检索结果-内蒙古大学图书馆

DRLO: Optimizing edge server placement in dynamic MEC scenarios using deep reinforcement learning

computer networks 2025年 268卷

作者： Yingya Guo Cen Chen College of Computer and Data Science Fuzhou University PR China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University PR China Engineering Research Center of Big Data Intelligence Ministry of Education Fujian PR China

As an emerging computing paradigm, Mobile Edge Computing (MEC) significantly enhances user experience and alleviates network congestion by strategically deploying edge servers in close proximity to mobile users. However, the effectiveness of MEC hinges on the precise placement of these edge servers, a critical factor in determining the Quality of Experience (QoE) for mobile users. While existing studies predominantly focus on optimizing edge server placement in static scenarios, they often fall short when faced with user mobility, resulting in a degradation of QoE. To address this challenge, we propose an adaptive edge server placement approach that leverages Deep Reinforcement Learning (DRL) to select the base stations for placing edge servers in a dynamic MEC environment. Our objective is to minimize access delay by optimizing edge server placement for adapting to dynamic environment. To tackle the vast action space associated with edge server placement, we introduce a novel activation function in the actor neural network for efficient exploration. Furthermore, to enhance the adaptability of the derived edge server placement strategy, we meticulously design a new reward function, which takes into account the minimization of total access delay within dynamic MEC scenarios. Finally, to validate the effectiveness of our proposed method, extensive experiments were conducted using the Shanghai Telecom dataset. The results demonstrate that our approach outperforms baseline methods in minimizing access delay for users in dynamic MEC scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mitigating cloud co-resident attacks via grouping-based virtual machine placement strategy 36

Mitigating cloud co-resident attacks via grouping-based virt...

引用

36th IEEE International Performance Computing and Communications Conference, IPCCC 2017

作者： Liang, Xin Gui, Xiaolin Jian, A.N. Ren, Dewang School of Electronics and Information Engineering and Shaanxi Province Key Laboratory of Computer Network Xi'An Jiaotong University Xi'an China

ISBN: (纸本)9781509064687

Security is one of the biggest concerns for the further adoption of Clouds. However, Cloud providers usually assign VMs leased by different customers upon the same physical server. Albeit maximizing resource efficiency, this cross-domain sharing poses a serious threat to customers' privacy concerns. A malicious VM could break or bypass the isolation mechanism and execute certain cross-VM attacks, such as side channel attacks or memory Dos attacks, etc. However, most of previous solutions are either attack-specific or unsuitable for immediate deployment, making the mitigation techniques for co-resident attacks still an important and worth-studying problem in cloud security. In this paper, we propose a novel grouping-based VM placement strategy to provide a secure optimization for existing VM placement policies. The theoretical analysis and simulation results show that our strategy decreases enormously the probability of co-residence while incurring only a slight loss on resource efficiency. The results also demonstrate that our strategy is significantly more effective in terms of both co-location resistance and resources efficiency, compared with the CLR policy. © 2017 IEEE.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

DynGL-SDP: Dynamic Graph Learning for Semantic Dependency Parsing 29

DynGL-SDP: Dynamic Graph Learning for Semantic Dependency Pa...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Li, Bin Gao, Miao Fan, Yunlong Sataer, Yikemaiti Gao, Zhiqiang Gui, Yaocheng School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Ministry of Education Nanjing210096 China School and Institute of Modern Posts Nanjing University of Posts and Telecommunications Nanjing210003 China

A recent success in semantic dependency parsing shows that graph neural networks can make significant accuracy improvements, owing to its powerful ability in learning expressive graph representations. However, this work learns graph representations based on a static graph constructed by an existing parser, suffering from two drawbacks: (1) the static graph might be error-prone (e.g., noisy or incomplete), and (2) graph construction stage and graph representation learning stage are disjoint, the errors introduced in the graph construction stage cannot be corrected and might be accumulated to later stages. To address these two drawbacks, we propose a dynamic graph learning framework and apply it to semantic dependency parsing, for jointly learning graph structure and graph representations. Experimental results show that our parser outperforms the previous parsers on the SemEval-2015 Task 18 dataset in three languages (English, Chinese, and Czech). © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A PSO Algorithm with Multi-Grouping and Two-Layer Structure

A PSO Algorithm with Multi-Grouping and Two-Layer Structure

引用

International Conference on Data Science and Business Analytics (ICDSBA)

作者： Tiaojun Zeng Chuanjian Wang Zhangliang Wei Shihezi University Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education

ISBN: (数字)9781728146447

ISBN: (纸本)9781728146454

A PSO (particle swarm optimization) algorithm with multiple groups and two-layer structure(MTPSO) is proposed. First, the whole particle swarm is divided into several groups, each one is optimized. For enhance efficiency in the optimization process, each particle adopts a mixed algorithm of negative gradient. Secondly, according to the function value of each particle solution, the particle group is divided into two structures: the elite layer and the ordinary layer. In the algorithm initialization phase, the particles with the best value in each group are selected into the elite layer. The particles in the elite layer are relatively fixed and regularly selected (similar to the parliamentary mechanism in human society), that is, each elite layer as a whole. After several iterations of optimization calculations in the same way as the normal layer, the new elite layer is formed again according to the previou method. The optimal solution calculated by the elite layer is added as a global optimal solution to the position update formula of each particle. Similarly, the optimal solution for the common layer is also added to the update formula for each particle in the elite layer. It reflects the upper and lower particle's mutual penetration and mutual influence of. Simulation experiments show the proposed algorithm is able to avoid premature and powerful global optimization ability and fast convergence, PSO's computing efficiency.

关键词： Optimization Particle swarm optimization Clustering algorithms Convergence Gradient methods Quantization (signal) Nickel

来源：评论

学校读者我要写书评

暂无评论

An dynamic-weighted collaborative filtering approach to address sparsity and adaptivity issues

An dynamic-weighted collaborative filtering approach to addr...

引用

Congress on Evolutionary Computation

作者： Liang Gu Peng Yang Yongqiang Dong Ministry of Education Key Laboratory of Computer Network and Information Integration (Southeast University) Nanjing China

ISBN: (纸本)9781479914869

Recommendation systems, as efficient measures to handle the information overload and personalized service problems, have attracted considerable attention in research community. Collaborative filtering is one of the most successful techniques based on the user-item matrix in recommendation systems. Usually the matrix is extremely sparse due to the massive number of users and items. And the sparsity of users and items tends to differ significantly in degree. The feature of the matrix changes with the variation of users/items data and hence, leads to poor scalability of the recommendation method. This paper proposes a dynamic-weighted collaborative filtering approach (DWCF) to address sparsity and adaptivity issues. In this approach, the relationship between the distributions of similar users and items is considered to get better recommendation, i.e., the contributions of the user part and the item part to recommendation results depend on their similarity ratios. Moreover, the effect strength of different parts is controlled by an averaging parameter. Experiments on MovieLens dataset illustrate that the DWCF approach proposed in this paper can obtain good recommendation result given different conditions of data sparsity and perform better than a user-based predictor, an item-based predictor and a conventional hybrid approach.

关键词： Filtering Collaboration Accuracy Sparse matrices Computational modeling Feature extraction Estimation

来源：评论

学校读者我要写书评

暂无评论

Cross-chain Transaction Tracking Protocol based on Multi-dimensional Digital Watermarking Fingerprints 6

Cross-chain Transaction Tracking Protocol based on Multi-dim...

引用

6th International Conference on Frontier Technologies of information and computer, ICFTIC 2024

作者： Li, Duanzhen Xu, Shujiang He, Haochen Xue, Hongrui Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250014 China

ISBN: (纸本)9798331541750

Cross-chain technology plays a critical role in the process of interconnecting blockchains. However, all attention has been focused on how to achieve efficient cross-chain interoperability protocols, thus neglecting the most important security issues in cross-chain data interaction. Frequent network attacks and data privacy leaks have sounded the alarm for the safety of cross-chain data transactions. How to solve the problem of data ownership tracking in cross-chain transactions has become the top priority. This paper designs a cross-chain transaction tracking protocol based on multi-dimensional digital watermark fingerprints, using robust watermark, fragile watermark, and user identity key to achieve multi-dimensional tracking and supervision of cross-chain data transactions. Finally, this paper analyzes the feasibility and efficiency of the proposed protocol through experiments. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Laser 728 nm Spectroscopy of Electrodeless Discharge Rb Lamp

引用

Chinese Physics Letters 2014年第12期31卷 23-26页

作者：刘忠征薛潇博牛富增张理国凌俐陈景标 State Key Laboratory of Advanced Optical Communication System and Network Institute of Quantum Electronics School of Electronics Engineering ~ Computer Science Peking University Beijing 100871 Institute of Information and Electronics Zhejiang University City College Hangzhou 310015

The electrodeless discharge rubidium vapor lamp plays a key role in a number of applications, such as atomic clock, atomic magnetometer, atomic optical filter and laser frequency stabilization. The electrodeless discharge Rb vapor lamp has rich spectra, including 420nm, 421nm, 565nm, 572nm, 607nm, 616nm, 728 nm, 776 nm, 780 nm, 795 nm, 1324 nm, 1344 nm, 1366 nm, 1475 nm, 1529 nm spectroscopy, etc. The 780nm transition wavelength between 5P3/2 and 5S1/2 of Rb atoms is usually used in fields of the Rb atomic clock and the Rb atomic *** the 421.7 nm laser pumping atoms from 5S1/2 to 6P1/2, 1366.9 nm transition from 6S1/2 to 5P3/2 can be used as a clock transition of Rb four levels for an atomic active optical clock. An active optical clock is a new conception of the atomic clock and has the potential to improve the stabil- ity of the best atomic clocks by about two orders of magnitude. Another application of the elec- trodeless discharge Rb vapor lamp is the Rb Faraday anomalous-dispersion optical filter （FADOF）（e.g., 776 nm] and 1529 nm spectroscopy）, in which the electrodeless discharge Rb vapor lamp is more feasible than the one using a laser pumped Rb vapor cell in some cases, since many excited states are populated enough for aimed FADOF transition. Although the rich spectra of Rb have many applications, so far no detailed investigations or applications have been achieved in 728.0nm transition. To the best of our knowledge, the Rb 728.0 nm spectral data are currently only from the fluorescence by Beacham arc spectrum of rubidium early in 1959.

关键词： LASER spectroscopy INDUCTION lamps RUBIDIUM ABSORPTION spectra LASER cooling PHASE transformations (Physics)

来源：评论

学校读者我要写书评

暂无评论

D-TDMA: An approach of dynamic TDMA scheduling for target tracking in wireless sensor networks

D-TDMA: An approach of dynamic TDMA scheduling for target tr...

引用

2010 IEEE/ACM International Conference on Green Computing and Communications, GreenCom 2010, 2010 IEEE/ACM International Conference on Cyber, Physical and Social Computing, CPSCom 2010

作者： Wang, Yun Shi, Peizhong Li, Kai Chen, Zhikui Department of Computer Science and Engineering Southeast University Key Lab. of Computer Network and Information Integration Nanjing 210096 China School of Software Technology Dalian University of Technology Dalian 116024 China

ISBN: (纸本)9780769543314

In the application of target tracking based on dynamic convey tree-based collaboration (DCTC) in wireless sensor networks, collisions and interferences among nodes pose a challenge for data aggregation. In this paper, we refine slot allocation to the nodes in dynamic convey tree and design an energy efficient MAC protocol called D-TDMA, which avoids collisions and interferences and allocates contiguous active slots to nodes as far as possible during data aggregation from leaf nodes to a root node. As a result, the energy consumption in switching from sleeping to active state is saved. Simulation results show that D-TDMA not only gets rid of the impact of collisions and interferences among nodes in dynamic convey tree, but also performs similar throughput to that of CSMA-like mechanism where nodes work without active/sleep scheduling strategy. Our protocol outperforms ESR in both energy efficiency and low delay. © 2010 IEEE.

关键词： Time division multiple access

来源：评论

学校读者我要写书评

暂无评论

Anonymous authentication-oriented vehicular privacy protection technology research in VANET

Anonymous authentication-oriented vehicular privacy protecti...

引用

International Conference on Electrical and Control Engineering (ICECE)

作者： Shuai Zhang Jun Tao Yijia Yuan Key Laboratory of Computer Network and Information Integration of Ministry of Education Southeast University Nanjing China

Vehicular Ad hoc networks (VANET) consists of several vehicular nodes and uses 802.11p protocol for communication. Because of its unique characteristics, such as fast speed, serious Doppler effect, large node number etc, VANET is vulnerable to be affected by a variety of security threats. In this paper, we firstly introduce the system architecture, applications and categories of attacks in VANET. Then we summarize several types of anonymous authentication techniques which aim at protecting the privacy of vehicular nodes, then discuss and compare the typical anonymous authentication schemes of each type. Finally, we present the problems which should be considered in the next step of research.

关键词： Vehicles Authentication Privacy Roads Protocols Ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Received value flipping based sphere decoding algorithm for polar codes

引用

Intelligent and Converged networks 2024年第4期5卷 370-379页

作者： Rui Wang Haiqiang Chen Yan Chen Yuanbo Liu Xiangcheng Li Youming Sun Qingnian Li School of Computer and Electronic Information Guangxi UniversityNanning 530004China Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi UniversityNanning 530004China College of Information Engineering Nanning UniversityNanning 530004China

Polar codes are considered as one of the most competitive channel coding schemes for the future wireless communication *** improve the performance of polar codes with short code-length for control channels,a sphere decoding algorithm based on received value flipping is proposed in this *** a codeword fails the cyclic redundancy check,the algorithm flips the received value with low reliability and forms a new received ***,this new sequence is sent to the decoder for another decoding *** addition,we also compare the performance of different flipping sets and evaluate the influence of the associated flipping set *** results show that,the proposed algorithm can achieve performance improvement over additive white Gaussian noise channel with acceptable *** the(64,16)polar code,the proposed algorithm can achieve about 0.23 dB 10-3performance gain at frame error rate=,compared to the conventional sphere decoding ***,we also verify the applicability of the proposed algorithm over Rayleigh fading channel and observe similar results.

关键词： polar codes sphere decoding bit flipping row weight polarization weight

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：