Predicting the Processing Effort for Block Relocation Prob...

引用

19th International Conference on Computer Aided Systems Theory, EUROCAST 2024

作者： Braune, Roland Raunig, Michael Operations Management University of Applied Sciences Upper Austria Wels Austria Department of Business Decisions and Analytics University of Vienna Vienna Austria Josef Ressel Center for Adaptive Optimization in Dynamic Environments University of Vienna Vienna Austria

ISBN: (纸本)9783031838873

In this paper, we propose a machine learning-based prediction approach for the block relocation problem. The target concept to be captured is the minimum number of relocations needed to clear all stacks of a given configuration. Since the problem is NP-hard, an exact determination of this value is computationally expensive. Therefore, quick and precise estimates are highly valuable, especially when the problem appears in hierarchical optimization contexts as a subproblem of another optimization problem, for example. We propose a design and training concept for a convolutional neural network that is capable of achieving accurate predictions on benchmark instances from the literature. The computational results further show that it is able to outperform competitor approaches like lower bounds, alternative machine learning techniques, and fast heuristics in terms of speed and common error metrics on most instance classes. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：