检索结果-内蒙古大学图书馆

Guaranteeing Service in Connected Microgrids: Storage Planning and Optimal Power Sharing Policy

学校读者我要写书评

暂无评论

Guaranteeing Service in Connected Microgrids: Storage Planni...

American Control Conference (ACC)

作者： Arnab Dey Vivek Khatana Ankur Mani Murti V. Salapaka Department of Electrical and Computer Engineering University of Minnesota Twin Cities USA Department of Department of Industrial and Systems Engineering University of Minnesota Twin Cities USA

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

The integration of renewable energy sources (RES) into power distribution grids poses challenges to system reliability due to the inherent uncertainty in their power production. To address this issue, battery energy sources (BESs) are being increasingly used as a promising solution to counter the uncertainty associated with RES power production. During the overall system planning stage, the optimal capacity of the BESs has to be decided. In the operational phase, policies on when to charge the BESs and when to use them to support loads must be determined so that the BESs remain within their operating range, avoiding depletion of charge on one hand and remaining within acceptable margins of maximum charge on the other. In this paper, a stochastic control framework is used to determine BESs capacity, for microgrids (MGs), ensuring that during the operational phase, BESs' operating range is respected with pre-specified high probability. We provide an explicit analytical expression of the required BESs energy capacity for a single MG with RES as the main power source. Leveraging insights from the single MG case, the article focuses on the design and planning of BESs for the two-MG scenario. In this setting, MGs are allowed to share power while respecting the capacity constraints imposed by the power lines. We characterize the optimal power transfer policy between the MGs and the optimal BES capacity for the MGs. This provides the BES savings arising from connecting the microgrids,

关键词： Renewable energy sources Uncertainty Design methodology Power distribution Microgrids Production Planning

Physics-Informed Machine Learning for Electricity Markets: A NYISO Case Study

学校读者我要写书评

暂无评论

IEEE Transactions on Energy Markets, Policy and Regulation

IEEE Transactions on Energy Markets, Policy and Regulation 2024年第1期2卷 40-51页

作者： Ferrando, Robert Pagnier, Laurent Mieth, Robert Liang, Zhirui Dvorkin, Yury Bienstock, Daniel Chertkov, Michael University of Arizona Program in Applied Mathematics and Department of Mathematics TucsonAZ85721 United States Department of Industrial and Systems Engineering at Rutgers University PiscatawayNJ08854 United States Johns Hopkins University Department of Electrical and Computer Engineering BaltimoreMD21218-2625 United States Elec. and Comp. Eng. and Ralph o'Connor Sustainable Energy Institute Department of Civil and Systems Engineering Johns Hopkins University BaltimoreMD21218-2625 United States Columbia University IEOR New YorkNY10027 United States

This article addresses the challenge of efficiently recovering exact solutions to the optimal power flow problem in real-time electricity markets. The proposed solution, named Physics-Informed Market-Aware Active Set learning OPF (PIMA-AS-OPF), leverages physical constraints and market properties to ensure physical and economic feasibility of market-clearing outcomes. Specifically, PIMA-AS-OPF employs the active set learning technique and expands its capabilities to account for curtailment in load or renewable power generation, which is a common challenge in real-world power systems. The core of PIMA-AS-OPF is a fully-connected neural network that takes the net load and the system topology as input. The outputs of this neural network include active constraints such as saturated generators and transmission lines, as well as non-zero load shedding and wind curtailments. These outputs allow for reducing the original market-clearing optimization to a system of linear equations, which can be solved efficiently and yield both the dispatch decisions and the locational marginal prices (LMPs). The dispatch decisions and LMPs are then tested for their feasibility with respect to the requirements for efficient market-clearing results. The accuracy and scalability of the proposed method is tested on a realistic 1814-bus NYISO system with current and future renewable energy penetration levels. © 2023 IEEE.

关键词： Costs

Exploring the Impact of Vibrotactile Feedback on Boom Lift Safety Training: A Study Design

学校读者我要写书评

暂无评论

Exploring the Impact of Vibrotactile Feedback on Boom Lift S...

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Minseok Kang Chae Heon Lim Seul Chan Lee Changgu Kang Kangsoo Kim Department of Electrical and Software Engineering University of Calgary Department of Industrial and Systems Engineering Gyeongsang National University Department of Computer Science Gyeongsang National University

ISBN: (数字)9798350374490

ISBN: (纸本)9798350374506

In this paper, we present our research plan to investigate how various locations of vibrotactile feedback influence user experience and risk perception within a virtual reality (VR) based safety training simulation. We describe our planned user study where the study participants experience a construction boom lift ride (or operation) in an immersive VR environment. During the virtual lift ride, participants perform stage-maintenance tasks, such as assembling light bulbs and electrical lines, which involve certain safety risks—for example, hitting electrical lines and structures during the lift operation. In the study, the vibrotactile feedback condition is varied in three levels: (1) No-Vibration, (2) Controller-Vibration, and (3) Floor-Vibration. We plan to collect and analyze both subjective and objective data related to general user experience, sense of presence, and risk perception to examine the effectiveness of the safety training. Further details of our study and the boom lift ride simulation are described, and future plans are discussed.

关键词： Training Ethics Three-dimensional displays Conferences Virtual reality User interfaces User experience

Multi-Task Learning for Material Property Prediction

学校读者我要写书评

暂无评论

Multi-Task Learning for Material Property Prediction

International Conference on Machine Learning and Applications (ICMLA)

作者： C. M. A. Rahman Nishat B. Alam Amr S. El-Wakeel JuHyeong Ryu P. K. Gyawali Lane Department of Computer Science and Electrical Engineering (LCSEE) West Virginia University Department of Industrial and Management Systems Engineering (IMSE) West Virginia University

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

Material property prediction is a critical task within material science and other related fields where the identification of advanced materials with dynamic characteristics is essential for developing innovative technologies, improving product performance, and driving scientific discoveries. The search for suitable candidate materials aimed at specific applications is traditionally conducted through time-consuming experimental methods. Conversely, computational approaches, such as density functional theory (DFT) calculations, necessitate the resolution of complex mathematical equations and significant computational resources. Machine learning (ML) models have significantly transformed this field by automating the tedious process of material searching within extensive search spaces. However, these models are unable to incorporate diverse features of varying dimensions for different materials and properties. Recently, graph convolutional neural networks (GCNNs), have been employed to analyze the complex structures of materials, thereby efficiently predicting their associated properties. In this work, we demonstrate the potential of multi-task learning (MTL) in conjunction with the GCNNs in material property prediction. Our findings suggest that the MTL framework integrated into the GCNN architecture such as Crystal Graph Convolutional Neural Network (CGCNN) and its advanced variant Orbital Graph Convolutional Neural Network (OGCNN) can enhance the generalization and efficacy of property predictions. Notably, we achieved a maximum improvement of 7.95 % in one of our setups, underscoring the potential of these models to handle multiple property predictions with considerable effectiveness.

关键词： Space vehicles Photonic band gap Computational modeling Machine learning computer architecture Predictive models Multitasking Mathematical models Convolutional neural networks Material properties

Sharp analysis of EM for learning mixtures of pairwise differences

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dhawan, Abhishek Mao, Cheng Pananjady, Ashwin School of Mathematics School of Industrial and Systems Engineering School of Electrical and Computer Engineering Georgia Institute of Technology United States

We consider a symmetric mixture of linear regressions with random samples from the pairwise comparison design, which can be seen as a noisy version of a type of Euclidean distance geometry problem. We analyze the expectation-maximization (EM) algorithm locally around the ground truth and establish that the sequence converges linearly, providing an l∞-norm guarantee on the estimation error of the iterates. Furthermore, we show that the limit of the EM sequence achieves the sharp rate of estimation in the l2-norm, matching the information-theoretically optimal constant. We also argue through simulation that convergence from a random initialization is much more delicate in this setting, and does not appear to occur in general. Our results show that the EM algorithm can exhibit several unique behaviors when the covariate distribution is suitably structured. Copyright © 2023, The Authors. All rights reserved.

关键词： Maximum principle

A globally convergent difference-of-convex algorithmic framework and application to log-determinant optimization problems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yao, Chaorui Jiang, Xin Department of Electrical and Computer Engineering UCLA United States Department of Industrial and Systems Engineering Lehigh University United States

The difference-of-convex algorithm (DCA) is a conceptually simple method for the minimization of (possibly) nonconvex functions that are expressed as the difference of two convex functions. At each iteration, DCA constructs a global overestimator of the objective and solves the resulting convex subproblem. Despite its conceptual simplicity, the theoretical understanding and algorithmic framework of DCA needs further investigation. In this paper, global convergence of DCA at a linear rate is established under an extended Polyak–Lojasiewicz condition. The proposed condition holds for a class of DC programs with a bounded, closed, and convex constraint set, for which global convergence of DCA cannot be covered by existing analyses. Moreover, the DCProx computational framework is proposed, in which the DCA subproblems are solved by a primal–dual proximal algorithm with Bregman distances. With a suitable choice of Bregman distances, DCProx has simple update rules with cheap per-iteration complexity. As an application, DCA is applied to several fundamental problems in network information theory, for which no existing numerical methods are able to compute the global optimum. For these problems, our analysis proves the global convergence of DCA, and more importantly, DCProx solves the DCA subproblems efficiently. Numerical experiments are conducted to verify the efficiency of DCProx. © 2023, CC BY-NC-SA.

关键词： Numerical methods

Competitive Multi-Verse Optimization with Deep Learning Based Sleep Stage Classification

学校读者我要写书评

暂无评论

computer systems Science & engineering 2023年第5期45卷 1249-1263页

作者： Anwer Mustafa Hilal Amal Al-Rasheed Jaber SAlzahrani Majdy M.Eltahir Mesfer Al Duhayyim Nermin M.Salem Ishfaq Yaseen Abdelwahed Motwakel Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam Bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Industrial Engineering College of Engineering at AlqunfudahUmm Al-Qura UniversitySaudi Arabia Department of Information Systems College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam Bin Abdulaziz UniversitySaudi Arabia Department of Electrical Engineering Faculty of Engineering and TechnologyFuture University in EgyptNew Cairo11835Egypt

Sleep plays a vital role in optimum working of the brain and the *** people suffer from sleep-oriented illnesses like apnea,insomnia,*** stage classification is a primary process in the quantitative examination of polysomnographic *** stage scoring is mainly based on experts’knowledge which is laborious and time ***,it can be essential to design automated sleep stage classification model using machine learning(ML)and deep learning(DL)*** this view,this study focuses on the design of Competitive Multi-verse Optimization with Deep Learning Based Sleep Stage Classification(CMVODL-SSC)model using Electroencephalogram(EEG)*** proposed CMVODL-SSC model intends to effectively categorize different sleep stages on EEG ***,data pre-processing is performed to convert the actual data into useful ***,a cascaded long short term memory(CLSTM)model is employed to perform classification *** last,the CMVO algorithm is utilized for optimally tuning the hyperparameters involved in the CLSTM *** order to report the enhancements of the CMVODL-SSC model,a wide range of simulations was carried out and the results ensured the better performance of the CMVODL-SSC model with average accuracy of 96.90%.

关键词： Signal processing EEG signals sleep stage classification clstm model deep learning cmvo algorithm

A Deep Neural Network-based Frequency Predictor for Frequency-Constrained Optimal Power Flow

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jiang, Fan Li, Xingpeng Van Hentenryck, Pascal Department of Electrical and Computer Engineering University of Houston HoustonTX United States School of Industrial and Systems Engineering Georgia Institute of Technology AtlantaGA United States

Rate of change of frequency (RoCoF) and frequency nadir should be considered in real-time frequency-constrained optimal power flow (FCOPF) to ensure frequency stability of the modern power systems. Since calculating the frequency response is complex, deep neural network (DNN) could be adopted to capture the nonlinearities and estimate those two metrics accurately. Therefore, in this paper, a DNN-based frequency predictor is developed with the training data obtained from time-domain simulations using PSCAD/EMTDC. Subsequently, it is reformulated using a set of mixed-integer linear programming formulations and then embedded into the FCOPF framework as constraints to ensure grid frequency stability, creating the proposed DNN-FCOPF model. Two benchmark models, a traditional OPF without any frequency constraints and a linear system-wide RoCoF-constrained FCOPF, are also implemented to gauge the proposed DNN-FCOPF. Finally, the solutions obtained with these three models are compared and evaluated with time-domain simulations using PSCAD under various load profiles, demonstrating the effectiveness of the proposed DNN-FCOPF. © 2025, CC BY-NC-SA.

关键词： Deep neural networks

Emulation Learning for Neuromimetic systems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Zexin Baillieul, John The Division of Systems Engineering Boston University United States The Departments of Mechanical Engineering Electrical and Computer Engineering The Division of Systems Engineering Boston University BostonMA02215 United States

Building on our recent research on neural heuristic quantization systems, results on learning quantized motions and resilience to channel dropouts are reported. We propose a general emulation problem consistent with the neuromimetic paradigm. This optimal quantization problem can be solved by model predictive control (MPC), but because the optimization step involves integer programming, the approach suffers from combinatorial complexity when the number of input channels becomes large. Even if we collect data points to train a neural network simultaneously, collection of training data and the training itself are still time-consuming. Therefore, we propose a general Deep Q Network (DQN) algorithm that can not only learn the trajectory but also exhibit the advantages of resilience to channel dropout. Furthermore, to transfer the model to other emulation problems, a mapping-based transfer learning approach can be used directly on the current model to obtain the optimal direction for the new emulation problems. © 2023, CC BY-NC-SA.

关键词： Integer programming