检索结果-内蒙古大学图书馆

2023 IEEE conference on control Technology and Applications, CCTA 2023

作者： Nielsen, Logan B. Warnick, Sean Condie, Scott S. Brigham Young University Department of Computer Science Provo United States Brigham Young University Department of Economics Provo United States

ISBN: (纸本)9798350335446

High-Frequency Trading (HFT) algorithms are automated feedback systems that interact with markets to maximize investment returns. These systems can process varying resolutions of market information at any given time, with Level I information providing basic equity data - primarily its price - and Level ii information offering the complete order book for that equity at a specific moment. This paper presents a study on the application of Recurrent Neural network (RNN) models to predict the spread of the DOW Industrial 30 index traded on NASDAQ, using both Level I and Level ii data as *** results suggest that the use of raw Level ii data, without preprocessing, does not enhance spread prediction. This finding implies that HFT algorithms should not directly utilize raw Level ii information;instead, computational resources should be allocated towards transforming Level ii data into a less noisy signal if it is to improve trading performance. Alternatively, when computational resources are limited, HFT algorithms may benefit from omitting Level ii data. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A TSN-based Technique for Real-Time Latency Evaluation in Communication networks

A TSN-based Technique for Real-Time Latency Evaluation in Co...

引用

IEEE International Instrumentation and Measurement Technology conference (I2MTC)

作者： Morato, Alberto Zunino, Claudio Cheminod, Manuel Vitturi, Stefano Tramarin, Federico Natl Res Council Italy CNR IEIIT Turin Italy Univ Modena & Reggio Emilia Dept Engn Enzo Ferrari Modena Italy

ISBN: (纸本)9798350380903;9798350380910

Real-time networks and Software-Defined networking (SDN) play pivotal roles in contemporary communication systems, supporting applications such as video conferencing, online gaming, VoIP calls, virtual reality (VR) systems, and Industry 4.0 automation. These applications necessitate low and predictable latency for real-time interactivity, responsiveness, and uninterrupted performance. Achieving low and predictable latency in dynamic network environments is challenging, as factors like changing network topology, traffic load, and connected devices impact latency. Furthermore, network protocols and devices introduce additional delays. SDN provides a solution by allowing dynamic control of communication paths, enhancing the performance of time-sensitive applications. This paper addresses the crucial task of evaluating latency in real-time networks. We propose a novel measurement methodology that effortlessly evaluates latency by utilizing Time-Sensitive networking (TSN) features and tools embedded in the Linux kernel. Our methodology accurately captures network latency irrespective of workload, configuration, and computational capabilities.

关键词： Real-time networks Software-Defined networking (SDN) Low Latency Time-Sensitive networking (TSN) Dynamic network Environments Latency Measurement Methodology

来源：评论

学校读者我要写书评

暂无评论

Submarine Cable Target Search Based on Improved Biological Neural network 20th

Submarine Cable Target Search Based on Improved Biological N...

引用

20th Chinese Intelligent systems conference

作者： Liu Zhenghua Jiao Huifeng Zhao Chuncheng Ai Yuhao Tan Rui Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China China Ship Sci Res Ctr State Key Lab Deep Sea Manned Vehicles Wuxi 214082 Jiangsu Peoples R China AECC Hunan Aviat Powerplant Res Inst Zhuzhou 412000 Peoples R China

ISBN: (纸本)9789819786565;9789819786541;9789819786534

In this study, we propose an innovative control algorithm leveraging an improved biological neural network for submarine cable target search tasks. This algorithm models the seafloor as a grid map, utilizing the neural network for simulation. Then a collaborative mechanism is designed to control the cooperative detection of multiple AUVs, which is able to avoid obstacles and cover the whole area to find the mission target, effectively improving the mission efficiency. The simulation results show that the proposed algorithm is able to search the submarine mission area with the presence of cables quickly and efficiently. The robustness and effectiveness of the cooperative mechanism are also verified, which can provide support for subsequent missions such as target striking.

关键词： submarine cable coverage path planning GBNN

来源：评论

学校读者我要写书评

暂无评论

ADSeq-5GCN: Anomaly Detection from network Traffic Sequences in 5G Core network control Plane 24

ADSeq-5GCN: Anomaly Detection from Network Traffic Sequences...

引用

IEEE 24th International conference on High performance Switching and Routing, (HPSR)

作者： Tian, Zixu Patil, Rajendra Gurusamy, Mohan McCloud, Joshua Natl Univ Singapore Singapore Singapore Cisco Syst Singapore Singapore

ISBN: (纸本)9781665476409

The service-based architecture (SBA) of 5G Core (5GC) introduces significant landscape changes to the modern communication and network system, and the network slicing enables different network Functions (NFs) to meet diverse service requirements. However, with the broadening interface, some key NFs may become more vulnerable to internal hostile NFs or external malicious entities, which pose severe threats to the control-plane components in the 5GC network (5GCN). In this paper, we propose ADSeq-5GCN, a network-level anomaly detection framework based on modeling network traffic sequences. Our framework focuses on the control plane of 5GCN, where the network traffic is captured and analyzed for anomalies. We use a sequence model, Bidirectional Long Short Terms Memory (Bi-LSTM) networks, to learn normal NF-to-NF interactions and detect anomalies based on incorrect service event prediction. We evaluate our proposed framework on a 5GCN testbed with Free5GC and UERANSIM under various scenarios. Our results demonstrate the overwhelming performance of our proposed framework over the baseline models.

关键词： network Anomaly Detection 5G Core network,control Plane network Traffic Sequence Sequence Models

来源：评论

学校读者我要写书评

暂无评论

Variable Gain Based Predictive Output Tracking control of networked systems 14

Variable Gain Based Predictive Output Tracking Control of Ne...

引用

14th Asian control conference (ASCC)

作者： Pang, Yingying Liu, Zhenyi Guo, Haibin Zheng, Yong Pang, Zhonghua Gao, Shengnan North China Univ Technol Dept Automat Beijing 100144 Peoples R China North China Elect Power Univ Sch Control & Comp Engn Beijing 102206 Peoples R China

ISBN: (纸本)9798331540845;9789887581598

This paper addresses the output tracking problem of network control systems (NCSs) with random communication constraints, especially when the lower bound of the time delay induced by random communication constraints is relatively large. Firstly, the output tracking problem is converted into the stabilization problem of an augmented system. Then, a networked predictive output tracking control scheme with time-varying control gains is proposed to compensate for the impact of the communication constraints so as to complete the desired output tracking performance under the large time delays. And, a set of control gains are calculated for each different time delay, which improves the adaptability of NCSs to time delays. Next, a sufficient condition is derived to keep the system stability. Finally, the effectiveness of the proposed method is verified by numerical simulations.

关键词： networked control systems variable gain output tracking control networked predictive control

来源：评论

学校读者我要写书评

暂无评论

On Linear Envelopes Calculation for Traffic Flows in Industrial control systems

On Linear Envelopes Calculation for Traffic Flows in Industr...

引用

2024 International Russian Smart Industry conference, SmartIndustryCon 2024

作者： Baybulatov, Artur Lepekhin, Igor Promyslov, Vitaly V.A. Trapeznikov Institute of Control Sciences of Ras Laboratory of Distributed Information and Control Systems Moscow Russia Russian Federal Center - All-Russian Research Institute of Experimental Physics Yu. Ye. Sedakov Research Institute of Measuring Systems Nizhny Novgorod Russia

ISBN: (纸本)9798350395044

Nowadays, industrial control systems are falling squarely under the Industry 4.0 dominant trends and technological challengers. In this, the problems associated with data, their processing and analysis happen to be particularly serious. Among all data issues, data flows, most commonly called traffic flows, cause a deep concern since they are crucial for the correct real-time system functioning, and the knowledge of their characteristics is decisive for the assessment of critical time performance measures such as delays in alarm presentation and control action transmission. In order to explore industrial control system traffic flows and to calculate time performance measures, a theory of deterministic queuing systems network calculus is worth to be utilized. The article is devoted to industrial control system traffic flows and the network calculus application to them. In particular, the approaches to estimating envelopes for traffic flows are considered. The concept of envelopes on finite intervals is introduced, and their linear model is expounded. The advantages of linear envelopes on finite intervals over classical minimal envelope are revealed, and the algorithm for their online calculation is analyzed. The basic features of typical traffic flows encountered in upper-level control systems of nuclear power plants are outlined, and the results of the investigation of their deterministic envelopes as well as statistical indicators are presented. Conclusions are drawn about the legitimacy and practical acceptability of using linear envelopes on finite intervals in the applications of industrial control systems. © 2024 IEEE.

关键词： Nuclear power plants

来源：评论

学校读者我要写书评

暂无评论

Neural network controller for Drones

Neural Network Controller for Drones

引用

2024 IEEE International conference on Unmanned systems, ICUS 2024

作者： Cui, Lin Zhou, Jianshan Wang, Mingqian Xu, Zixuan Duan, Xuting Ren, Chenghao State Key Lab of ITS Beihang University Beijing China Zibo Vaucrefy Intel. Tech. Co. Ltd. Zibo China

ISBN: (纸本)9798350384185

Neural networks have gained prominence in control systems due to their ability to approximate complex nonlinear mappings and adapt to uncertain environments. The model predictive control (MPC) problem for a quadcopter is a complex one, rooted in the fact that the dynamics model of the quadcopter is inherently complex and requires a suitable controller. This study proposes a design for an MPC controller to land a quadcopter by training a neural network. It also integrates a linear dynamic model to achieve a smooth descent of the quadcopter. The loss function considers the impact of path planning, deviations from the target state, and operational costs. Experiments demonstrate the advantages of the constructed model by varying the number of hidden layers, and the results show that it achieves good control performance. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

RIS Assisted Millimeter Wave Communication with Imperfect CSI Based on DRL 9

RIS Assisted Millimeter Wave Communication with Imperfect CS...

引用

9th International conference on Computer and Communication systems (ICCCS)

作者： Liu, Jin Wang, Junxuan Zhang, Yanyan Xian Univ Posts & Telecommun Sch Commun & Informat Engn Xian Peoples R China

ISBN: (纸本)9798350350227;9798350350210

In order to improve the data rate received at the user's end,Reconfigurable Intelligent Surface (RIS),an artificial material that can control electromagnetic wave characteristics,can reshape the wireless channel. This allows it to be built in millimeter-wave non-line-of-sight links that are obscured by obstacles. This paper combines a long-short-term memory (LSTM) network with depth-deterministic policy gradient (DDPG),taking into account the fact that imperfect channel state information (CSI) can also result in a degradation of communication system performance. By using the LSTM neural network's memory function to control data delivery,the combined approach optimizes both the RIS reflective phase shift and the base station transmitting beam-forming matrix in an undesirable environment. The simulation findings demonstrate that,in comparison to the current deep reinforcement learning algorithms,the LSTM-DDPG algorithm can offer customers more stable and efficient data rates.

关键词： Reconfigurable Intelligent Surface imperfect CSI,LSTM network deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Parameter-Adaptive Distributed Model-Predictive control for Islanded AC Microgrids: Privacy-Preserving Perspective

引用

IEEE TRANSACTIONS ON SMART GRID 2024年第5期15卷 4424-4435页

作者： Wang, Ziqiang Zhou, Lidan Xiong, Linyun Yang, Haosen Wang, Jie Huang, Sunhua Shanghai Jiao Tong Univ Key Lab Control Power Transmiss & Convers Minist Educ Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Elect Engn Dept Shanghai 200240 Peoples R China Chongqing Univ Sch Elect Engn Chongqing 400044 Peoples R China Hong Kong Polytech Univ Dept Elect & Elect Engn Hong Kong Peoples R China

Information disclosure is a potential challenge in the practical implement of distributed algorithm and wireless communications on islanded AC microgrid (MG) for better flexibility and low cost. It can be solved by the initial-value-around and real-time-values privacy preservations against internal curious distributed generations (DGs) and external cyber attackers respectively. However, three problems should be solved before the existing information privacy-preserving mechanisms implemented on control level: (i) Encryption algorithm for real-time-values privacy will exacerbate the delay problem;(ii) When the delay problem is solved by the existing distributed model predictive controls, the decaying disturbance for initial-value-around privacy will impact the stability of islanded AC MG;(iii) The compromise problem between the privacy-preserving performance and transient performance of distributed model-predictive control (DMPC) is unacceptable. For the above problems, this paper proposes a parameter-adaptive DMPC (PA-DMPC), where two decaying functions are designed to adjust parameters in terminal constraints and optimal cost function for the third problem. The optimal control results are obtained by solving time-varying quadratic programming (QP) problem. The real-time simulation platform based on NI-PXI (National Instruments-PCI eXtensions for Instrumentation) and Wireless Local Area network (WLAN) is built to validate its effectiveness and advantages.

关键词： Encryption Delays Prediction algorithms Wireless communication Transient analysis Privacy Real-time systems AC microgrid model predictive control adaptive parameters privacy preservation

来源：评论

学校读者我要写书评

暂无评论

Sensor-Weapon-Target Assignment Based on Hopfield Neural network 43

Sensor-Weapon-Target Assignment Based on Hopfield Neural Net...

引用

43rd Chinese control conference (CCC)

作者： Wang, Yujue Xin, Bin Wang, Qing Beijing Inst Technol Sch Automat Beijing Peoples R China

ISBN: (纸本)9798350366907;9789887581581

This study focuses on the dual-objective optimization problem of Sensor-Weapon-Target Assignment (SWTA), aiming to minimize the expected threat values of incoming targets during combat while considering the minimal consumption of resources for effective resource allocation. We propose an innovative solution based on the Hopfield neural network by transforming the optimization model of the problem and introducing the energy function of the Hopfield neural network, which linearly combines the two optimization objectives. The states of the neural network correspond to the final allocation matrix, and by randomly adjusting weights, the neural network can converge to different solutions, ultimately obtaining the Pareto front. We designed scenarios for both small and large-scale cases in various combat situations and compared this method with traditional algorithms GA and PSO. The comparison algorithms also use linearly weighted objectives to solve the Pareto front. Experimental results indicate that in most cases, the Hopfield neural network demonstrates superior performance, achieving high-quality solutions at a lower time cost. Compared to traditional GA and PSO algorithms, it exhibits outstanding effectiveness in solving the SWTA problem. This research provides an advanced and reliable approach for military combat decision-making and offers valuable insights for the future development of intelligent systems.

关键词： Hopfield network Sensor Weapon Target Assignment Genetic Algorithm Particle Swarm Optimization

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：