检索结果-内蒙古大学图书馆

Centralized Control for Optimizing Microgrids Operation

学校读者我要写书评

暂无评论

Centralized Control for Optimizing Microgrids Operation

IEEE Power and Energy Society General Meeting

作者： Antonis G. Tsikalakis Nikos D. Hatziargyriou National Technical University of Athens

ISBN: (纸本)9781457710001

Microgrids are Low Voltage distribution networks comprising various distributed generators (DG), storage devices and controllable loads that can operate either interconnected or isolated from the main distribution grid as a controlled entity. This paper describes the operation of a Central Controller for Microgrids. The controller aims to optimize the operation of the Microgrid during interconnected operation, i.e. maximize its value by optimizing production of the local DGs and power exchanges with the main distribution grid. Two market policies are assumed including Demand Side Bidding options for controllable loads. The developed optimization algorithms are applied on a typical LV study case network operating under various market policies and assuming realistic spot market prices and DG bids reflecting realistic operational costs. The effects on the Microgrid and the Distribution network operation are presented and discussed.

关键词： Microgrids Distributed Generation Demand Side Bidding Markets optimization Renewable Energy Sources MICRO-GRID Power grids Renewable energy renewable energy sources distributed power generation INTEGRATED SHIP CONTROL Markets Surgery interconnected operation central controller commercial policies Pricing optimization algorithms

Automatic Differentiation for Sensitivity Calculation in Electromagnetism: Application for optimization of a Linear Actuator

学校读者我要写书评

暂无评论

Automatic Differentiation for Sensitivity Calculation in Ele...

Biennial Institute of Electrical and Electronics Engineers Conference on Electomagnetic Field Computation

作者： P. Enciu F. Wurtz L. Gerbaud G2ELab Laboratory

ISBN: (纸本)9781424470594

Automatic Differentiation (AD) is introduced as a powerful technique to compute derivatives of functions given in the form of computer programs in high level programming languages such FORTRAN, C or C++. The paper applies AD to compute error-free gradients of sizing models describing electromagnetic devices. Then, the obtained gradients are exploited by optimization algorithms. The goal is to find the device geometry that minimizes an objective function by respecting some additional constrained parameters and performances. When algorithms are used for model formulation, evaluating their derivatives becomes a complicated task. The paper proposes a model of a linear actuator dealing with implicit equations solved by numerical methods.

关键词： device geometry linear actuator Differentiation Implicit equations optimization algorithms Electromagnetism Computer Programming Languages Electromagnetic fields Numerical methods Objective function AD model size AUTOMATIC differentiation Individualized Instruction

CONSISTENT algorithms FOR MULTI-LABEL CLASSIFICATION WITH MACRO-AT-k METRICS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Schultheis, Erik Kotlowski, Wojciech Wydmuch, Marek Babbar, Rohit Borman, Strom Dembczyński, Krzysztof Aalto University Helsinki Finland Poznan University of Technology Poznan Poland University of Bath Bath United Kingdom Yahoo Research Champaign United States Yahoo Research New York United States

We consider the optimization of complex performance metrics in multi-label classification under the population utility framework. We mainly focus on metrics linearly decomposable into a sum of binary classification utilities applied separately to each label with an additional requirement of exactly k labels predicted for each instance. These "macro-at-k" metrics possess desired properties for extreme classification problems with long tail labels. Unfortunately, the at-k constraint couples the otherwise independent binary classification tasks, leading to a much more challenging optimization problem than standard macro-averages. We provide a statistical framework to study this problem, prove the existence and the form of the optimal classifier, and propose a statistically consistent and practical learning algorithm based on the Frank-Wolfe method. Interestingly, our main results concern even more general metrics being non-linear functions of label-wise confusion matrices. Empirical results provide evidence for the competitive performance of the proposed approach. Copyright © 2024, The Authors. All rights reserved.

关键词： optimization algorithms

An optimisation algorithm for matching large scale databases on customers for improved characterisation of electricity consumption

学校读者我要写书评

暂无评论

An optimisation algorithm for matching large scale databases...

Mediterranean Conference on Power Generation, Transmission, Distribution and Energy Conversion (MedPower 2016)

作者： Thibaut Barbier Robin Girard Nicolas Kong François-Pascal Neirac Georges Kariniotakis Elena Magliaro Centre for Processes Renewable Energies and Energy Systems (PERSEE) MINES ParisTech PSL - Research University Sophia Antipolis France Enedis Paris La Défense France

ISBN: (纸本)9781510836884

This paper presents a method that permits to match customer information from the French DSO Enedis and housing information from the French population census institute INSEE. Our method allows having a list of housings linked to each customer in order to add household and building information to customers. We show with our method improvements in predictions of aggregated load curve indicators compared to the traditional method that averages socio demographic indicators from housing information of the zone covered by measurements. Our results indicate that the proposed algorithm is able to capture efficiently the information of housings in some feeders. This permits to combine the databases of the DSO with external databases that exist from census or other processes. Enriching the information at the level of clients through the proposed automated way is a cost effective approach given the number of customers served by a DSO. This enhanced information can be then the basis to model, analyse and simulate demand in a bottom up approach which can be useful for planning purposes of the distribution networks.

关键词： power distribution planning optimisation power consumption power distribution planning optimization algorithms Domestic architecture digital storage oscilloscopes Power consumption customers Customer information electricity consumption Purchasing census External databases Power grids Database information

A survey on pioneering metaheuristic algorithms between 2019 and 2024

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dokeroglu, Tansel Canturk, Deniz Kucukyilmaz, Tayfun TED University Software Engineering Department Ankara Turkey Department of Technology and Operations Management Erasmus University Netherlands

This review examines over 150 new metaheuristics of the last six years (between 2019-2024), underscoring their profound influence and performance. Over the past three decades, more than 500 new metaheuristic algorithms have been proposed, with no slowdown in sight—an overwhelming abundance that complicates the process of selecting and assessing the most effective solutions for complex optimization challenges. Our evaluation centers on pivotal criteria, including annual citation metrics, the breadth of addressed problem types, source code availability, user-friendly parameter configurations, innovative mechanisms and operators, and approaches designed to mitigate traditional metaheuristic issues such as stagnation and premature convergence. We further explore recent high-impact applications of the past six years’ most influential 23 metaheuristic algorithms, shedding light on their advantages and limitations, while identifying challenges and potential avenues for future research. © 2024, CC BY.

关键词： optimization algorithms

Faster Adaptive Decentralized Learning algorithms

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Feihu Zhao, Jianyu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

Decentralized learning recently has received increasing attention in machine learning due to its advantages in implementation simplicity and system robustness, data privacy. Meanwhile, the adaptive gradient methods show superior performances in many machine learning tasks such as training neural networks. Although some works focus on studying decentralized optimization algorithms with adaptive learning rates, these adaptive decentralized algorithms still suffer from high sample complexity. To fill these gaps, we propose a class of faster adaptive decentralized algorithms (i.e., AdaMDOS and AdaMDOF) for distributed nonconvex stochastic and finite-sum optimization, respectively. Moreover, we provide a solid convergence analysis framework for our methods. In particular, we prove that our AdaMDOS obtains a near-optimal sample complexity of Õ(ϵ−3) for finding an ϵ-stationary solution of nonconvex stochastic optimization. Meanwhile, our AdaMDOF obtains a near-optimal sample complexity of O(√nϵ−2) for finding an ϵ-stationary solution of nonconvex finite-sum optimization, where n denotes the sample size. To the best of our knowledge, our AdaMDOF algorithm is the first adaptive decentralized algorithm for nonconvex finite-sum optimization. Some experimental results demonstrate efficiency of our algorithms. © 2024, CC BY-NC-ND.

关键词： optimization algorithms

Submodular Information Selection for Hypothesis Testing with Misclassification Penalties

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bhargav, Jayanth Ghasemi, Mahsa Sundaram, Shreyas Elmore Family School of Electrical & Computer Engineering Purdue University IN47907 United States

We consider the problem of selecting an optimal subset of information sources for a hypothesis testing/classification task where the goal is to identify the true state of the world from a finite set of hypotheses, based on finite observation samples from the sources. In order to characterize the learning performance, we propose a misclassification penalty framework, which enables nonuniform treatment of different misclassification errors. In a centralized Bayesian learning setting, we study two variants of the subset selection problem: (i) selecting a minimum cost information set to ensure that the maximum penalty of misclassifying the true hypothesis is below a desired bound and (ii) selecting an optimal information set under a limited budget to minimize the maximum penalty of misclassifying the true hypothesis. Under certain assumptions, we prove that the objective (or constraints) of these combinatorial optimization problems are weak (or approximate) submodular, and establish high-probability performance guarantees for greedy algorithms. Further, we propose an alternate metric for information set selection which is based on the total penalty of misclassification. We prove that this metric is submodular and establish near-optimal guarantees for the greedy algorithms for both the information set selection problems. Finally, we present numerical simulations to validate our theoretical results over several randomly generated instances. © 2024, CC BY.

关键词： optimization algorithms

Lifted implicit integrators for direct optimal control

学校读者我要写书评

暂无评论

Lifted implicit integrators for direct optimal control

IEEE Annual Conference on Decision and Control

作者： Rien Quirynen Sebastien Gros Moritz Diehl Department ESAT-STADIUS KU Leuven University Kasteelpark Arenberg 10 3001 Leuven Belgium Department of Signals and Systems Chalmers University of Technology Horsalsvagen 11 SE-412 96 Goteborg Sweden

ISBN: (纸本)9781479978878

Nonlinear Model Predictive Control (NMPC) relies on solving an Optimal Control Problem (OCP) online at every sampling time. The discretization of the continuous time dynamics requires the deployment of some numerical integration method. To that end, implicit integrators are often preferred when stiff or implicitly defined dynamics are present in the system. Implicit integration schemes, however, are typically more expensive to implement than explicit methods. This paper presents a novel lifting method for implicit integrators which improves their computational efficiency and accuracy in the context of Newton-type optimization algorithms. Similar to the standard lifted Newton, the proposed lifting method requires a marginal implementation effort. This novel approach has been implemented in the ACADO code generation software, and its efficiency illustrated using a nontrivial control example. An improved convergence and a computational speedup of about factor 2 are reported.

关键词： lift integrators Implicit optimization algorithms Integration Methods Optimal control nonlinear model predictive control Computational efficiency deployment lifts

Distributed Alternating Direction Method of Multipliers

学校读者我要写书评

暂无评论

Distributed Alternating Direction Method of Multipliers

IEEE Annual Conference on Decision and Control

作者： Ermin Wei Asuman Ozdaglar Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology

ISBN: (纸本)9781467320658

We consider a network of agents that are cooperatively solving a global unconstrained optimization problem, where the objective function is the sum of privately known local objective functions of the agents. Recent literature on distributed optimization methods for solving this problem focused on subgradient based methods, which typically converge at the rate O(1/{the square root of}k) where k is the number of iterations. In this paper, we introduce a new distributed optimization algorithm based on Alternating Direction Method of Multipliers (ADMM), which is a classical method for sequentially decomposing optimization problems with coupled constraints. We show that this algorithm converges at the rate O (1/k).

关键词： Multiplying circuits Objective function Distribute optimization methods optimization algorithms iterative methods Agents optimization method NETWORKING AGENT UNCONSTRAINED OPTIMISATION