检索结果-内蒙古大学图书馆

Mobility-Aware Deep Reinforcement Learning with Seq2seq Mobility Prediction for Offloading and Allocation in Edge computing

引用

IEEE Transactions on Mobile computing 2024年第6期23卷 6803-6819页

作者： Wu, Chao-Lun Chiu, Te-Chuan Wang, Chih-Yu Pang, Ai-Chun Academia Sinica Research Center for Information Technology Innovation Taipei115 Taiwan National Tsing Hua University Department of Computer Science Hsinchu300 Taiwan National Taiwan University Institute of Networking and Multimedia Taipei10617 Taiwan National Taiwan University High Performance and Scientific Computing Center Taipei10617 Taiwan

Mobile/multi-access edge computing (MEC) is developed to support the upcoming AI-aware mobile services, which require low latency and intensive computation resources at the edge of the network. One of the most challenging issues in MEC is service provision with mobility consideration. It has been known that the offloading decision and resource allocation need to be jointly handled to optimize the service provision efficiency within the latency constraints, which is challenging when users are in mobility. In this paper, we propose Mobility-Aware Deep Reinforcement Learning (M-DRL) framework for mobile service provision in the MEC system. M-DRL is composed of two parts: glimpse, a seq2seq model customized for mobility prediction to predict a sequence of locations just like a 'glimpse' of the future, and a DRL specialized in supporting offloading decisions and resource allocation in MEC. By integrating the proposed DRL and glimpse mobility prediction model, the proposed M-DRL framework is optimized to handle the MEC service provision with average 70% performance improvements. © 2002-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 268卷

作者： Ren, Yingying Li, Qiuli Guo, Yangyang Pedrycz, Witold Xing, Lining Liu, Anfeng Song, Yanjie Guangxi Univ Sch Comp Elect & Informat Nannig Peoples R China Network Technol Guangxi Key Lab Multimedia Commun Nanning Peoples R China Guangxi Univ Key Lab Parallel Distributed & Intelligent Comp Nanning Peoples R China Beijing Jiaotong Univ Sch Syst Sci Beijing Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB Canada Polish Acad Sci Syst Res Inst Warsaw Poland Fac Engn & Nat Sci Dept Comp Engn Istanbul Turkiye Xidian Univ Sch Elect Engn Xian Peoples R China Cent South Univ Sch Elect Engn Changsha Peoples R China Dalian Maritime Univ Natl Engn Res Ctr Maritime Nav Syst Dalian Peoples R China

With the rapid development of the satellite industry, the information transmission network based on communication satellites has gradually become a major and important part of the future satellite ground integration network. However, the low transmission efficiency of the satellite data relay back mission has become a problem that is currently constraining the construction of the system and needs to be solved urgently. Effectively planning the task of satellite ground networking by reasonably scheduling resources is crucial for the efficient transmission of task data. In this paper, we hope to provide a task execution scheme that maximizes the profit of the networking task for satellite ground network planning considering feeding mode (SGNPFM). To solve the SGNPFM problem, a mixed-integer planning model with the objective of maximizing the gain of the link-building task is constructed, which considers various constraints of the satellite in the feed-switching mode. Based on the problem characteristics, we propose a distance similarity-based genetic optimization algorithm (DSGA), which considers the state characteristics between the tasks and introduces a weighted Euclidean distance method to determine the similarity between the tasks. To obtain more high-quality solutions, different similarity evaluation methods are designed to assist the algorithm in intelligently screening individuals. The DSGA also uses an adaptive crossover strategy based on similarity mechanism, which guides the algorithm to achieve efficient population search. In addition, a task scheduling algorithm considering the feed-switching mode is designed for decoding the algorithm to generate a high-quality scheme. The results of simulation experiments show that the DSGA can effectively solve the SGNPFM problem. Compared to other algorithms, the proposed algorithm not only obtains higher quality planning schemes but also has faster algorithm convergence speed. The proposed algorithm improves data tra

关键词： Communications satellite Satellite ground networking Feed-switching Similarity assessment Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Special Issue on AI Enabled Cognitive Communication and networking for IoT

引用

IEEE INTERNET OF THINGS JOURNAL 2019年第2期6卷 1906-1910页

作者： Yang, Kai Liu, Sijia Cai, Lin Yilmaz, Yasin Chen, Pin-Yu Walid, Anwar Tongji Univ Dept Comp Sci Shanghai 201804 Peoples R China IBM Res MIT IBM Watson AI Lab Yorktown Hts NY 10598 USA Univ Victoria Dept Elect & Comp Engn Victoria BC V8W 2Y2 Canada Univ S Florida Elect Engn Dept Tampa FL 33620 USA IBM Thomas J Watson Res Ctr AI Fdn Learning Grp Yorktown Hts NY 10598 USA Nokia Bell Labs Murray Hill NJ 07974 USA

As we enter the Internet of Things (IoT) era in which the communication network is becoming increasingly dynamic, heterogeneous, and complex, it is desirable to have cognitive communication systems and networks that possess multiple interacting capabilities for situation assessment, resource management, online/distributed learning, big-data processing, and intelligent decision making. AI techniques, such as deep learning, probabilistic graph model, and reinforcement learning, aided with big data and IoT, provide a wide variety of tools and solutions to many new problems encountered in the design, operation, and optimization of cognitive communication systems and networking, including resource management, situation assessment, channel identification, anomaly detection, root cause analysis, and online/distributed learning.

关键词： Special issues and sections Internet of Things Resource management Dynamic scheduling Decision making Communication networks Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Software defined radio-based mixed signal detection laboratories for enhancing undergraduate communication and networking curricula 125

Software defined radio-based mixed signal detection laborato...

引用

125th ASEE Annual Conference and Exposition

作者： Wu, Zhiqiang Wang, Bin Cheng, Chi-Hao Cao, Deng Zhang, Zhiping Wright State University United States Miami University United States Central State University United States

Communication and networking courses, especially wireless communication and networking courses, have become more and more important in many disciplines such as Electrical Engineering, Computer Science, and Computer Engineering. Due to costly hardware needed for communication and networking teaching laboratories, many of these courses are taught without a laboratory. In the rare cases of existing labs, such hardware based teaching labs lack the flexibility to evolve over time and adapt to different environments. Supported by a NSF TUES type II project, we have developed a series of software defined radio (SDR) based mixed signal detection laboratories for enhancing undergraduate communication and networking curricula. In our previous NSF funded CCLI project "Evolvable wireless laboratory design and implementation for enhancing undergraduate wireless engineering education", we have developed and demonstrated the first nationwide example of evolvable SDR based laboratories for three existing undergraduate courses. In this project, we are developing new lab components that can be adopted by multiple courses ranging from freshman year introductory course to senior year capstone design projects. Specifically, in this paper, we report the development of a SDR based mixed radio frequency signal detection platform with a graphical user interface (GUI). This user-friendly GUI will allow students to adjust RF parameters such as carrier frequency, symbol rate, pulse shaping filter, etc., and mix multiple RF signals together. Additionally, students are able to observe the transmitted signal in both time and frequency at both transmitter and receiver. At receiver side, the SDR based platform also provides students the functionality of performing RF signal detection via different detection methods including energy based detection, waveform based detection, and cyclostationary analysis based detection. It is shown that by exploiting sophisticated signal processing techniques such a

关键词：

来源：评论

学校读者我要写书评

暂无评论

A systematic literature review of mobile cloud computing

International Journal of Multimedia and Ubiquitous Engineeri...

引用

International Journal of multimedia and Ubiquitous Engineering 2015年第12期10卷 135-152页

作者： Ibukun, Eweoya Daramola, Olawande Covenant University Ota Nigeria

Mobile cloud computing (MCC) is a relatively new concept that leverages the combination of cloud technology, mobile computing, and wireless networking to enrich the usability experiences of mobile users. Many field of application such as mobile health, mobile learning, mobile commerce and mobile entertainment are now taking advantage of MCC technologies. Since MCC is new, there is need to advance research in MCC in order to deepen practice. Currently, what exist are mostly descriptive literature reviews in the area of MCC. In this paper, a systematic literature review (SLR), which offers a structured, methodical, and rigorous approach to the understanding of the trend of research in MCC, and the least and most researched issue is presented. The objective of the study is to provide a credible intellectual guide for upcoming researchers in MCC to help them identify areas in MCC research where they can make the most impact. The SLR was limited to peer-reviewed conference papers and journal articles published from 2002 to 2014. The study reveals that privacy, security and trust in MCC are the least researched, whereas issues of architecture, context awareness and data management have been averagely researched, while issues on operations, end users, service and applications have received a lot of attention in the literature. © 2015 SERSC.

关键词： Mobile cloud computing

来源：评论

学校读者我要写书评

暂无评论

User behavior augmented software testing for user-centered GUI 11

User behavior augmented software testing for user-centered G...

引用

2011 ACM Research in Applied Computation Symposium, RACS 2011

作者： Chuang, Kuan-Chun Shih, Chi-Sheng Hung, Shih-Hao Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Graduate Institute of Networking and Multimedia Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan

ISBN: (纸本)9781450310871

User interface design plays an important role in software usability. In particular, the user human interaction in embedded systems and cyber-physical systems is a critical design challenge. GUI improves user experience for untrained users but, at the same time, brings great challenges to software testing. In 2002, Memon reported that up to 60% of the software testing are conducted against user interface. In the last decade, many automatic GUI testing approaches are proposed to address this challenge. In particular, model-based GUI testing mechanisms generate testing cases according to state transition diagram and software model. In this paper, we present the design and implementation for a user behavior augmented GUI test case generation mechanism. We define User Computer Interaction Hidden Markov Model (UCIHMM) to model user behaviors. With trained UCIHMMs, the developed algorithm generates test cases to emulate user computer interactions for various types of users. To evaluate the effectiveness and completeness of the developed mechanism, we conduct the experiments against an open source embedded software for hospital staffs. The results show that the developed mechanism allows the developers to discover the software flaws that model-based testing approaches fail to. © 2011 ACM.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

multimedia computing and networking 2002

Multimedia Computing and Networking 2002

引用

2001年

来源：评论

学校读者我要写书评

暂无评论

Proceedings of SPIE: multimedia computing and networking 2002

Proceedings of SPIE: Multimedia computing and networking 200...

引用

multimedia computing and networking 2002

The proceedings contains 19 articles from the Conference of SPIE: multimedia computing and networking 2002. Topics discussed include: end-to-end differentiation of congestion and wireless losses;multiresource allocation and scheduling for periodic soft real-time applications;exploiting the fair share to smoothly transport layered encoded video into proxy caches;wireless network interface energy consumption implications of popular streaming formats;efficient delivery techniques for variable-bit-rate multimedia;and distributed video streaming over Internet.

关键词： Wireless telecommunication systems

来源：评论

学校读者我要写书评

暂无评论

A statistical prediction-based scheme for energy-aware multimedia data streaming

A statistical prediction-based scheme for energy-aware multi...

引用

IEEE Conference on Wireless Communications and networking

作者： Y. Wei Surendar Chandra Suchendra Bhandarkar Department of Computer Science University of Georgia Athens GA USA Department of Computer Sci. & Engr University of Notre Dame Notre Dame IN USA

The proliferation of multimedia-capable mobile devices and ubiquitous high-speed network technologies to deliver multimedia objects has fueled the demand of mobile streaming multimedia. A necessary criterion for the mass acceptance of mobile devices is acceptable battery life of these devices. This paper explores linear prediction-based client-side strategies to reduce the wireless network interface card (WNIC) energy consumption by transitioning the WNIC to a lower power consuming sleep state. The basic idea of this strategy is to selectively choose proper periods of time to suspend communication by switching the WNIC to sleep state. A linear prediction-based time series forecasting technique is used to predict future no-data intervals. Simulation results show that linear prediction-based strategy gives better results than those based on simple averaging [Surendar Chandra et al., (2002)].

关键词： Streaming media Energy consumption Batteries Wireless networks Mobile computing Communication switching Network interfaces Computer science Sleep multimedia computing

来源：评论

学校读者我要写书评

暂无评论

multimedia computing and networking 2002 (MMCN02)

引用

Computers & Graphics 2001年第5期25卷 923-923页

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：