检索结果-内蒙古大学图书馆

32nd Mediterranean conference on control and Automation, MED 2024

作者： Said, Anwar Ahmad, Obaid Ullah Abbas, Waseem Shabbir, Mudassir Koutsoukos, Xenofon Vanderbilt University Computer Science Department NashvilleTN United States University of Texas at Dallas Electrical Engineering Department RichardsonTX75080 United States University of Texas at Dallas Systems Engineering Department RichardsonTX United States Information Technology University Computer Science Department Lahore Pakistan

ISBN: (纸本)9798350395440

network control theory (NCT) offers a robust analytical framework for understanding the influence of network topology on dynamic behaviors, enabling researchers to decipher how certain patterns of external control measures can steer system dynamics towards desired states. Distinguished from other structure-function methodologies, NCT's predictive capabilities can be coupled with deploying Graph Neural networks (GNNs), which have demonstrated exceptional utility in various network-based learning tasks. However, the performance of G NN s heavily relies on the expressiveness of node features, and the lack of node features can greatly degrade their performance. Furthermore, many real-world systems may lack node-level information, posing a challenge for GNNs. To tackle this challenge, we introduce a novel approach, NCT-based Enhanced Feature Augmentation (NCT-EFA), that assimilates average controllability, along with other centrality indices, into the feature augmentation pipeline to enhance GNNs performance. Our evaluation of NCT-EFA, on six benchmark GNN models across two experimental setting-solely employing average controllability and in combination with additional centrality metrics-showcases an improved performance reaching as high as 11 %. Our results demonstrate that incorporating NCT into feature enrichment can substantively extend the applicability and heighten the performance of GNNs in scenarios where node-level information is unavailable. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Concept of a data centralization system for a railway transportation and station management systems 28

Concept of a data centralization system for a railway transp...

引用

28th International conference on Methods and Models in Automation and Robotics (MMAR)

作者： Bauer, Waldemar Grobler-Debska, Katarzyna Woiniak, Wlodzimierz AGH Univ Sci & Technol Dept Automat Control & Robot Krakow Poland Poznan Inst Technol Lukasiewicz Res Network Poznan Poland

ISBN: (纸本)9798350362350;9798350362343

This paper advocates for the digitization of transportation enterprises, focusing on the railway industry's need for integrated ticketing and asset management systems. It introduces Data Lake technology as a solution for centralized data management, enabling railway companies to enhance operational efficiency and improve decision-making processes. By integrating diverse data sources within the Data Lake framework, the paper demonstrates the potential for achieving holistic insights and predictive analytics to optimize railway operations. Practical implementation of Data Lake in the MOTIONAL project exemplifies its efficacy in real-world applications, underscoring its pivotal role in modernizing railway transportation and station management systems.

关键词： Transportation digitization Data Lake technology Railway operations optimization Asset management

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Reinforcement Learning for Multi-objective SFC Deployment 21

Evolutionary Reinforcement Learning for Multi-objective SFC ...

引用

21st IEEE International conference on Mobile Ad-Hoc and Smart systems (MASS)

作者： Zhao, Jialiang Wang, Ran Wu, Qiang Hao, Jie Xiong, Zehui Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 211106 Peoples R China Singapore Univ Technol & Design Singapore 487372 Singapore

ISBN: (纸本)9798350363999;9798350364002

In the 5G era, the diversification of application scenarios and the expansion of service demands necessitate a paradigm shift in mobile communication development to ensure Quality of Service (QoS) for a multitude of network services, thereby enhancing user experience and optimizing network resource management. To address this, we extend the traditional single-objective optimization model of Service Function Chains (SFC) to a multi-objective optimization model, incorporating considerations such as latency, deployment cost, and throughput. However, traditional evolutionary computation struggles to optimize multiple objectives simultaneously without considering initial population quality, while Deep Reinforcement Learning (DRL) faces challenges in determining weights between multiple objectives, requiring repeated training and optimization. In this paper, we propose a two-stage solution multi-objective evolutionary reinforcement learning (MOERL) to deploy SFC. In the first stage, DRL can effectively generate excellent initial population solutions, while in the second stage, using this solution as the initial solution for NSGA-ii can obtain the required placement solution and reduce computational time. Extensive experiments demonstrate that MOERL significantly reduces computational time, with its efficacy increasing as the initial population size grows. Furthermore, MOERL exhibits superior performance across three objective functions under varying request numbers, outperforming DRL by 20.9% and NSGA-ii by 38.2% in computational time reduction. Thus, MOERL adeptly meets the rigorous resource and real-time demands within 5G network environments.

关键词： network Function Virtualization Service Function Chain Multi-Objective Optimization MOERL

来源：评论

学校读者我要写书评

暂无评论

performance analysis and multi-objective optimization of a rotating triple-tube latent heat thermal energy storage unit with V-fin

引用

APPLIED THERMAL ENGINEERING 2025年 264卷

作者： Li, Baofeng Yang, Xinle Yu, Ning Bu, Shujuan Zhang, Shuaibo Dai, Wenzhi Wang, Xin Suo, Shaoyi Liu, Jia Jiang, Linsong Liaoning Tech Univ Sch Mech Engn Fuxin 123000 Peoples R China Liaoning Prov Key Lab Heavy Min Equipment Fuxin 123000 Peoples R China Liaoning Tech Univ Sch Elect & Control Engn Huludao 125105 Peoples R China

Phase change heat storage technology faces challenges such as slow heat transfer rates and uneven melting, limiting its performance. Introducing active rotation can effectively enhance the heat storage rate in phase change systems. This study presents a novel triplex-tube latent heat storage unit with a rotating middle tube and coupled V-fin to improve heat transfer efficiency through active rotation. The main goal is to investigate the effects of the rotating wall and structural parameters on system performance. The relationship between structural parameters and performance is fitted using the MEA-BP neural network, followed by optimization with the NSGA-ii algorithm. The results show that rotating the wall at 2 rps reduces melting time by 66.32 %, with a slight decrease in heat absorption by 3.72 %, indicating significant improvements in heat transfer efficiency and uneven heat distribution. Further analysis shows that increasing fin length from 20 mm to 32 mm reduces melting time by 30.86 %, and the optimal fin angle of 20 degrees achieves the shortest melting time of 24.8 min. A five-fin configuration results in the most uniform melting, while an 8 mm eccentricity reduces melting time by 5.86 % compared to the central model. Higher wall temperatures (367.15 K) improve melting efficiency. Multi- objective optimization determined the better fin parameters (length of 28.53 mm, angle of 15 degrees, and eccentricity of 9.33 mm), resulting in a 44.75 % reduction in melting time and a 2.29 % increase in heat absorption. This study provides new insights into the application and optimization of rotational mechanisms in phase change storage systems.

关键词： Thermal energy storage Rotational mechanism Numerical simulation Melting performance Multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

A Packet Delay Emulator for High-Bandwidth and Low-Latency Traffic in 5G networks

A Packet Delay Emulator for High-Bandwidth and Low-Latency T...

引用

IEEE conference on Global Communications (IEEE GLOBECOM) - Intelligent Communications for Shared Prosperity

作者： Bolla, Raffaele Bruschi, Roberto Davoli, Franco Lombardo, Chiara Mohammadpour, Alireza Rabbani, Ramin CNIT S2N Natl Lab Genoa Italy DITEN Univ Genoa Genoa Italy

ISBN: (纸本)9798350310900

A Packet delay emulator for high bandwidth traffic is a specialized tool designed to simulate network delays and measure the impact on high-speed data transmission. Simulating network delays and measuring the impact on data transmission allows network administrators and developers to test their systems in a controlled environment, mimicking real-world scenarios with different network conditions. This paper discusses the limitations of traditional packet latency emulators and the technical con-siderations required to test high-speed networks, and proposes a specialized packet latency emulator to replicate real-world network conditions. Results compare the proposed emulator with the best tools that are currently available and show a performance in line with the reference, with a significant accuracy improvement in the presence of higher latencies. © 2023 IEEE.

关键词： 5G networks Packet delay emulation network performance testing

来源：评论

学校读者我要写书评

暂无评论

performance Analysis of MPPT Tracking Algorithm Based on Artificial Neural network for a PV Pumping System 4

Performance Analysis of MPPT Tracking Algorithm Based on Art...

引用

4th International conference on Innovative Research in Applied Science, Engineering and Technology, IRASET 2024

作者： Ghizlane, Chbirik Byar, Mohcine Abdenabi, Brahmi Abdelouahed, Abounada University Of Sultan Moulay Sliman Laboratory Of Automatic And Energy Conversion Faculty Of Sciences And Technology Electrical Engineering Department Béni Mellal Morocco

ISBN: (纸本)9798350309508

The field of integrating renewable energies into elec-trical systems is increasingly vital, with photovoltaic technology playing a pivotal role, especially in irrigation research. This significance is attributed to the competitive cost of photovoltaic (PV) pumping systems in comparison to those reliant on fossil fuels. PV power generation systems frequently employ step-up converters to amplify the output voltage of solar panels, thereby achieving an optimal power operation point. The effective functioning of these converters hinges on a high-performance control algorithm. This study aims to conduct a comparative analysis of two maximum power point tracking (MPPT) controls: the Perturb and Observe (P and O) algorithm and the neural network (ANN) algorithm. The comparison seeks to ascertain which algorithm enhances control efficiency in PV systems, with particular emphasis on their application in irrigation. Simulation results prove that PV pumping system based on neural network MPPT control exhibits a quicker response time in reaching the maximum power compared to the P and O-controlled system. Furthermore, the P and O controlled system shows oscillations around Vmpp, which minimises system efficiency. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Power WLAN Security: Strengthening Comprehensive Strategies for Trustworthy and Zero-Trust Authentication 24

Power WLAN Security: Strengthening Comprehensive Strategies ...

引用

2nd International conference on Artificial Intelligence, systems and network Security, AISNS 2024

作者： Zhao, Xiaohong Chen, Hao Zhang, Qiang Guan, Ti Yuan, Chao Technology Information Center State Grid Shandong Electric Power Research Institute Shandong Jinan China Power dispatch control center State Grid Shandong Electric Power Company Shandong Jinan China

ISBN: (纸本)9798400711237

Power communication networks are crucial for the safe and stable operation of power systems, supporting both real-time and non-real-time services. This paper introduces Software Defined network (SDN) technology into power communication networks to meet demands for real-time performance, high efficiency, and security. SDN networks enable dynamic traffic optimization, achieving high bandwidth and low latency while offering flexibility and redundancy. However, the centralized nature of SDN controllers presents security challenges. To address these, this paper proposes zero-trust security policies and endpoint hardening measures. In the SDN-based power WLAN architecture, the SDN controller handles network management and control. The zero-trust model enhances security by enforcing strict authentication and authorization, reducing reliance on a centralized controller. Additionally, incorporating the WAPI (Wireless LAN Security Mandatory Standard) improves WiFi network security. To address WAPI’s inherent security flaws, a dynamic (R, N) threshold method for key storage is proposed, enhancing its applicability and security. Simulations verify the scheme’s performance, showing improved connection security and efficiency. The comprehensive security strategy strengthens the security performance of power communication networks, ensuring safe and stable power system operations. By integrating SDN technology, zero-trust authentication, and the WAPI standard, the network’s real-time performance, efficiency, and security are significantly enhanced. © 2024 Copyright held by the owner/author(s).

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Targeted Output Driven Dataset Generation Methodology for Training Neural network controllers in Specific nth Order systems 50

Targeted Output Driven Dataset Generation Methodology for Tr...

引用

50th Annual conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Kumar, Aman Hari Teja, A.V. Ravi Department of Electrical Engineering Indian Institute of Technology Ropar Punjab India

ISBN: (纸本)9781665464543

The performance of a neural network controller majorly depends on the dataset used for training. Traditionally, Proportional-Integral (PI) controller data is used to train a neural network. In this scenario, the performance of the neural controller is limited by the performance of the PI. Similarly, any other controller data, when used, restricts the neural controller’s performance within its limitations. In this paper, a targeted output-driven dataset that theoretically gives the best desirable response is derived and used for training the neural controllers. Therefore, enhanced performance could be achieved that is better than that of traditional PI controllers. Detailed theoretical derivations are provided for obtaining the proposed dataset generation methodology for any nth order system without zeros. The viability of the proposed neural controller was simulated and trained in a MATLAB/Simulink environment, and its response to variation in reference input has been inferred. The performance comparisons are made with the PI controller data and presented. © 2024 IEEE.

关键词： Closed loop control systems

来源：评论

学校读者我要写书评

暂无评论

Faults and Attacks Collaborative Detection for Cyber-Physical systems with Mixed network Attacks 43

Faults and Attacks Collaborative Detection for Cyber-Physica...

引用

43rd Chinese control conference, CCC 2024

作者： Li, Geng Wang, Yang Min, Zhaoyi Zhang, Duanjin Zhengzhou University School of Electrical and Information Engineering 450001 China

ISBN: (纸本)9789887581581

This article investigates the collaborative detection of attacks and faults in Cyber-Physical systems (CPSs) under the scenario of dual-channel network attacks and replay attacks on sensors within the system. Considering the simultaneous existence of time-varying delays and communication constraints in the system, a discretization method based on the delta operator was adopted to construct a discrete-time model that considers the coexistence of mixed network attacks and faults. By constructing two observer-based detection filters, one filter is sensitive to fault signals and the other is sensitive to attack signals. In the case of concurrent faults and attacks, attack and fault signals are detected separately with dynamic thresholds to make the detection results more reliable. Sufficient conditions for ensuring asymptotic stability and H∞ performance of the system are derived using Lyapunov-Krasovaskii functionals and linear matrix inequalities. Through simulation and performance analysis on an angle positioning system, it has been proven that this method can quickly and effectively detect faults and attacks when the system is simultaneously attacked and malfunctioned. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Energy Optimization for Building Energy Management with Thermal Storage: A Multi-Agent Deep Reinforcement Learning Approach 43

Energy Optimization for Building Energy Management with Ther...

引用

43rd Chinese control conference (CCC)

作者： Zhu, Shifeng Lu, Wei Feng, Yi Sun, Changhai Dalian Univ Technol Sch Control Sci & Engn Dalian 116024 Peoples R China Dalian Univ Technol Coll Elect Engn Dalian 116024 Peoples R China

ISBN: (纸本)9798350366907;9789887581581

Building Energy Management (BEM) with Thermal Energy Storage (TES) poses significant challenges due to the intricate coordination required among components such as Power-to-Heat (P2H) converters, TES units, and zone temperature controllers. In this paper, we propose a novel multi-agent Deep Reinforcement Learning (DRL) method for BEM, capable of optimizing the energy efficiency and flexibility of Building Energy systems (BESs) integrated with TES without requiring manual efforts to set up a control-oriented model. Our method-distributed optimized NNPC via DRL-consists of two parts: i) a Neural network Predictive control (NNPC) for zone temperature regulation, leveraging an attention-based artificial neural network for forecasting operational conditions and a Dynamic Programming (DP) algorithm to jointly optimize both comfort levels and energy efficiency;and ii) a distributed optimization strategy realized through a coordinating policy that facilitates the collaboration between conventional on/off and NNPC agents/controllers. The efficacy of our method is confirmed through simulations established based on a real-world BES that integrates a TES unit. We compare our method with three alternatives: a conventional on/off control, an optimized on/off control, and an optimized Naive NNPC, with the latter two also incorporating our distributed optimization strategy. Specifically, our method realizes approximately 7% reduction in energy consumption compared to the conventional on-off method while maintaining equivalent comfort levels. Furthermore, it attains parity with the performance of the optimized Naive NNPC without requiring manual tuning, thereby illustrating its adaptability and ease of implementation. Collectively, these findings underscore our method's superiority across metrics of energy efficiency, comfort and applicability, demonstrating the profound potential of DRL in BEM, particularly when TES is involved.

关键词： Building Energy Management Thermal Energy Storage Operational Optimization Deep Reinforcement Learning Neural network Predictive control

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：