检索结果-内蒙古大学图书馆

Distributed Optimization for Quadratic Cost Functions With Quantized Communication and Finite-Time Convergence

ieee TRANSACTIONS ON control OF NETWORK systems 2025年第1期12卷 930-942页

作者： Rikos, Apostolos I. Grammenos, Andreas Kalyvianaki, Evangelia Hadjicostis, Christoforos N. Charalambous, Themistoklis Johansson, Karl H. KTH Royal Inst Technol Div Decis & Control Syst S-11428 Stockholm Sweden Digital Futures S-11428 Stockholm Sweden Univ Cambridge Dept Comp Sci & Technol Cambridge CB3 0FD England Alan Turing Inst London NW1 2DB England Univ Cyprus Sch Engn Dept Elect & Comp Engn CY-1678 Nicosia Cyprus Aalto Univ Sch Elect Engn Dept Elect Engn & Automat Espoo 02150 Finland

In this article, we propose two distributed iterative algorithms that can be used to solve the distributed optimization problem for quadratic local cost functions over large-scale networks in finite time. The first algorithm exhibits synchronous operation while the second one exhibits asynchronous operation. Both algorithms operate exclusively with quantized values. This means that the information stored, processed, and exchanged between neighboring nodes is subject to deterministic uniform quantization. The algorithms rely on event-driven updates in order to reduce energy consumption, communication bandwidth, network congestion, and/or processor usage. Finally, once the algorithms converge, nodes distributively terminate their operation. We prove that our algorithms converge in a finite number of iterations to the exact optimal solution depending on the quantization level, and we present applications of our algorithms to, first, optimal task scheduling for data centers, and second, global model aggregation for distributed federated learning. We provide simulations of these applications to illustrate the operation, performance, and advantages of the proposed algorithms. In addition, it is shown that our proposed algorithms compare favorably to algorithms in the current literature.

关键词： Convergence Quantization (signal) Stochastic processes Task analysis Machine learning algorithms Cost function control systems Distributed algorithms federated learning finite-time optimization quantization resource allocation

来源：评论

学校读者我要写书评

暂无评论

On the Applicability of Reinforcement learning in the Traffic Flow control Problem

On the Applicability of Reinforcement Learning in the Traffi...

引用

2025 systems of Signals Generating and Processing in the Field of on Board Communications, SOSG 2025

作者： Gorodnichev, Mikhail Moscow Technical University of Communications and Informatics Moscow Russia

ISBN: (纸本)9798331532635

This article presents the development of a traffic flow regulation method based on an adaptive approach that accounts for changing characteristics of traffic conditions. The study explores key reinforcement learning techniques utilizing Q-learning to enhance traffic management. Simulations of traffic flow control were conducted in the SUMO simulation environment, focusing on cyclic switching methods. The article outlines the implementation of an environment management strategy and the application of reinforcement learning algorithms via the SUMO API. Two reinforcement learning techniques were selected for traffic flow regulation, and extensive training was conducted with various hyperparameters to identify optimal configurations. A comparative analysis of traditional cyclic switching methods and data-driven approaches is provided, highlighting the potential advantages of adaptive methods for improving traffic efficiency and safety in urban environments. The findings suggest that reinforcement learning can significantly enhance traffic management systems in real-time applications. © 2025 ieee.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Novel data-driven Method of Real-Time Transient Stability Assessment for AC/DC Hybrid Power systems

引用

ieee Access 2025年 13卷 80748-80758页

作者： Li, Haifeng Wang, Zhiwei Jin, Tao Xu, Xian Shi, Lin State Grid Jiangsu Electric Power Company Ltd. Jiangsu Nanjing324000 China

To effectively tackle the operational challenges facing today’s bulk power systems with growing uncertainties, this paper presents a novel data-driven method for transient stability assessment method of the AC/DC hybrid power systems using auto-encoder-based algorithms for feature extraction and convolutional deep belief networks and Boltzmann machines for training accurate and robust models. First, a feature set is established from power grid operational states, and a stack-based noise reduction automatic encoder (SDAE) is used to extract key features that significantly affect the transient stability of the system. Next, transient stability assessment models are trained based on attention mechanisms, improved convolutional deep belief networks (CDBN), and multiple convolution-constrained Boltzmann machines to learn effective features from the input data adaptively. With such a design, the attention mechanism improves the model’s attention to instability samples, and the high-precision assessment of the systems’ transient stability is achieved. The experimental results conducted on the New England 39-bus system and the WECC 179-bus system show that the proposed method can accurately assess the transient stability of the system with multi-infeed DC by outperforming traditional supervised learning models considering various noise levels. © 2013 ieee.

关键词： Transient stability

来源：评论

学校读者我要写书评

暂无评论

An Uncertainty Involved Two-Stage Energy Optimization Framework Based on Deep Reinforcement learning for Steel Enterprise

引用

ieee TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2025年

作者： Wang, Zhiyuan Han, Zhongyang Zhao, Jun Wang, Wei Dalian Univ Technol Sch Control Sci & Engn Dalian 116023 Peoples R China

The optimization of energy systems within the steel industry faces challenges due to the complexity of nonconvex models as well as supply and demand uncertainty. To address these issues, a novel two-stage data-driven deep reinforcement learning (DRL) framework is proposed in this study. The first stage is focused on offline learning, where probability distribution of energy media is incorporated into Augmented Lagrangian based Alternating Direction Inexact Newton method (ALADIN) for solving nonconvex problems. Some key physics-related constraints, such as gas transmission and steam heat conduction, are comprehensively integrated. Then in order to ensure the independence of various energy media and to reduce the dimensionality of the solution process, the iterative process of updating consensus variables in ALADIN is regarded as a Markov Decision Process (MDP). An optimal decision-making method based on Soft Actor-Critic (SAC) algorithm is established for the energy system. The second stage is targeted at online guidance, where a fuzzy c-means clustering based algorithm is designed for real-time energy optimization. Through the continuous interaction and collaboration between the two-stage framework, the potential disruptions caused by uncertain factors in energy supply and demand on the stable control and operation of steel plants have been effectively hedged. Experiments using data from a steel enterprise in China are conducted, where the proposed framework is compared with both commonly deployed and state-of-the-art methods. The results demonstrate the significant advantages in terms of scheduling efficiency, cost-effectiveness, as well as the adaptability to the uncertainties of the industrial environment, compared with other existing state-of-the-art methods.

关键词： Optimization Mathematical models Uncertainty Steel Biological system modeling Pipelines Media Costs Job shop scheduling Heuristic algorithms Deep reinforcement learning (DRL) energy system steel industry uncertainty

来源：评论

学校读者我要写书评

暂无评论

Finite-Time learning-Based Optimal Elliptical Encircling control for UAVs With Prescribed Constraints

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2025年第5期26卷 7065-7080页

作者： Shao, Xingling Zhang, Fei Liu, Jun Zhang, Qingzhen North Univ China Sch Elect & Control Engn Taiyuan 030051 Peoples R China Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China North Univ China Sch Instrument & Elect Taiyuan 030051 Peoples R China Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China

This paper addresses an optimal elliptical enclosing problem of Unmanned Aerial Vehicles (UAVs) under prescribed constraints, whose objective is to steer UAVs to fulfill accurate target encirclement while complying with arriving time restrictions and minimum efforts. A novel learning-based approximate optimal control policy including two-stage designs is presented. At the first stage, a steady-state robust control protocol is developed to steer UAVs to precisely travel along a predefined elliptical path based on concise filtering. At the second stage, to address specified-time constraints and gain the online optimization ability, a single-critic based enhanced learning rule is explored to generate an approximate optimal regulator that stabilizes error dynamics and minimizes value functions, wherein specified-time constraints can be handled by encoding inequality conditions as skilled barrier functions, and by making full use of historical data and current information, a finite-time learning mechanism driven by weight errors rather than Bellman errors is proposed to approximate the solution of Hamilton-Jacobi-Bellman (HJB) equation with faster decaying. The distinct merit is that an improved reinforcement learning (RL) paradigm is formulated to prescribe an elliptical circumnavigation with assured time requirements and optimization behaviors, which can greatly outperform non-RL alternatives in maintaining the optimal performance index while exhibiting restriction handling ability via online learning. Lyapunov stability demonstrates that involved error variables are ultimately limited and resultant controller obeys optimality. The feasibility and values of presented algorithm are accessed by comparisons and simulations.

关键词： Optimal control Autonomous aerial vehicles Artificial neural networks Costs Vehicle dynamics Time factors Steady-state Robust control Perturbation methods Constraint handling Optimal elliptical encircling prescribed constraints finite-time learning performance optimization UAVs

来源：评论

学校读者我要写书评

暂无评论

learning control Affine Neural NARX Models for Internal Model control Design

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 8137-8149页

作者： Xie, Jing Bonassi, Fabio Scattolini, Riccardo Politecn Milan Dipartimento Elettron Informaz & Bioingn I-20156 Milan Italy Uppsala Univ Dept Informat Technol S-75105 Uppsala Sweden

This paper explores the use of control Affine Neural Nonlinear AutoRegressive eXogenous (CA-NNARX) models for nonlinear system identification and model-based control design. The idea behind this architecture is to match the known control-affine structure of the system to achieve improved performance. Coherently with recent literature of neural networks for data-driven control, we first analyze the stability properties of CA-NNARX models, devising sufficient conditions for their incremental Input-to-State Stability ( $\delta$ ISS) that can be enforced at the model training stage. The model's stability property is then leveraged to design a stable Internal Model control (IMC) architecture. The proposed control scheme is tested on a real Quadruple Tank benchmark system to address the output reference tracking problem. The results achieved show that (i) the modeling accuracy of CA-NNARX is superior to the one of a standard NNARX model for given weight size and training epochs, (ii) the proposed IMC law provides performance comparable to the ones of a standard Model Predictive controller (MPC) at a significantly lower computational burden, and (iii) the delta ISS of the model is beneficial to the closed-loop performance. Note to Practitioners-Many engineering systems, such as robotic manipulators and chemical reactors, are described by control Affine (CA) models, characterized by onlinear dynamics where the control variable enters in a linear way. If only this structural information is available without any additional knowledge, for instance on the order of the system or on the value of its parameters, a black-box identification approach can be followed to estimate the model from data. For these reasons, in this paper we propose a modeling and control design method suited for this class of systems. Specifically, we assume that the system is described by a CA-Neural Nonlinear AutoRegressive eXogenous (CA-NNARX) model. Then, the estimated model is used to design a stable I

关键词： control affine neural networks internal model control model predictive control control affine neural networks internal model control model predictive control

来源：评论

学校读者我要写书评

暂无评论

Effective Analysis of Machine and Deep learning Methods for Diagnosing Mental Health Using Social Media Conversations

引用

ieee TRANSACTIONS ON COMPUTATIONAL SOCIAL systems 2025年第1期12卷 274-294页

作者： Kasanneni, Yashwanth Duggal, Achyut Sathyaraj, R. Raja, S. P. Vellore Inst Technol Sch Comp Sci & Engn SCOPE Vellore 632014 India

The increasing incidence of mental health issues demands innovative diagnostic methods, especially within digital communication. Traditional assessments are challenged by the sheer volume of data and the nuanced language found on social media and other text-based platforms. This study seeks to apply machine learning (ML) to interpret these digital narratives and identify patterns that signal mental health conditions. We apply natural language processing (NLP) techniques to analyze sentiments and emotional cues across datasets from social media and other text-based communication. Using ML, deep learning, and transfer learning models such as bidirectional encoder representations (BERTs), robustly optimized BERT approach (RoBERTa), distilled BERT (DistilBERT), and generalized autoregressive pretraining for language understanding (XLNet), we assess their ability to detect early signs of mental health concerns. The results show that BERT, RoBERTa, and XLNet consistently achieve over 95% accuracy, highlighting their strong contextual understanding and effectiveness in this application. The significance of this research lies in its potential to revolutionize mental health diagnostics by providing a scalable, data-driven approach to early detection. By harnessing the power of advanced NLP models, this study offers a pathway to more timely and accurate identification of individuals in need of mental health support, thereby contributing to better outcomes in public health.

关键词： Mental health Accuracy Social networking (online) Analytical models Computational modeling Linguistics Encoding data models Bidirectional control Natural language processing Bidirectional encoder representation (BERT) deep learning (DL) distilled BERT (DistilBERT) generalized autoregressive pretraining for language understanding (XLNet) machine learning (ML) mental health prediction natural language processing (NLP) robustly optimized BERT approach (RoBERTa) social media analytics transfer learning

来源：评论

学校读者我要写书评

暂无评论

Decision Making for Multi-Robot Fixture Planning Using Multi-Agent Reinforcement learning

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 5578-5589页

作者： Canzini, Ethan Auledas-Noguera, Marc Pope, Simon Tiwari, Ashutosh Univ Sheffield Dept Automat Control & Syst Engn Sheffield S10 2TN England Airbus Robot Broughton CH4 0DR England

Within the realm of flexible manufacturing, fixture layout planning allows manufacturers to rapidly deploy optimal fixturing plans that can reduce surface deformation that leads to crack propagation in components during manufacturing tasks. The role of fixture layout planning has evolved from being performed by experienced engineers to computational methods due to the number of possible configurations for components. Current optimisation methods commonly fall into sub-optimal positions due to the existence of local optima, with data-driven machine learning techniques relying on costly to collect labelled training data. In this paper, we present a framework for multi-agent reinforcement learning with team decision theory to find optimal fixturing plans for manufacturing tasks. We demonstrate our approach on two representative aerospace components with complex geometries across a set of drilling tasks, illustrating the capabilities of our method;we will compare this against state of the art methods to showcase our method's improvement at finding optimal fixturing plans with 3 times the improvement in deformation control within tolerance bounds.

关键词： Fixtures Planning Task analysis Manufacturing Reinforcement learning Robots Layout Multi-agent systems reinforcement learning aerospace manufacturing fixture planning robotic fixturing

来源：评论

学校读者我要写书评

暂无评论

data-driven Decision-Making for SCUC: An Improved Deep learning Approach Based on Sample Coding and Seq2Seq Technique

引用

PROTECTION AND control OF MODERN POWER systems 2025年第2期10卷 13-24页

作者： Yang, Nan Hao, Juncong Li, Zhengmao Ye, Di Xing, Chao Zhang, Zhi Wang, Can Huang, Yuehua Zhang, Lei China Three Gorges Univ Coll Elect Engn & New Energy Yichang 443002 Peoples R China Aalto Univ Sch Elect Engn Espoo 02150 Finland State Grid Fujian Elect Power Co Ltd Fuzhou Power Supply Co Fuzhou 350009 Peoples R China Yunnan Power Grid Co Ltd Elect Power Res Inst Kunming 650217 Yunnan Peoples R China State Grid Corp China Beijing 100031 Peoples R China

The electricity industry has witnessed increasing challenges in power system operation and rapid developments of artificial intelligence technologies in the last decades. In this context, studying the approach of security-constrained unit commitment (SCUC) decision-making with high adaptability and precision is of great importance. This paper proposes an improved data-driven deep learning (DL) approach, following the sample coding and Sequence to Sequence (Seq2Seq) technique. First, an encoding and decoding strategy is utilized for high-dimensional sample matrix dimension compression. A DL SCUC decision model based on a Seq2Seq network with gated recurrent units as neurons is then constructed, and the mapping between load and unit on/off scheme is established through massive data from historical scheduling. Numerical simulation results based on the ieee 118-bus test system demonstrate the correctness and effectiveness of the proposed approach.

关键词： data-driven gated recurrent unit sam- ple coding sam- ple coding Sequence to Sequence Sequence to Sequence

来源：评论

学校读者我要写书评

暂无评论

MDFF: A Multilevel Deep Fusion Framework of Multisource Heterogeneous data for FeO Content Prediction in Sintering Process

引用

ieee TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Wei, Shiyi Ye, Chenxin Zhao, Yuchen Zhang, Xinmin Song, Zhihuan Zhejiang Univ Coll Control Sci & Engn State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China

As the key quality indicator in the iron ore sintering process, the ferrous oxide (FeO) content in the finished sinter directly reflects its thermal state and denotes sintering quality. Currently, data-driven soft sensor modeling technology has become the mainstream method for predicting this quality indicator. However, existing approaches either fail to leverage the multimodal properties of the sintering dataset or simply neglect to explore the interrelationships between multisource heterogeneous data, thus limiting the improvement of prediction accuracy. To address this issue, we propose a multilevel deep fusion framework (MDFF) for real-time FeO content detection, which combines data fusion, feature fusion, and decision fusion methods together to form an end-to-end framework for soft sensor modeling. First, shallow features are extracted from cross section images based on expert knowledge for data-level fusion. Then, two multiscale encoding networks and a shared representation learning network are employed to realize feature-level fusion. Subsequently, the final predicted FeO content is obtained by fusing the prediction results of shared representations and modality-specific features at the decision level. By integrating multisource data and designing multilevel information fusion, the proposed MDFF method can make full exploitation of the intrinsic interactions among multisource information at various levels. The experimental results of the actual sintering process show that MDFF is superior to the existing models in terms of prediction accuracy and stability.

关键词： Sintering Feature extraction Soft sensors Predictive models data models Accuracy data mining Real-time systems Production Numerical models Deep learning end-to-end modeling ferrous oxide (FeO) content prediction iron ore sintering multisource data fusion soft sensing

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：