检索结果-内蒙古大学图书馆

QoE-Aware 3D Video Streaming via Deep Reinforcement Learning in Software Defined networking Enabled Mobile Edge computing

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2021年第1期8卷 419-433页

作者： Zhou, Pan Xie, Yulai Niu, Ben Pu, Lingjun Xu, Zichuan Jiang, Hao Huang, Huawei Huazhong Univ Sci & Technol Hubei Engn Res Ctr Big Data Secur Sch Cyber Sci & Engn Wuhan 430074 Peoples R China Chinese Acad Sci Inst Informat Engn Beijing 100864 Peoples R China Nankai Univ Coll Comp Sci Tianjin 300071 Peoples R China Dalian Univ Technol Sch Software Dalian 116024 Peoples R China Wuhan Univ Sch Elect Informat Wuhan 430072 Peoples R China Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou 510006 Peoples R China

With the advancements of wireless network transmission technology, 2D video is hard to satisfy people's requirement for multimedia. Therefore, the high-definition 3D video that can bring a whole new viewing experience is starting to enter people's vision. However, when a tremendously large number of users play 3D video, it puts enormous computational pressure on the cloud server, which incurs high transmission latency. To release the tension, in this articl we consider a promising computing and networking architecture by incorporating Mobile Edge computing (MEC) and Software-defined networking (SDN) and propose a novel resource allocation model (RAM) to allocate resources and reduce delay. At the same time, we introduce the Quality of Experience (QoE) Model (QoEM), which uses information collected during 3D video playback to adaptively allocate the rate of future tiles. The model addresses the problem of assigning the best transmission speed to the block in the case of time-varying characteristicfactors during transmission. We propose an Actor-Critic-based deep reinforcement learning algorithm for viewport prediction and QoE optimization, called QoE-AC. For the differential transmission in the playback phase, we use the LSTM network for bandwidth and viewport prediction, while combining the historical information of the blocks into the Actor-Critic network as observations. The network can be adaptively assigned the best transmission speed for future tiles based on observations to maximize QoE. Finally, the experimental results show that the actual performance of the model is much better than other existing 3D video network models. Under different QoE targets, our proposed system can be adapted to all situations and has a 10%-15% performance improvement.

关键词： Streaming media Quality of experience Three-dimensional displays Servers Resource management Bandwidth Heuristic algorithms 3D video deep reinforcement learning centrally controlled network SDN MEC QoE

来源：评论

学校读者我要写书评

暂无评论

The Phe nome non of Social computing

The Phe nome non of Social Computing

引用

作者： Marie D. Fernando Western Sydney University

学位级别：博士

In the preceding decade world has witnessed the emergence of a new phenomenon: a predominately mobile based computing paradigm aiming to meet the needs of the broader society termed Social computing. This new computing paradigm has introduced a myriad of applications. Three main characteristics observed within this phenomenon were these applications gained a rapid growth, built remarkably large user communities and disrupted the traditional societal and business practices. The recent advancements in Information and Communication Technologies (ICTs) have facilitated the emergence of this new computing paradigm. Enabling technologies of this computing paradigm can be considered as broadband connectivity mobile or WiFi, frontend devices with sensors such as smart phones. The other enablers are, backend cloud computing and growth of the Web from 1.0 which was for one-way communication that wasn't providing interactive content to 2.0 which support effective two-way rich multimedia communication. Social computing has changed how we find accommodation like Airbnb, how we book a taxi like Uber, or how we reference a book with access over ownership by accessing only the necessary chapter for a short period on Amazon. We socially interact with peers across the globe for free using social networking site Facebook or share user generated content with a global audience on YouTube. These successful applications possess exponential growth curves and exceptionally large community sizes. Facebook initiated in 2004 by 2017 has a community of 2.2 billion users, YouTube 1.5 billion users and Airbnb 200 million users. These applications have demonstrated new approaches to enhance triple bottom line of businesses: financially, social corporate responsibly and environmentally. For example, application like Airbnb cause extra income for a host, YouTube cause empowerment through user generated content shared to international audience for free, Uber cut down fuel consumption by ride sharing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An NFV-Based Service Framework for IoT Applications in Edge computing Environments

An NFV-Based Service Framework for IoT Applications in Edge ...

引用

作者： Shih, Yuan-Yao Lin, Hsin-Peng Pang, Ai-Chun Chuang, Ching-Chih Chou, Chun-Ting Department of Communications Engineering National Chung Cheng University Minxiong621 Taiwan Chunghwa Telecom Laboratories Chunghwa Telecom Company Ltd. Taipei326 Taiwan Graduate Institute of Networking and Multimedia National Taiwan University Taipei106 Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei106 Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei115 Taiwan

Emerging Internet of Things (IoT) applications share the same characteristics of involving multiple processing components (i.e., function modules) and requiring a massive amount of data to be processed with low latency. To meet these needs, edge/fog computing has been proposed for next-generation mobile networks to migrate the computing from the cloud to the edge of the network. Thanks to the development of Network Functions Virtualization (NFV), with which edge computing platform can virtualize function modules and deploy them on any edge devices to provide flexible services on the edge networks. However, such platform would need to deal with complicated function module calling relationship (i.e., call graph) of applications and user mobility, and both are not thoroughly considered by existing works of NFV and edge computing. In this paper, based on our previous idea of virtual local-hub (VLH), we propose a complete design of edge computing framework, which applies NFV technology on edge computing environment for IoT applications. To handle the complicated call graphs of IoT applications with better resource utilization, the VLH framework adapts the technologies of container-based virtualization and microservice architecture, which enables remote function module sharing on the edge computing environment. The framework includes the heuristic algorithm for function module allocation with the objective of minimizing total bandwidth consumption. We also present a design of protocols for system operations and mobility handling in the framework. Then we implement the framework on commodity hardware as a testbed. Via simulations under a large-scale environment with practical settings and experiments on the testbed under real-world scenarios, we demonstrate and verify the effectiveness and practicability of the proposed VLH framework for IoT application service provision. © 2004-2012 IEEE.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Signal Processing and the Internet of Things

引用

IEEE SIGNAL PROCESSING MAGAZINE 2018年第5期35卷 13-15页

作者： Xu, Chenren Sun, Yan (Lindsay) Plataniotis, Konstantinos (Kostas) N. Lane, Nic AT&T Shannon Labs Florham Pk NJ 07932 USA Microsoft Res Cambridge England Peking Univ Sch Elect Engn & Comp Sci Beijing Peoples R China Peking Univ Ctr Energy Efficient Comp & Applicat Beijing Peoples R China Univ Rhode Isl Dept Elect Comp & Biomed Engn Kingston RI 02881 USA Informat Forens & Secur Tech Comm Kingston RI USA Univ Toronto Toronto ON Canada Univ Toronto Multimedia Elect & Comp Engn Dept Toronto ON Canada Univ Toronto Ident Privacy & Secur Inst Res Toronto ON Canada Univ Toronto Knowledge Media Design Inst Toronto ON Canada Engn Inst Canada Ottawa ON Canada Univ Oxford Comp Sci Dept Oxford England

The notion of the Internet of Things (IoT) has emerged as a last-mile solution for connecting various cyber technologies to our everyday life. It envisions a three-tier architecture where highly distributed and heterogeneous sensor data will be collected through a gateway and made available to the Internet to be readily accessible for a wide range of applications. Today, with ever increasing types of IoT devices as well as the growing demand being placed on the end user, the sensing platform, and the computing and storage infrastructure, more is being asked of engineers, designers, and scientists. Discusses how we can leverage today’s pervasive cloud and network infrastructure to foster more intriguing applications with more demanding signal processing and machine learning techniques.

关键词： Special issues and sections Internet of Things Signal processing Machine learning Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Energy efficiency in large-scale distributed systems

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF GRID computing AND ESCIENCE 2012年第5期28卷 743-744页

作者： Tuan Anh Trinh Hlavacs, Helmut Talia, Domenico Budapest Univ Technol & Econ Network Econ Grp H-1117 Budapest Hungary IBM Corp Armonk NY USA Univ Vienna Inst Distributed & Multimedia Comp A-1010 Vienna Austria Univ Vienna Res Grp Entertainment Comp Fac Comp Sci A-1010 Vienna Austria Univ Calabria Fac Engn I-87030 Commenda Di Rende Italy Italian Natl Res Council ICAR CNR Inst High Performance Comp & Networks Rome Italy

来源：评论

学校读者我要写书评

暂无评论

An approximation algorithm and dynamic programming for reduction in heterogeneous environments

引用

Algorithmica (New York) 2009年第3期53卷 425-453页

作者： Liu, Pangfeng Kuo, May-Chen Wang, Da-Wei Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Graduated Institute of Networking and Multimedia National Taiwan University Taipei Taiwan Institute of Information Science Academia Sinica Nankang Taipei Taiwan

Network of workstation (NOW) is a cost-effective alternative to massively parallel supercomputers. As commercially available off-the-shelf processors become cheaper and faster, it is now possible to build a cluster that provides high computing power within a limited budget. However, a cluster may consist of different types of processors and this heterogeneity complicates the design of efficient collective communication protocols. For example, it is a very hard combinatorial problem to find an optimal reduction schedule for such heterogeneous clusters. Nevertheless, we show that a simple technique called slowest-node-first (SNF) is very effective in designing efficient reduction protocols for heterogeneous clusters. First, we show that SNF is actually a 2-approximation algorithm, which means that an SNF schedule length is always within twice of the optimal schedule length, no matter what kind of cluster is given. In addition, we show that SNF does give the optimal reduction time when the cluster consists of two types of processors, when the ratio of communication speed between them is at least two. When the communication speed ratio is less than two, we develop a dynamic programming technique to find the optimal schedule. Our dynamic programming utilizes the monotone property of the objective function, and can significantly reduce the amount of computation time. Finally, combined with an approximation algorithm for broadcast 2004, we propose an all-reduction algorithm which sends the reduction answer to all processors, with approximation ratio 3.5. We conduct three groups of experiments. First, we show that SNF performs better than the built-in MPI-Reduce in a test cluster. Second, we observe a factor of 93 times saving in computation time to find the optimal schedule, when compared with a naive dynamic programming implementation. Thirdly, we apply the theoretical results to a branch-and-bound search and show that they can reduce the search time of the optimal reduct

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

multimedia computing and networking 2004

Multimedia Computing and Networking 2004

引用

2004年

作者： Nalini Venkatasubramanian

来源：评论

学校读者我要写书评

暂无评论

Service adoption strategies of push over cellular

引用

PERSONAL AND UBIQUITOUS computing 2008年第1期12卷 35-44页

作者： Ali-Vehmas, Timo Luukkainen, Sakari Aalto Univ Networking Lab FIN-02150 Espoo Finland Aalto Univ Telecommun Software & Multimedia Lab FIN-02150 Espoo Finland

Push to talk over Cellular (PoC) is a new still evolving service concept for mobile systems. Traditionally Push to Talk (PTT) service has been used in proprietary networks for decades but recently new Internet Protocol (IP) based specifications for PoC have been introduced. The service has been available in lead markets since 2004 but the mass-market adoption has not yet taken place. Commercialization process of PoC still includes many technical and market risks. The PoC technology has, however, potential to create new mobile service evolution path starting from voice and extending later on to other group applications. This document reviews different strategies related to standardization, system architecture, vendors' product strategies, substitutes, regulation and service provision relevant for PoC and discusses the various options for mobile operators and vendors how to implement this new service successfully.

关键词： PoC standards regulation diffusion of innovations

来源：评论

学校读者我要写书评

暂无评论

Service adoption strategies of push over cellular

Service adoption strategies of push over cellular

引用

作者： Ali-Vehmas, Timo Luukkainen, Sakari Networking Laboratory Helsinki University of Technology Espoo Finland Telecommunications Software and Multimedia Laboratory Helsinki University of Technology Espoo Finland

关键词： Internet service providers

来源：评论

学校读者我要写书评

暂无评论

Proceedings of SPIE: multimedia computing and networking 2004

Proceedings of SPIE: Multimedia Computing and Networking 200...

引用

multimedia computing and networking 2004

The proceedings contain 18 papers from the Conference on SPIE: multimedia computing and networking 2004. The topics discussed include: movie placement in a hierarchical CDN with stream merging mechanism;congestion control and maessage loss in Gnutella networks;energy conservation in ad hoc multimedia networks using traffic-shaping mechanisms;process group management in cross-layer adaptation and performance analysis of a hybrid media streaming system.

关键词： multimedia systems

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：