检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Zhixing Fan, Zhaoyu Li, Yang Kang, Yibin Yan, Qi Shi, Qingjiang The School of Software Engineering Tongji University Shanghai China The Shenzhen Research Institute of Big Data Shenzhen China The Networking and User Experience Lab Huawei Technologies Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China

Coordinated multipoint (CoMP) systems incur substantial resource consumption due to the management of backhaul links and the coordination among various base stations (BSs). Accurate prediction of coordinated spectral efficiency (CSE) can guide the optimization of network parameters, resulting in enhanced resource utilization efficiency. However, characterizing the CSE is intractable due to the inherent complexity of the CoMP channel model and the diversity of the 5G dynamic network environment, which poses a great challenge for CSE prediction in real-world 5G CoMP systems. To address this challenge, in this letter, we propose a data-driven model-assisted approach. Initially, we leverage domain knowledge to preprocess the collected raw data, thereby creating a well-informed dataset. Within this dataset, we explicitly define the target variable and the input feature space relevant to channel statistics for CSE prediction. Subsequently, a residual-based network model is built to capture the high-dimensional non-linear mapping function from the channel statistics to the CSE. The effectiveness of the proposed approach is validated by experimental results on real-world data. Copyright © 2024, The Authors. All rights reserved.

关键词： Spectrum efficiency

来源：评论

学校读者我要写书评

暂无评论

Socialized Learning for Smart Cities: Cognitive Paradigm, Methodology, and Solution

引用

IEEE WIRELESS COMMUNICATIONS 2021年第5期28卷 200-208页

作者： Zhao, Yunfeng Liu, Zhicheng Qiu, Chao Li, Xiuhua Wang, Xiaofei Hu, Qinghua Tianjin Univ Comp Sci Tianjin Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin Peoples R China Tianjin Univ Coll Intelligence & Comp Sch Comp Sci & Technol Tianjin Peoples R China Tianjin Univ Sch Comp Sci & Technol Tianjin Key Lab Adv Networking Tianjin Peoples R China Tianjin Univ Tianjin Peoples R China Chongqing Univ Chongqing Peoples R China Chongqing Univ Sch Big Data & Software Engn Educ Minist Chongqing Peoples R China Chongqing Univ Inst Intelligent Software & Serv Comp Key Lab Dependable Serv Comp Cyber Phys SocEduc Minist Chongqing Peoples R China

Along with the unprecedented boom of 5G, the Internet of Things (IoT), and artificial intelligence, smart cities are making a great clamor. When billions of IoT devices are streaming in the smart city, realizing low-latency and high-bandwidth services has a significant impact on the benefits of smart cities. Thus, managing resources efficiently and intelligently to meet various service requirements has become a challenge for smart cities. With the rapid development of machine intelligence, it can be considered that many machines constitute a machine society just like that of human beings. Inspired by the efficient and collaborative operation mechanism of human society, we propose a socialized learning scheme to address various needs in smart cities (e.g., reasonable resource allocation). Specifically, we present the socialized learning scheme from three perspectives. First, we design a cognitive paradigm of socialized learning to enlighten the long-term vision of applying learning-based resource management to smart cities, with comprehensive discussions of three dimensions consisting of architecture, decision, and knowledge. Second, we also probe the socialized learning methodology including socialized training and socialized inference. It highlights social relationships and introduces a series of technologies to realize social relations within and across layers. Finally, we give a socialized learning solution for solving the practical resource allocation problem in smart cities, thereby jointly improving decision accuracy and reducing training costs. Illustrative simulations are provided to show the effectiveness of the proposed scheme.

关键词： Training Costs Smart cities Collaboration Resource management Internet of Things Probes

来源：评论

学校读者我要写书评

暂无评论

CroApp: A CNN-Based Resource Optimization Approach in Edge Computing Environment

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2022年第9期18卷 6300-6307页

作者： Jia, Yongzhe Liu, Bowen Dou, Wanchun Xu, Xiaolong Zhou, Xiaokang Qi, Lianyong Yan, Zheng Nanjing Univ Dept Comp Sci & Technol State Key Lab Novel Software Technol Nanjing 210023 Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp & Software Jiangsu Collaborat Innovat Ctr Atmospher Environm Nanjing 210044 Peoples R China Shiga Univ Fac Data Sci Hikone 5228522 Japan RIKEN Ctr Adv Intelligence Project Tokyo 1030027 Japan Qufu Normal Univ Sch Comp Sci Rizhao 276826 Peoples R China Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Xidian Univ Sch Cyber Engn Xian 710071 Peoples R China Aalto Univ Dept Commun & Networking Espoo 02150 Finland

With the emergence of various convolutional neural network (CNN)-based applications and the rapid growth of CNN model scale, the resource-constricted end devices can hardly deploy CNN-based applications. Current work optimizes the CNN model on edge servers and deploys the optimized model on devices in an edge computing environment. However, most of them only optimize the resource consumption within or across models solely, whereas neglecting the other side. In this article, we propose a novel CNN-based resource optimization approach (CroApp) that not only optimizes the resource consumption within the CNN model but also pays attention to resource optimization across the applications. Specifically, we adopt model compression as the "inner-model" optimization method, as well as computation sharing as the "intermodel" optimization method. First, during "inner-model" optimization, the CroApp prunes unnecessary parameters within the model on edge servers to reduce the scale of the model. Then, during "intermodel" optimization, the CroApp trains a set of shareable models based on the pruned model and sends these shareable models to end devices. Finally, the CroApp adaptively adjusts the shared models to reduce resource consumption. The experimental results show that the CroApp outperforms the state-of-the-art approaches in terms of resource reduction, scalability, and application performance.

关键词： Computational modeling Optimization Servers Adaptation models Solid modeling Surveillance Edge computing Computation sharing convolutional neural networks (CNNs) edge computing model pruning resource optimization

来源：评论

学校读者我要写书评

暂无评论

Economic Analysis of Edge Caching Enabled Mobile Internet Ecosystem

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第11期23卷 10647-10664页

作者： Jiang, Changkun Gao, Lin Hou, Fen Li, Jianqiang Shenzhen Univ Coll Comp Sci & Software Engn Natl Engn Lab Big Data Syst Comp Technol Shenzhen 518060 Peoples R China Harbin Inst Technol Sch Elect & Informat Engn Guangdong Prov Key Lab Aerosp Commun & Networking Shenzhen 518055 Peoples R China Shenzhen Inst Artificial Intelligence & Robot Soc Shenzhen 518000 Peoples R China Univ Macau Dept Elect & Comp Engn State Key Lab IoT Smart City Guangdong Hong Kong Macau Joint Lab Smart Cities Macau 999078 Peoples R China

Mobile edge caching is promising to improve content delivery and alleviate backbone burden by caching contents at the network edges. The commercial deployment relies on a comprehensive understanding of the economic interactions involved. This paper studies the edge caching enabled Internet ecosystem including a Content Provider (CP), a Global ISP (G-ISP) providing backbone services, a Local ISP (L-ISP) providing access services, and End-Users (EUs). The CP serves EUs via Internet servers or L-ISP's edge cache. We formulate their multi-tiered interactions as a three-stage dynamic game. In Stage I, CP determines edge cache storage to purchase from L-ISP and cache access fee to charge EUs. In Stage II, G-ISP and L-ISP determine backbone and access prices. In Stage III, EUs decide whether to choose edge cache services, considering cache hit probability, cache access fee, and backbone access prices. We analyze the subgame perfect equilibrium by elaborately designing five cases of EUs' choices, five regions of ISPs' pricing, and three patterns of CP's caching, under cooperative and competitive ISP pricing scenarios. Our analysis demonstrates that adopting edge caching leads to win-win outcomes for all parties involved. Furthermore, we find that competitive pricing is more advantageous for CP's profit when cache costs are low, while cooperative pricing is more beneficial when cache costs are high.

关键词： Mobile edge caching mobile Internet ecosystem multi-stage dynamic game network economics Mobile edge caching mobile Internet ecosystem multi-stage dynamic game network economics

来源：评论

学校读者我要写书评

暂无评论

Two-Layer Federated Learning With Heterogeneous Model Aggregation for 6G Supported Internet of Vehicles

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2021年第6期70卷 5308-5317页

作者： Zhou, Xiaokang Liang, Wei She, Jinhua Yan, Zheng Wang, Kevin Shiga Univ Fac Data Sci Hikone 5228522 Japan Hunan Univ Technol & Business Base Int Sci & Technol Innovat & Cooperat Big Da Changsha 410205 Peoples R China Tokyo Univ Technol Sch Engn Tokyo 1920982 Japan Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Xidian Univ Sch Cyber Engn Xian 710071 Peoples R China Aalto Univ Dept Commun & Networking Espoo 02150 Finland Univ Auckland Dept Elect Comp & Software Engn Auckland 1010 New Zealand

The vision of the upcoming 6G technologies that have fast data rate, low latency, and ultra-dense network, draws great attentions to the Internet of Vehicles (IoV) and Vehicle-to-Everything (V2X) communication for intelligent transportation systems. There is an urgent need for distributed machine learning techniques that can take advantages of massive interconnected networks with explosive amount of heterogeneous data generated at the network edge. In this study, a two-layer federated learning model is proposed to take advantages of the distributed end-edge-cloud architecture typical in 6G environment, and to achieve a more efficient and more accurate learning while ensuring data privacy protection and reducing communication overheads. A novel multi-layer heterogeneous model selection and aggregation scheme is designed as a part of the federated learning process to better utilize the local and global contexts of individual vehicles and road side units (RSUs) in 6G supported vehicular networks. This context-aware distributed learning mechanism is then developed and applied to address intelligent object detection, which is one of the most critical challenges in modern intelligent transportation systems with autonomous vehicles. Evaluation results showed that the proposed method, which demonstrates a higher learning accuracy with better precision, recall and F1 score, outperforms other state-of-the-art methods under 6G network configuration by achieving faster convergence, and scales better with larger numbers of RSUs involved in the learning process.

关键词： 6G mobile communication Collaborative work data models Training Distributed databases Computational modeling Object detection Federated learning End-edge-cloud computing Internet of vehicles Heterogeneous data 6G technology

来源：评论

学校读者我要写书评

暂无评论

Differentially Private K-Means Clustering Applied to Meter data Analysis and Synthesis

引用

IEEE TRANSACTIONS ON SMART GRID 2022年第6期13卷 4801-4814页

作者： Ravi, Nikhil Scaglione, Anna Kadam, Sachin Gentz, Reinhard Peisert, Sean Lunghino, Brent Levijarvi, Emmanuel Shumavon, Aram Cornell Tech Dept Elect & Comp Engn New York NY 10044 USA Arizona State Univ Sch Elect Comp & Energy Engn Tempe AZ 85281 USA Sungkyunkwan Univ Suwon 16419 Gyeonggi South Korea Lawrence Berkeley Natl Lab Computat Res Berkeley CA 94720 USA Amazon Networking Dept Seattle WA 98170 USA Kevala Inc Data Sci & Methodol Implementat San Francisco CA 94133 USA Kevala Inc Software Engn Dept San Francisco CA 94133 USA Kevala Inc San Francisco CA 94133 USA

The proliferation of smart meters has resulted in a large amount of data being generated. It is increasingly apparent that methods are required for allowing a variety of stakeholders to leverage the data in a manner that preserves the privacy of the consumers. The sector is scrambling to define policies, such as the so called '15/15 rule', to respond to the need. However, the current policies fail to adequately guarantee privacy. In this paper, we address the problem of allowing third parties to apply K-means clustering, obtaining customer labels and centroids for a set of load time series by applying the framework of differential privacy. We leverage the method to design an algorithm that generates differentially private synthetic load data consistent with the labeled data. We test our algorithm's utility by answering summary statistics such as average daily load profiles for a 2-dimensional synthetic dataset and a real-world power load dataset.

关键词： Differential privacy clustering smart grids summary statistics synthetic load generation

来源：评论

学校读者我要写书评

暂无评论

Task Offloading for Deep Learning Empowered Automatic Speech Analysis in Mobile Edge-Cloud Computing Networks

引用

IEEE TRANSACTIONS ON CLOUD COMPUTING 2023年第2期11卷 1985-1998页

作者： Li, Xiuhua Xu, Zhenghui Fang, Fang Fan, Qilin Wang, Xiaofei Leung, Victor C. M. Chongqing Univ Sch Big Data & Software Engn Chongqing 400000 Peoples R China Haihe Lab Informat Technol Applicat Innovat Tianjin 300072 Peoples R China Western Univ Dept Elect & Comp Engn London ON N6A 3K7 Canada Western Univ Dept Comp Sci London ON N6A 3K7 Canada Tianjin Univ Sch Comp Sci & Technol Tianjin Key Lab Adv Networking Tianjin 300072 Peoples R China Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518000 Peoples R China Univ British Columbia Dept Elect & Comp Engn Vancouver BC V6T 1Z4 Canada

With the explosive growth of mobile multimedia services and artificial intelligence applications involving automatic speech analysis (ASA), mobile devices are increasingly unable to handle these computation-intensive tasks generated by users due to the limited computing resource. Besides, the existing cloud computing paradigm is not capable of processing such real-time and delaysensitive ASA tasks. In this paper, by leveraging mobile edge computing and deep learning (DL), we investigate task offloading for DLempowered ASA in mobile edge-cloud computing networks to minimize the total time for processing ASA tasks, thereby providing an agile service response. Specifically, to accelerate the processing of ASA tasks, we decompose a convolutional neural network based encoder-decoder model and deploy the encoder at edge servers to extract the features of ASA tasks. Moreover, edge servers derive the user tolerance limit by using a linear regression model for further enhancing the quality of experience of users. Based on some certain network constraints (i.e., user association and edge servers' storage/computing capacity), we propose a low-complexity and distributed offloading framework to solve the formulated complex problem. Evaluation results demonstrate the effectiveness of the proposed framework on reducing the total time and improving the satisfaction rate of users.

关键词： Automatic speech analysis deep learning edge-cloud computing mobile edge computing task offloading

来源：评论

学校读者我要写书评

暂无评论

A new approach of analyzing time-varying dynamical equation via an optimal principle

引用

MODERN PHYSICS LETTERS B 2017年第8期31卷

作者： Zhao, Hui Li, Lixiang Peng, Haipeng Kurths, Juergen Xiao, Jinghua Yang, Yixian Li, Ang Beijing Univ Posts & Telecommun Sch Sci State Key Lab Informat Photon & Opt Commun Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Informat Secur Ctr State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China State Key Lab Publ Big Data Guizhou 550025 Peoples R China Potsdam Inst Climate Impact Res D-14473 Potsdam Germany Beijing Univ Posts & Telecommun Sch Software Engn Beijing 100876 Peoples R China

In this paper, an innovative design approach is proposed to solve time-varying dynamical equation, including matrix inverse equation and Sylvester equation. Based on the precondition of the existing solution of time-varying dynamical equation, different from previous approach to solve unknown matrix, an optimal design principle is used to solve the unknown variables. A performance index is introduced based on the inherent properties of the time-varying dynamical equation and Euler equation. The solution of time-varying dynamical equation is converted to an optimal problem of performance index. Furthermore, convergence and sensitivity to additive noise are also analyzed, and simulation results confirm that the method is feasible and effective. Especially, in simulations we design a tunable positive parameter in the dynamic optimization model. The tunable parameter is not only helpful to accelerate its convergence but also reduce its sensitivity to additive noise. Meanwhile the comparative simulation results are shown for the convergence accuracy and robustness of this method.

关键词： Time-varying dynamical equation an optimal design principle convergence performance sensitivity to additive noise

来源：评论

学校读者我要写书评

暂无评论

Federated Transfer Learning Based Cross-Domain Prediction for Smart Manufacturing

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2022年第6期18卷 4088-4096页

作者： Wang, Kevin I-Kai Zhou, Xiaokang Liang, Wei Yan, Zheng She, Jinhua Univ Auckland Dept Elect Comp & Software Engn Auckland 1010 New Zealand Shiga Univ Fac Data Sci Hikone 5228522 Japan RIKEN RIKEN Ctr Adv Intelligence Project Tokyo 1030027 Japan Hunan Univ Technol & Business Base Int Sci & Technol Innovat & Cooperat Big Dat Changsha 410205 Peoples R China Xidian Univ Sch Cyber Engn State Key Lab Integrated Ser Vices Networks Xian 710071 Peoples R China Aalto Univ Dept Commun & Networking Espoo 02150 Finland Tokyo Univ Technol Sch Engn Tokyo 1920982 Japan

Smart manufacturing aims to support highly customizable production processes. Therefore, the associated machine intelligence needs to be quickly adaptable to new products, processes, and applications with limited training data while preserving data privacy. In this article, a new federated transfer learning framework, federated transfer learning for cross-domain prediction, is proposed to address the challenges of data scarcity and data privacy faced by most machine learning approaches in modern smart manufacturing with cross-domain applications. The framework architecture consists of a central server and several groups of smart devices, where each group handles a different application. The existing applications can share their knowledge through the central server as base models, while new applications can convert a base model to their target-domain models with limited application-specific data using a transfer learning technique. Meanwhile, the federated learning scheme is deployed within a group to further enhance the accuracy of the application-specific model. The integrated framework allows model sharing across the central server and different smart devices without exposing any raw data and, hence, protects the data privacy. Two public datasets, COCO and PETS2009, which represent the source and target applications, are employed for evaluations. The simulation results show that the proposed method outperforms two state-of-the-art machine learning approaches by achieving better learning efficiency and accuracy.

关键词： Transfer learning data privacy Collaborative work data models Smart manufacturing Training data Servers Cross-domain prediction federated learning industry 4 0 Internet of Things transfer learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Dynamic Beam Selection in Dual-Band Communication Systems

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2024年第4期23卷 2591-2606页

作者： Zhang, Zhen Zhang, Jianhua Zhang, Yuxiang Yu, Li Gao, Feifei Shi, Qingjiang Liu, Guangyi Yuan, Zhiqiang Fan, Wei Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Tsinghua Univ Tsinghua Univ THUAI Inst Artificial Intelligence State Key Lab Intelligent Technol & Syst Beijing 100084 Peoples R China Tongji Univ Sch Software Engn Shanghai 201804 Peoples R China Shenzhen Res Inst Big Data Shenzhen 518172 Peoples R China China Mobile Res Inst Beijing 100053 Peoples R China Southeast Univ Sch Informat Sci & Engn Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China

To reduce the downlink beam sweep overhead of mmWave systems, we propose a deep reinforcement learning based dynamic beam selection (DRL-DBS) method. A new learning motivation is presented by analyzing the dynamic change laws of high- and low-frequency channels in the spatial domain: to learn the index offset between the optimal beam of mmWave and sub-6 GHz spatial spectrum. In the DRL-DBS method, we propose a novel action space where actions can dynamically adjust the size of the beam sweep subset according to the high- and low-frequency channel propagation laws. Hence, the DRL-DBS method can predict a mmWave downlink beam sweep subset with dynamic size, and the optimal beamforming index is from beam sweep results on the subset. A dual-input dueling Q-network with noisy networks and prioritized experience replay is designed to select the optimal action. The DRL-DBS method can achieve a dynamic trade-off between mmWave beam selection quality and beam sweep overhead based on the reward function. Simulation results demonstrate the superior performance of the DRL-DBS method compared with the existing strategies. Especially, the DRL-DBS method outperforms the exhaustive search algorithm in achievable rate because the overhead of mmWave beam sweep is considered.

关键词： Millimeter wave communication Wireless communication Training Indexes Vehicle dynamics Array signal processing Wireless sensor networks mmWave sub-6 GHz beam selection deep reinforcement learning

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：