检索结果-内蒙古大学图书馆

Optimal Frequency Control for Energy-Efficient in-Network Distributed Computation Under Delay Constraints

IEEE COMMUNICATIONS LETTERS 2024年第4期28卷 862-866页

作者： Li, Xiaolu Xie, Renchao Huang, Tao Liu, Yunjie Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Purple Mt Labs Dept Future Networks Nanjing 211111 Peoples R China

In-network distributed computation (INDC) is promising in future networks. This letter focuses on optimal frequency control for energy consumption minimization under application completion delay constraint. To design low-complexity optimal algorithms, we transform the application delay constraint to path delay constraints. Considering a special case of problems with a single path delay constraint (SPDC), a water-filling algorithm termed as WF-SPDC is proposed. When generalizing to problems with multiple intersected path delay constraints (MIPDC), we propose an ADMM-WF-MIPDC algorithm by utilizing the ADMM method and WF-SPDC. Nume- rical results also verify the optimality of our proposed algorithms.

关键词： In-network distributed computation frequency control energy and delay water-filling ADMM

来源：评论

学校读者我要写书评

暂无评论

CCFL: Communication-Efficient Cross-Cluster Blockchain-Based Federated Learning

CCFL: Communication-Efficient Cross-Cluster Blockchain-Based...

引用

IEEE Wireless Communications and networking Conference (WCNC)

作者： Gao, Zhipeng Song, Yue Lin, Yijing Zhang, Lijia Yang, Yang Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9781665491228

Federated Learning (FL) is a distributed learning framework that enables data sharing among multiple devices to protect data privacy. Blockchain is a decentralized ledger that can record data securely and reliably. The blockchainbased FL (BFL) framework has been used to share data and computing resources in multiple clusters. However, for the BFL framework among multi-institutional clusters, data sparsity in a cluster is a key issue. Most of the relevant works assume that the data in one cluster is rich enough to build a suitable model, which is not always satisfied in all scenarios. One method to address the problem is that enlarging the size of a BFL cluster that covers as many nodes as possible is one way. However, this method will increase communication overheads and reduce transaction throughput of the blockchain. To solve the above issues, we propose a communication-efficient blockchainbased FL framework called CCFL, which connects multiple BFL clusters to solve the data sparsity issue. We also design a pearson correlation coefficient-based dynamic model filtering mechanism that filters unnecessary models to reduce communication costs and exclude malicious models. Moreover, we illustrate a reliable contribution-based interactive validation reputation mechanism to prevent malicious nodes from participating in the training. We carry out some experiments to show the feasibility and efficiency of the proposed framework.

关键词： Federated Learning Blockchain Model filtering Cross-cluster Reputation

来源：评论

学校读者我要写书评

暂无评论

Blaze: Delay-Aware Cloud-Edge Collaborative Service Function Chain Deployment with Network Calculus 25

Blaze: Delay-Aware Cloud-Edge Collaborative Service Function...

引用

IEEE Wireless Communications and networking Conference (IEEE WCNC)

作者： Luo, Huimin Zhang, Jiao Pan, Yongchen Pan, Tian Huang, Tao BUPT State Key Lab Networking & Switching Technol Beijing Peoples R China Purple Mt Labs Nanjing Peoples R China

ISBN: (纸本)9798350303582;9798350303599

With the rapid development of Internet of the Things (IoT) technology, IoT services have higher and higher requirements for latency. In the IoT environment, virtual network functions (VNFs) are deployed on general-purpose hardware and are sequentially connected to form service function chain (SFC) to provide network services for IoT devices. However, the high latency of the link between the cloud center and the edge nodes and the resource capacity limitation of the edge nodes pose challenges to the deployment of SFCs in IoT devices. In this paper, we study the cloud-edge collaborative SFC deployment problem. We applied the network calculus theory to the cloud-edge collaborative SFC deployment for the first time, aiming to provide the end-to-end delay guarantee for the deployed SFC. We model the SFC deployment problem as Mixed Integer Nonlinear Programming (MINLP). Then we propose a heuristic algorithm (Blaze) to solve this problem. Blaze is proven to complete the deployment of SFCs in polynomial time. Finally, the algorithm is evaluated by experimental simulation. The experimental results show that compared with the existing state-of-the-art corresponding algorithms, the proposed algorithm achieves better performance in terms of the number of VNFs deployed in the cloud, resource consumption of edge nodes, and SFC request acceptance rate.

关键词： Network function virtualization service function chain network calculus deployment

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Network Traffic Classification Based on Multi-source Synergistic Distribution Alignment

Unsupervised Network Traffic Classification Based on Multi-s...

引用

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

作者： Gao, Bowen Yang, Yang Gao, Zhipeng Yu, Peng Lyu, Rui Chen, Shaoyin Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350310900

Network traffic classification is a key technology in network communication management, which is of great significance for building intelligent communication and so on. Due to the difficult and time-consuming process of network traffic labeling, it is difficult to obtain any labeled traffic data in some special networks. At the same time, in a real network environment, there are multiple network traffic domains, and the data distribution of each network traffic domain is different, making it extremely difficult to train a network traffic classification model that performs well on multiple traffic domains simultaneously. Therefore, this paper proposes a network traffic classification method in unsupervised scenarios, aiming to study how to learn traffic knowledge from multiple source traffic domains and achieve accurate classification of unlabeled network traffic without labeled traffic data in the target traffic domain. This paper divides three traffic domains from the data set, namely VPN, nonVPN and nonTor. And three traffic classification tasks of unsupervised multi-source domain are constructed. The accuracy of traffic classification tasks in the source traffic domain is nonTor and nonVPN, and the target traffic domain is VPN reaches 89.76%. The source traffic domain is VPN and nonTor,the accuracy of the classification task is 91.73% when the target traffic domain is nonVPN, and 90.35% when the source traffic domain is VPN and nonVPN, and the target traffic domain is nonTor. Experimental results show the effectiveness of the network traffic classification algorithm proposed in this paper.

关键词： unsupervised network traffic classification dynamic multi-scale fusion convolution synergistic distribution alignment multi-source decision related certainty weighting

来源：评论

学校读者我要写书评

暂无评论

Freshness -aware Content Update for Earth Observation: Trading Off AoI and Accuracy 31

Freshness -aware Content Update for Earth Observation: Tradi...

引用

31st IEEE International Conference on Network Protocols (ICNP)

作者： Guo, Yuran Ma, Xiao Sun, Qibo Zhou, Ao Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350303223

Space networks composed of Low Earth Orbit (LEO) satellites play a significant role in Earth observation systems. LEO satellite constellations, which provide wide-ranging coverage, continuously observe the Earth and transmit the observed data to satellites in higher orbits or ground stations for further analysis, benefiting from their more powerful computation capacity. In such an observation and analysis network, the timeliness of data update and the quality of analysis are crucial factors, both constrained by limited energy resources. In this paper, we jointly optimize the timeliness and analysis quality by constructing an update scheduling problem with a trade-off between Age of Information (AoI) and accuracy. Considering the unpredictable and changeable environment dynamics, we formulate this problem into a Markov decision process and propose an algorithm based on deep reinforcement learning to obtain an optimal policy that effectively tackles the trade-off problem. Simulation results demonstrate that our algorithm can jointly reduce AoI and increase accuracy, outperforming benchmark algorithms in different cases.

关键词： Space Network Earth Observation Age of Information AoI and accuracy trade-off satellite scheduling

来源：评论

学校读者我要写书评

暂无评论

PICO: Pipeline Inference Framework for Versatile CNNs on Diverse Mobile Devices

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第4期23卷 2712-2730页

作者： Yang, Xiang Xu, Zikang Qi, Qi Wang, Jingyu Sun, Haifeng Liao, Jianxin Guo, Song Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Hong Kong Polytech Univ Dept Comp Kowloon Hong Kong Peoples R China

Distributing the inference of convolutional neural network (CNN) to multiple mobile devices has been studied in recent years to achieve real-time inference without losing accuracy. However, how to map CNN to devices remains a challenge. On the one hand, scheduling the workload of state-of-the-art CNNs with multiple devices is NP-Hard because the structures of CNNs are directed acyclic graphs (DAG) rather than simple chains. On the other hand, distributing the inference workload suffers from expensive communication and unbalanced computation due to the wireless environment and heterogeneous devices. This paper presents PICO, a pipeline cooperation framework to accelerate the inference of versatile CNNs on diverse mobile devices. At its core, PICO features: (1) a generic graph partition algorithm that considers the characteristics of any given CNN and orchestrates it into a list of model pieces with suitable granularity, and (2) a many-to-many mapping algorithm that produces the best pipeline configuration for heterogeneous devices. In our experiment with 2 similar to 8 Raspberry-Pi devices, the throughput can be improved by 1.8 similar to 6.8 x under different CPU frequencies.

关键词： Mobile handsets Pipelines Kernel Convolutional neural networks Computational modeling Optimization Throughput Mobile computing pipeline inference model deployment

来源：评论

学校读者我要写书评

暂无评论

A Cooperative Relay Network for Semantic Communication with Network Coding

A Cooperative Relay Network for Semantic Communication with ...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC Workshops 2023

作者： Yin, Qikun Liang, Haotai Bao, Zhicheng An, Wannian Beijing University of Posts and Telecommunications The State Key Laboratory of Networking and Switching Technology Beijing China

ISBN: (纸本)9798350345407

Semantic communication can improve communication efficiency and quality. However, when the communication distance is long, it will cause severe signal attenuation. This paper discusses a cooperative relay network based on semantic network coding (CR-SNC) to improve the reliability problem in long-distance semantic communication image transmission. By introducing a relay node, we cooperatively encode the semantic information of multiple users at the relay. Without reducing the transmission efficiency, the reliability of image transmission in semantic communication is improved. The solution efficiently utilizes the characteristic of semantic information by using network coding techniques to jointly encode the semantic features of multiple users, thereby improving the reliability of transmission. Through experiments, compared with the traditional communication model, the cooperative relay network model proposed in this paper can achieve a better image restoration effect in the environment of low signal-to-noise ratio (SNR). © 2023 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Flow Preprocessing for Online Routing and Scheduling in Time-Sensitive Networks

Flow Preprocessing for Online Routing and Scheduling in Time...

引用

2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2023

作者： Chen, Zehua Wang, Zhili Chen, Xingyu Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China

ISBN: (纸本)9798350321524

More and more attention has been attracted to online flow scheduling mechanisms in Time-Sensitive Networks (TSN) because of the significantly increasing demand for low delay and low jitter communication in fields such as smart factories or automatic vehicles. However, because of the lack of flow information known in advance, such as when and what kind of flows will arrive and will be scheduled, it's easy for most online routing and scheduling methods to reach the bottleneck of flow scheduling in the scenario where there are time-triggered flows with large period differences to be scheduled, resulting in a low scheduling success *** this paper, a flow preprocessing method is proposed to filter flows with certain characteristics that have potential negative influence on the overall scheduling success rate or bandwidth utilization according to their periods and arrival probability. The proposed method can be easily superimposed on any kind of online routing and scheduling methods in TSN to improve performance. The flow preprocessing method is evaluated in scenarios with different numbers and types of flows, and the result shows that the flow scheduling with our preprocessing method outperform the flow scheduling without preprocessing in terms of scheduling success rate, bandwidth utilization and computation time. © 2023 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Age-Aware Status Updating for Solar Energy Storage Systems 23

Age-Aware Status Updating for Solar Energy Storage Systems

引用

23rd IEEE International Conference on Communication technology, ICCT 2023

作者： Tian, YuJia Meng, Yue Qin, Xiaoqi Ma, Nan Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China

ISBN: (纸本)9798350325959

Solar Energy Storage Systems (SESS) are deployed to address the unstable and intermittent nature of photovoltaic (PV) systems by allowing swift adjustments to system power. In such scenarios, the freshness of collected status updates is critical for controlling system performance. This timeliness is quantified through the Age of Information (AoI) metric. LoRa is introduced to the SESS as a Low-Power Wide-Area Network technology (LPWAN) to ensure reliable and energy-efficient data transmission. We explore a load monitoring system employing LoRa devices with periodic Slotted ALOHA (SA) access, where data updates with unfixed priority since the load process can be modeled as the time-variant Ornstein-Uhlenbeck (OU) process. The long-term expectation of AoI under fixed priorities is derived while the monitored process is time-invariant. Then the estimation error minimization problem is formulated while monitoring the time-variant OU process, which jointly considers delivered samples, estimated parameters, and AoI. To efficiently solve the problem, a greedy maximum scheduling (GMS) algorithm is proposed. Simulation results validate the AoI analysis with time-invariant processes and demonstrate the effectiveness of our data updating and estimation strategy using both generated data and real industry park data. © 2023 IEEE.

关键词： Age of Information Internet of Things Load monitoring Solar Energy Storage Systems

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Log Management System Based on Cloud Native Architecture 9

Design and Development of a Log Management System Based on C...

引用

9th International Conference on Systems and Informatics, ICSAI 2023

作者： Sun, Yuchen Chen, Yanpiao Zhao, Haotian Peng, Shan Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China

ISBN: (纸本)9798350383706

With the rapidly development and wide application of cloud computing and service computing, the use of cloud native architecture has become a mainstream trend in software development and deployment. In this booming background, logs have become the key information for each application to record its operation process throughout its life cycle, while existing log management systems are usually designed for specific production environments, which are not able to effectively meet the growing and diversified scenarios. The existing log management systems are usually designed for specific production environments and cannot effectively meet the needs of the growing number of diverse scenarios. Therefore, how to effectively handle log information from multiple sources becomes a key issue. In this paper, we design and develop a log management platform based on cloud-native architecture, which provides log collection, transmission, storage, and system management functions, and at the same time can be oriented to the cloud-native environment and other third-party applications for collection, providing a powerful tool for developers and operation and maintenance personnel. In addition, we designed an anomaly detection system using large language models for log parsing and used this system for anomaly detection in platform logs. Finally, the effectiveness of the system was verified by commonly used log data. The log management platform based on cloud-native architecture passed the test and has been utilized in our real production. © 2023 IEEE.

关键词： Software design

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：