检索结果-内蒙古大学图书馆

Huge Page Friendly Virtualized Memory Management

Journal of Computer Science & technology 2020年第2期35卷 433-452页

作者： Sai Sha Jing-Yuan Hu Ying-Wei Luo Xiao-Lin Wang Zhenlin Wang School of Electronics Engineering and Computer Science Peking UniversityBeijing 100871China Peng Cheng Laboratory Shenzhen 518052China Shenzhen Key Laboratory for Cloud Computing Technology&Applications School of Electronic and Computer EngineeringPeking University ShenzhenShenzhen 518000China Department of Computer Science Michigan Technological UniversityMichigan 49246U.S.A.

With the rapid increase of memory consumption by applications running on cloud data centers,we need more efficient memory management in a virtualized *** huge pages becomes more critical for a virtual machine's performance when it runs large working set size *** with large working set sizes are more sensitive to memory allocation,which requires us to quickly adjust the virtual machine's memory to accommodate memory phase *** would be much more efficient if we could adjust virtual machines'memory at the granularity of huge ***,existing virtual machine memory reallocation techniques,such as ballooning,do not support huge *** addition,in order to drive effective memory reallocation,we need to predict the actual memory demand of a virtual *** find that traditional memory demand estimation methods designed for regular pages cannot be simply ported to a system adopting huge *** to adjust the memory of virtual machines timely and effectively according to the periodic change of memory demand is another challenge we *** paper proposes a dynamic huge page based memory balancing system(HPMBS)for efficient memory management in a virtualized *** first rebuild the ballooning mechanism in order to dispatch memory in the granularity of huge *** then design and implement a huge page working set size estimation mechanism which can accurately estimate a virtual machine's memory demand in huge pages *** these two mechanisms,we finally use an algorithm based on dynamic programming to achieve dynamic memory *** show that our system saves memory and improves overall system performance with low overhead.

关键词： virtualization huge page ballooning memory balancing

来源：评论

学校读者我要写书评

暂无评论

Design model execution engine based on web services for distributed geography modeling environment

Design model execution engine based on web services for dist...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xiaolin Wang Hongqiang Mao Yingwei Luo The Shenzhen Key Laboratory for Cloud Computing Technology and Applications Peking University Shenzhen Graduate School Guangdong China

The design of execution engine based on web services for distributed geography modeling environment relies on model contract, model management environment, execution node, data center and control node. The execution procedure of geography model execution engine would be like this: first, geographers construct model contract according to the rule of model contract, and then submit the model contract into control node; Second, the control node parsers the model contract, queries the geography model deployment information, entry point and model input/output information from model management environment, keeps them in memory; Third, control node prepares model data and calls the models which distributed on each execution node for simulation; Finally, the environment returns the result to geographers. The model execution engine adopts multi-thread technology, and could handle multi-job submitted by geographers.

关键词： Computational modeling Biological system modeling Data models Geography Contracts Engines Web services

来源：评论

学校读者我要写书评

暂无评论

Model semantic network for massive spatial information

Model semantic network for massive spatial information

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xiaolin Wang Yingwei Luo The Shenzhen Key Laboratory for Cloud Computing Technology and Applications (SPCCTA) Peking University Shenzhen Graduate School Shenzhen Guangdong China

Spatial information is now increasing continuously and is available via the Internet. But facing the abundant spatial information, people recognize many agonizing problems, such as how can spatial information cooperate with each other to solve users' task and how do users know where spatial information is located, what kinds of spatial information can be used, and the way of how to use them. The only way to remedy those problems is to use spatial metadata. Spatial metadata is the description of spatial information and its associated information, which give a semantic expatiation for spatial information. Spatial metadata is now developed as an indispensable and powerful tool for data finding, data exchanging, data managing and data utilization. Currently, there are some standards for spatial metadata such as FGDC and ISO/TC211. But the existing spatial metadata is largely for people to use, and only describes spatial information itself. In this paper, spatial metadata is extended to describe the relations among different spatial information and the distribution of spatial information on the Internet. Based on the extensive spatial metadata, a semantic network model for massive spatial information is presented to support the collaboration among spatial information and make the navigation of spatial information more fast and exact. At last, XML technology is adopted to represent the semantic network for spatial information.

关键词： Semantics XML Spatial databases Resource description framework Educational institutions ISO standards

来源：评论

学校读者我要写书评

暂无评论

Managing and integrating geography models in distributed environment

Managing and integrating geography models in distributed env...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xiaolin Wang Hui Li Hao Deng Yingwei Luo The Shenzhen Key Laboratory for Cloud Computing Technology and Applications (SPCCTA) Peking University Shenzhen Graduate School Shenzhen Guangdong China

For the current "Model islands" problems which occur in the process of the geography modeling and model sharing, we propose an idea of geography model sharing and reusing method which based on the metadata standard in distributed environment. This article mainly solves how to describe and manage the geography model to achieve the model sharing and reuse. We work on the design of the metadata standard, the integrating standard and the managing environment of the geography model. It is expected to provide a convenient platform for the geographers, so that they can easily reuse any model, which means the heterogeneous models can be well shared.

关键词： Geography Computational modeling Contracts Data models Databases Sea surface Semantics

来源：评论

学校读者我要写书评

暂无评论

Sharing and reusing geography models via model execution engine

Sharing and reusing geography models via model execution eng...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xiaolin Wang Hui Li Hao Deng Hongqiang Mao Yingwei Luo The Shenzhen Key Laboratory for Cloud Computing Technology and Applications (SPCCTA) Peking University Shenzhen Graduate School Shenzhen Guangdong China

This article analyzes the sharing and reuse of the geography model in the distributed environment based on the methods of geography model integration and framework. We use the model contract to describe the integration of geography model, and design a model contract language to express. We also design the model execution engine architecture which can execute the model contract language. This is the core function to achieve the sharing and reuse of the geography model in distributed environment.

关键词： Contracts Computational modeling Geography Adaptation models Engines Biological system modeling Web services

来源：评论

学校读者我要写书评

暂无评论

Exploring the availability and effectiveness of named data networking in handling consumer mobility

Exploring the availability and effectiveness of named data n...

引用

2014 International Conference on Industrial Electronics and Engineering (ICIEE 2014)

作者： Kai Lei Fanyun Zou Shenzhen Key Laboratory for Cloud Computing Technology and Applications(SPCCTA) School of Electronics and Computer Engineering Peking University

Due to increasing demands from mobile users for continuous and high-quality Internet access, especially in rapidly mobile environment such as on fast cars or trains, it becomes more important and urgent to design and reform mobile network protocols to satisfy those needs. Current solutions for mobile networks under TCP/IP architecture, like mobile IP, produce enormous overhead and high forwarding delay. A new network architecture called Named Data Networking(NDN) is believed to be more suitable to deal with mobile network, due to its nature of consumer-driven and its own characteristics such as cache, forwarding strategy and security. Motivated by that, in this paper, we designed Consumer Mobility model in NDN(CMNDN) and implemented it in ndn SIM. CMNDN achieved good performance in quick-response and high-speed environment. The experimental results show that NDN is available and effective in handling consumer mobile network.

关键词： consumer mobility TCP/IP named data networking CMNDN ndn SIM

来源：评论

学校读者我要写书评

暂无评论

A model contract and model integration language for integrating geography models in distributed environment

A model contract and model integration language for integrat...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xiaolin Wang Hui Li Yingwei Luo The Shenzhen Key Laboratory for Cloud Computing Technology and Applications Shenzhen Graduate School Peking University Guangdong China Peking University Beijing Beijing CN

This paper presents the model contract and the model integration language, which is used for sharing and reusing geography models in a distributed geography modeling environment. The model contract mainly consists of three parts, the model external description information, the model internal structural information and the model execution flow information. Geographer can structure the model contract to invoke shared models and method to simulate the geography phenomenon using the model integration language. The model integration language is a kind of markup language to express the model contract.

关键词： Geography Contracts Computational modeling Data models Engines Abstracts Educational institutions

来源：评论

学校读者我要写书评

暂无评论

A Rule-Based Pretreatment Mechanism for Online Mobile Map Data

A Rule-Based Pretreatment Mechanism for Online Mobile Map Da...

引用

IEEE Conference on Vehicular technology (VTC)

作者： Xiaolin Wang Hui Li Yingwei Luo Department of Computer Science and Technology Peking University Beijing China Shenzhen Key Laboratory for Cloud Computing Technology and Applications (SPCCTA) Peking University Shenzhen Graduate School Shenzhen China

In online map service for mobile users, it's necessary to provide different map data according to different application scenarios. For a given scenario, we can preprocess the map data to satisfy the online and mobile requirements. This paper proposes a rule-based pretreatment mechanism for online mobile map data which using a novel mobile map data format Byte-Map. Through the use of pretreatment rules definition and rule engine, we can externalize the decision logic from the business logic in data pretreatment mechanism. We can also separate the data preparer and data pretreatment programmer from each other. In one hand, the data preparer can make definition and configure rules to change the pretreatment procedure, without knowing the program code. In another hand, the data pretreatment programmer can avoid modifying and re-compiling program code for handling map data from different source and type. The rule-based pretreatment mechanism made the online mobile map data pretreatment procedure flexible and extensional.

关键词： Mobile communication Geometry Engines Business Mobile handsets Roads Geography

来源：评论

学校读者我要写书评

暂无评论

Efficient cube computing on an extended multidimensional model over uncertain data

Efficient cube computing on an extended multidimensional mod...

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Chunyang Wei Hongyan Li Kai Lei Tengjiao Wang Key Laboratory of High Confidence Software Technologies Ministry of Education School of Electronics Engineering and Computer Science Peking University Beijing China The Shenzhen Key Laboratory for Cloud Computing Technology and Applications (SPCCTA) Peking University Shenzhen Graduate School Shenzhen China

Data uncertainty is an inherent property in various applications due to reasons such as measurement errors, incompleteness of data and so on. While On-Line Analytical Processing (OLAP) has been a powerful method for analyzing large data warehouse, OLAP over uncertain data has become a valuable and attractive issue because of the increasingly demand for handling uncertainty in multidimensional data. In this paper, we firstly describe our UStar-Schema model that extends the traditional OLAP model to support uncertain dimension attributes in fact table, uncertain measures in fact table and uncertainty in dimension table. Then we extend the processing model of the aggregate queries and cube computing on Ustar-Schema. Secondly, we design a novel index structure called PSI-Index on UStar-Schema to improve efficiency of OLAP quering and cube computing. Furthermore, an advanced index structure called HB-Index and an efficient algorithm are proposed to accelerate iceberg cube computing based on our model using pruning techniques to eliminate huge amounts of useless computations. Finally, extensive experiments are performed to examine the efficiency and effectiveness of our proposed techniques.

关键词： Indexes Aggregates Uncertainty Computational modeling Sensors Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Holistic twig joins based on Sketch Tree

Holistic twig joins based on Sketch Tree

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： JunWen Ji Yue Wang Kai Lei Tengjiao Wang Key Laboratory of High Confidence Software Technologies Ministry of Education School of Electronics Engineering and Computer Science Peking University Beijing China The Shenzhen Key Laboratory for Cloud Computing Technology and Applications (SPCCTA) Peking University Shenzhen Graduate School Shenzhen China

Due to the wide spread of XML and its importance, twig query matching, which has been identified as a core operation in querying XML data, has become a research hotspot. Although a number of algorithms have been proposed recently to process a twig query holistically, existing algorithms can be further improved with the help of the DTD file. In this paper, we (1) proposed the Sketch Tree structure according to the DTD scheme and employed it to translate the queries; (2) proposed a new labeling scheme named Sketch Dewey on the basis of the Sketch Tree to encode not only the elements in XML data but also the query; (3) designed an efficient path matching algorithm called PathCheck and a novel holistic twig join algorithm called TJumperJoin utilizing the Sketch Dewey code. To answer a query, they only need to scan the elements of leaf nodes in the query and benefitting from the Sketch Dewey labeling scheme, they can take advantage of bitwise operation to make acceleration. At last, extensive experiments are performed to examine the efficiency and effectiveness of our proposed techniques.

关键词： XML Labeling Algorithm design and analysis Pattern matching Sections Databases Finite element methods

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：