检索结果-内蒙古大学图书馆

Duo: A High-Throughput Reconfigurable Datacenter network Using Local Routing and control

PROCEEDINGS OF THE ACM ON MEASUREMENT AND ANALYSIS OF COMPUTING systems 2023年第1期7卷 1-25页

作者： Zerwas, Johannes Gyoergyi, Csaba Blenk, Andreas Schmid, Stefan Avin, Chen Tech Univ Munich TUM Sch Computat Informat & Technol Munich Germany Eotvos Lorand Univ Budapest Hungary Univ Vienna Budapest Hungary Siemens AG Munich Germany TU Berlin Berlin Germany Fraunhofer SIT Berlin Germany Ben Gurion Univ Negev Sch Elect & Comp Engn Beer Sheva Israel

The performance of many cloud-based applications critically depends on the capacity of the underlying datacenter network. A particularly innovative approach to improve the throughput in datacenters is enabled by emerging optical technologies, which allow to dynamically adjust the physical network topology, both in an oblivious or demand-aware manner. However, such topology engineering, i.e., the operation and control of dynamic datacenter networks, is considered complex and currently comes with restrictions and overheads. We present Duo, a novel demand-aware reconfigurable rack-to-rack datacenter network design realized with a simple and efficient control plane. Duo is based on the well-known de Bruijn topology (implemented using a small number of optical circuit switches) and the key observation that this topology can be enhanced using dynamic ("opportunistic") links between its nodes. In contrast to previous systems, Duo has several desired features: i) It makes effective use of the network capacity by supporting integrated and multi-hop routing (paths that combine both static and dynamic links). ii) It uses a work-conserving queue scheduling which enables out-of-the-box TCP support. iii) Duo employs greedy routing that is implemented using standard IP longest prefix match with small forwarding tables. And iv) during topological reconfigurations, routing tables require only local updates, making this approach ideal for dynamic networks. We evaluate Duo in end-to-end packet-level simulations, comparing it to the state-of-the-art static and dynamic networks designs. We show that Duo provides higher throughput, shorter paths, lower flow completion times for high priority flows, and minimal packet reordering, all using existing network and transport layer protocols. We also report on a proof-of-concept implementation of Duo's control and data plane.

关键词： datacenter networks network design demand-aware optical networks

来源：评论

学校读者我要写书评

暂无评论

Constrained K-means++ for multi-controller placement load balance

Constrained K-means++ for multi-controller placement load ba...

引用

2024 International conference on Circuit, systems and Communication, ICCSC 2024

作者： Chentouf, Aymen Miyara, Mounia Chiba, Zouhair Hassan Ii University of Casablanca Lis Labs Faculty of Sciences Ain Chock Mathematics and Computing Department Morocco

ISBN: (纸本)9798350365306

The surge in interest surrounding Software Defined networking (SDN) reflects its status as a groundbreaking and transformative network approach. In large-scale SDN networks, a sole centralized controller cannot fulfill the requirement;there arises the necessity for multiple controllers. With performance heavily correlated with the placement of controllers, the controller placement problem became the most important challenge in multi-controller SDN networks. In this paper, we introduce an algorithm that incorporates constrained k-means++ and subsequent modifications to mitigate some k-means-based network partition limitations. The experimental result shows that incorporating constraints on the amount of switches pertaining to controllers efficiently balances the load on controllers and considerably reduces the load difference degree compared to k means and k-means++. © 2024 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

DDOSHIELD-IoT: A Testbed for Simulating and Lightweight Detection of IoT Botnet DDoS Attacks 54

DDOSHIELD-IoT: A Testbed for Simulating and Lightweight Dete...

引用

54th Annual IEEE/IFIP International conference on Dependable systems and networks (DSN)

作者： De Vivo, Simona Obaidat, Islam Dai, Dong Liguori, Pietro Univ Naples Federico II Naples Italy Univ North Carolina Charlotte Charlotte NC USA

ISBN: (纸本)9798350395730;9798350395723

In the rapidly expanding realm of the Internet of Things (IoT), the escalation of sophisticated cyber threats, particularly botnet Distributed Denial of Service (DDoS) attacks, highlights the importance of Intrusion Detection systems (IDS) for maintaining network integrity. IDSs are necessary tools for identifying and mitigating such threats. Consequently, there is a compelling need for a testbed that can facilitate the development and rigorous evaluation of IDS solutions, specifically designed to meet unique requirements and constraints of IoT environments. To bridge this gap, DDOSHIELD-IoT, an IDS testbed, is introduced, aiming to provide a platform for creating and evaluating IDSs within the IoT context. DDOSHIELD-IoT leverages Docker containers and the NS-3 network simulator to accurately mimic IoT environments and traffic. DDOSHIELD-IoT is used to implement and evaluate multiple IDSs. These IDSs leverage different machine learning models, such as K-Means, to detect Mirai botnet DDoS traffic, achieving an accuracy of over 90%. This evaluation highlights DDOSHIELD-IoT's precision as an IDS testbed. Furthermore, DDOSHIELD-IoT provides the capability to measure diverse performance metrics, such as CPU and memory usage. These assessments show DDOSHIELD-IoT's contributions to IoT security practices by offering scalability and reproducibility for enhanced IDS creation and evaluation.

关键词： IDS Botnet DDoS IoT

来源：评论

学校读者我要写书评

暂无评论

Detecting False Data Injection Attacks using Spatial-temporal Graph Neural network 12

Detecting False Data Injection Attacks using Spatial-tempora...

引用

IEEE 12th Data Driven control and Learning systems conference (DDCLS)

作者： Wei, Xingshen Liu, Wei Zhou, Jian Zhou, Xiaoming Zhang, Wenjie Cao, Yongjian Nanjing NARI Informat Commun Technol Co Ltd NARI Grp Corp State Grid Elect Power Res Inst Nanjing Peoples R China State Grid Liaoning Elect Power Supply Co Shenyang Peoples R China

ISBN: (纸本)9798350321050

There are a large number of cyber-attacks in the power system, especially the false data injection attack (FDIA). This attack can bypass the traditional bad data detection mechanism (BDDM), and affect the operation of the power system. In this paper, for the purpose of guaranteeing the reliable operation of the cyber-physical power system (CPPS), a novel FDIA detection model is developed based on spatial-temporal graph neural network (STGNN). The STGNN can extract the temporal features and spatial features of measurement data simultaneously in the CPPS. Specially, the spatial features and the temporal features are extracted by graph neural network (GNN) and recurrent neural network (RNN), respectively. Simulation results based on IEEE 14-bus system verify the performance of the proposed method.

关键词： False data injection attack Attack detection Graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

Leveraging Symmetry in RL-based Legged Locomotion control

Leveraging Symmetry in RL-based Legged Locomotion Control

引用

2024 International conference on Intelligent Robots and systems

作者： Su, Zhi Huang, Xiaoyu Ordonez-Apraez, Daniel Li, Yunfei Li, Zhongyu Liao, Qiayuan Turrisi, Giulio Pontil, Massimiliano Semini, Claudio Wu, Yi Sreenath, Koushil Univ Calif Berkeley Uc Berkeley CA 94720 USA Tsinghua Univ Inst Interdisciplinary Informat Sci Beijing Peoples R China Ist Italiano Tecnol Genoa Italy Shanghai Qi Zhi Inst Shanghai Peoples R China

ISBN: (纸本)9798350377712;9798350377705

Model-free reinforcement learning is a promising approach for autonomously solving challenging robotics control problems, but faces exploration difficulty without information about the robot's morphology. The under-exploration of multiple modalities with symmetric states leads to behaviors that are often unnatural and sub-optimal. This issue becomes particularly pronounced in the context of robotic systems with morphological symmetries, such as legged robots for which the resulting asymmetric and aperiodic behaviors compromise performance, robustness, and transferability to real hardware. To mitigate this challenge, we can leverage symmetry to guide and improve the exploration in policy learning via equivariance / invariance constraints. We investigate the efficacy of two approaches to incorporate symmetry: modifying the network architectures to be strictly equivariant / invariant, and leveraging data augmentation to approximate equivariant / invariant actor-critics. We implement the methods on challenging loco-manipulation and bipedal locomotion tasks and compare with an unconstrained baseline. We find that the strictly equivariant policy consistently outperforms other methods in sample efficiency and task performance in simulation. Additionaly, symmetry-incorporated approaches exhibit better gait quality, higher robustness and can be deployed zero-shot to hardware.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Scheduling Versus Multicasting Capability on Enhancing Voltage Stability of Interconnected DERs

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems ii-EXPRESS BRIEFS 2024年第9期71卷 4361-4365页

作者： Qu, Chunxiao Liu, Xinyu Wu, Jianjian Li, Husheng Cheng, Chi-Tsun Zhou, Qingfeng Dongguan Univ Technol Guangdong Prov Key Lab Intelligent Disaster Preve Dongguan 523808 Guangdong Peoples R China Dongguan Univ Technol Dongguan Key Lab Artificial Informat Network Dongguan 523808 Guangdong Peoples R China Purdue Univ Sch Aeronaut & Astronaut W Lafayette IN 47907 USA Purdue Univ Elmore Family Sch Elect & Comp Engn W Lafayette IN 47907 USA RMIT Univ Dept Mfg Mat & Mechatron Melbourne Vic 3001 Australia

A delay-tolerant Kalman filter (DTKF) was proposed in an earlier work of the authors for solving the voltage stability problem in distributed generation systems (DGSs). Several scheduling schemes were compared for the DGS, where 4 wireless-connected sensor-controller pairs are equally divided into 2 groups and the wireless channel within each group has interference. This brief further generalizes the approach for large-scale DGSs with numerous interconnected distributed energy resources (DERs), where each distributed voltage sensor can perform a multicast to reach multiple controllers and each controller can receive messages from different sensors. In this brief, the aim is to investigate the effects of sensors' scheduling schemes and their multicasting capability on the stability of their DGS. Understanding the dominant factor influencing stability performance (sensor scheduling or multicasting capability) is crucial for making informed decisions and optimizing system design, resource allocation, and performance improvements.

关键词： Voltage control Multicast communication Power system stability Circuit stability Distributed power generation Wireless sensor networks Voltage measurement Distributed energy resources distributed estimation communication strategy scheduling multicasting

来源：评论

学校读者我要写书评

暂无评论

Dynamic Encoding-Decoding-Based Quantized Iterative Learning control 13

Dynamic Encoding-Decoding-Based Quantized Iterative Learning...

引用

13th IEEE Data Driven control and Learning systems conference, DDCLS 2024

作者： Huo, Niu Shen, Dong School of Mathematics Renmin University of China Beijing100872 China

ISBN: (纸本)9798350361674

The tracking performance of linear discrete-time systems under quantized iterative learning control is investigated in this paper. An encoding-decoding mechanism is utilized to process the output of the system that is transmitted over the network channel. The encoding method includes the quantization procedure, which employs a uniform quantizer with finite quantization levels. The scaling parameters in the encoder and decoder are formulated to dynamically adjust based on the input of the quantizer. The learning control scheme is designed based on the output generated by the decoder. The results demonstrate that the system attains error-free tracking performance. The theoretical findings of this research are confirmed by a numerical simulation. © 2024 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

GADEC: Discovering Abnormal Citation Groups Based on Enhanced Local Community Expansion and DQN 35th

GADEC: Discovering Abnormal Citation Groups Based on Enhance...

引用

35th International conference on Database and Expert systems Applications (DEXA)

作者： Zhu, Yan Wang, Xiaofei Lin, Xinrui Peng, Yiqiang Southwest Jiaotong Univ Sch Comp & AI Chengdu Peoples R China Xihua Univ Chengdu Peoples R China

ISBN: (纸本)9783031683114;9783031683121

Scholars are enhancing their academic publication for research sharing, professional development, opportunities for collaboration, and so on. They will win academic prestige if their publications have a high citation index due to the excellent quality. However, some scholars ally with each other to build a group (community) for over-citing each other's papers, in order to increase citation amount fraudulently and further angle for praises and benefits. Such a group demonstrates a tightly linked citation relationship in academic social network (graph). Many existing anomaly group detection methods don't extract and utilize rich semantic information from network and neglect the joint optimization of dense subgraphs discovery and node representation learning, thus the detection performance is degraded. To deal with these issues, an anomalous citation group detection approach GADEC is proposed, which bases on local expansion community discovery andDQN(DeepQnetwork). Semantic information such as research field, paper title, and self-citation is extracted and represented to richen authors' abnormal features. An expansion measure function is enhanced for community discovery, which integrates several key metrics like node transfer similarity, node community membership, abnormal citation degree, etc. GADEC can accurately find the anomaly citation groups by mutually promoting both detection performance of anomalous communities and authors. The experiments on real data sets have demonstrated very good effectiveness of GADEC on the abnormal citation group mining.

关键词： Academic network Abnormal Citation Group Detection Local Community Expansion Deep Q network (DQN) Semantic Features

来源：评论

学校读者我要写书评

暂无评论

Accountable and Distributed Industrial control systems with Autonomous Contracts 26

Accountable and Distributed Industrial Control Systems with ...

引用

26th conference on Innovation in Clouds, Internet and networks and Workshops (ICIN) - Distributed Intelligence across network and Edge-to-Cloud Continuum

作者： Makhijani, Kiran Faisal, Tooba Futurewei Technol Santa Clara CA 95050 USA Kings Coll London London England

ISBN: (纸本)9798350398045

Industrial control systems (ICS) have specific data requirements in terms of Quality of Service (QoS). Lost or delayed critical data, such as control signals, can damage widespread production, such as machine performance. The problem is compounded in the next-generation Industry 4.0, where the operations will be even less human-dependent, involving multiple organizations. Moreover, the communication aspects across multistakeholders require a disaggregated approach contrary to the current closed ICS architecture. This paper presents a framework for decentralization of ICS called Operations and control networks (OCN) in which 'contracts' are the basic units of abstraction to exchange information with trust and precision between different actors. In the lower layers, High-Precision Communication (HPC) contracts execute control functions with requested service level guarantees in the network. A high-level trusted delegation of tasks is executed as smart contracts using Distributed Ledger Technology (DLT) to enable multi-stakeholder auditability and accountability.

关键词： Smart Contracts New IP DLT High-Precision Communication HPC-Contract Operation & control networks (OCN) and control systems

来源：评论

学校读者我要写书评

暂无评论

Stability-informed Bayesian Optimization for MPC Cost Function Learning 8

Stability-informed Bayesian Optimization for MPC Cost Functi...

引用

8th IFAC conference on Nonlinear Model Predictive control (NMPC)

作者： Hirt, Sebastian Pfefferkorn, Maik Mesbah, Ali Findeisen, Rolf Tech Univ Darmstadt Control & Cyber Phys Syst Lab Darmstadt Germany Univ Calif Berkeley Dept Chem & Biomol Engn Berkeley CA 94720 USA

Designing predictive controllers towards optimal closed-loop performance while maintaining safety and stability is challenging. This work explores closed-loop learning for predictive control parameters under imperfect information while considering closed-loop stability. We employ constrained Bayesian optimization to learn a model predictive controller's (MPC) cost function parametrized as a feedforward neural network, optimizing closed-loop behavior as well as minimizing model-plant mismatch. Doing so offers a high degree of freedom and, thus, the opportunity for efficient and global optimization towards the desired and optimal closed-loop behavior. We extend this framework by stability constraints on the learned controller parameters, exploiting the optimal value function of the underlying MPC as a Lyapunov candidate. The effectiveness of the proposed approach is underlined in simulations, highlighting its performance and safety capabilities. Copyright (C) 2024 The Authors.

关键词： Closed-loop Learning Model Predictive control Bayesian Optimization Lyapunov Stability Policy Optimization Neural network

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：