检索结果-内蒙古大学图书馆

Clifford algebra-based spatio-temporal modelling and analysis for complex geo-simulation data

AIP Conference Proceedings 2013年第1期1558卷 542-545页

作者： Wen Luo Zhaoyuan Yu Yong Hu Linwang Yuan Key Laboratory of Virtual Geographic Environment Ministry of Education Nanjing Normal University No.1 Wenyuan Road Nanjing China Key Laboratory of Virtual Geographic Environment Ministry of Education Nanjing Normal University No.1 Wenyuan Road Nanjing China and Jiangsu Provincial Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal Univer China

The spatio-temporal data simulating Ice-Land-Ocean interaction of Antarctic are used to demonstrate the Clifford algebra-based data model construction, spatio-temporal query and data analysis. The results suggest that Clifford algebra provides a powerful mathematical tool for the whole modelling and analysis chains for complex geo-simulation data. It can also help implement spatio-temporal analysis algorithms more clearly and simply.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scalability Evaluation of Big Data Processing Services in Clouds 1st

Scalability Evaluation of Big Data Processing Services in Cl...

引用

1st International Symposium on Benchmarking, Measuring, and Optimization, Bench 2018

作者： Zhou, Xin Jiang, Congfeng Qiu, Yeliang Fan, Tiantian Wang, Yumei Zhang, Liangbin Wan, Jian Shi, Weisong Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou Dianzi University Hangzhou310037 China School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310037 China College of Big Data and Software Engineering Zhejiang Wanli University Ningbo China School of Information and Electronic Engineering Zhejiang University of Science and Technology Hangzhou310023 China Department of Computer Science Wayne State University DetroitMI48202 United States

ISBN: (纸本)9783030328122

Currently, many cloud providers deploy their big data processing systems as cloud services, which helps users conveniently manage and process their data in clouds. Among different service providers’ big data processing services, how to evaluate and compare their scalability is an interesting and challenging work. Most traditional benchmark tools focus on performance evaluation of big data processing systems, such as aggregated throughput and IOPS, but fail to conduct a quantitative analysis of their scalability. In this paper, we propose a measurement methodology to quantify the scalability of big data processing services, which makes the cloud services scalability comparable. We conduct a group of comparative experiments on AliCloud E-MapReduce and Baidu MRS, and collect their respective scalability characteristics under Hadoop and Spark workloads. The scalability characteristics observed in our work could help cloud users choose the best cloud service platform to set up an optimized big data processing system to achieve their specific goals more successfully. © 2019, Springer Nature Switzerland AG.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Research and implementation of distributed disaster recovery system based on PRS algorithm

International Journal of Database Theory and Application

引用

International Journal of Database Theory and Application 2014年第3期7卷 91-106页

作者： Wan, Jian Xuan, Huijia Zhang, Jilin School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory of Complex System Modeling and Simulation Ministry of Education Hangzhou China Electric Engineering School Zhejiang University Hangzhou China

With the advent of the information age, the data volumes of various industries are in explosive growth, which increasingly highlights the importance of data. When a disaster occurs, how to recover the data completely and rapidly is one of the important issues receiving common concerns throughout the current industrial and academic circles. Based on the traditional disaster recovery system, this paper researches and implements a PRS algorithm-based distributed disaster recovery system[1, 2] called OsnDDR, which ensures the high availability of the system under the circumstance of continuous disasters or multi-node damage. The system adopts PRS algorithm based on RS erasure code [3] to reduce the storage resource consumption caused by the data redundancy and designs the load balancing strategy to guarantee the load balancing of each disaster recovery center in the system. © 2014 SERSC.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

Improved optimization for data disaster recovery system over low-bandwidth networks

International Journal of Database Theory and Application

引用

International Journal of Database Theory and Application 2014年第5期7卷 1-16页

作者： Wan, Jian Hong, Xiaolong Zhang, Jinlin School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory of Complex System Modeling and Simulation Ministry of Education Hangzhou China Electric Engineering School Zhejiang University Hangzhou China

Data generated by various fields are increasing exponentially and thus results in challenges for data performances in both scales of diversity and complexity. The problem how to solve the bottlenecks of low-bandwidth networks has been of fatal significance for all kinds of network status. We present a new approach on improved optimization for data disaster recovery system (DDRS) over low-bandwidth networks that not only aims to improve the defects and deficiencies of mainstream DDRS but also helps ensure the reliable network resources for operators to conduct multi-services. A novel bandwidth self-adaptive approach (BSAA) for data packing replication was essentially established to make contribution to the integral performance improvement. A Hidden Markov Model (HMM) for predicting network status was also built to ensure system availability and stability. Experiments showed that the DDRS over low-bandwidth networks named InfoDr can effectively optimize the workload with better performance and better application self-adaptability for multi-services.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Strength of the North African monsoon in the Last Interglacial and under future warming

引用

Atmospheric and Oceanic Science Letters 2023年第3期16卷 20-26页

作者： Jiazhi He Weiyi Sun Jing Wang Bin Wang Jian Liu Key Laboratory for Virtual Geographic Environment Ministry of EducationState Key Laboratory Cultivation Base of Geographical Environment Evolution of Jiangsu ProvinceJiangsu Center for Collaborative Innovation in Geographical Information Resource Development and ApplicationSchool of Geography ScienceNanjing Normal UniversityNanjingChina Department of Atmospheric Sciences and AtmosphereOcean Research Center University of Hawaii at ManoaHonoluluHIUA Jiangsu Provincial Key Laboratory for Numerical Simulation of Large Scale Complex Systems School of Mathematical ScienceNanjing Normal UniversityNanjingChina Open Studioforthe Simulationof Ocean-Climate-Isotope Qingdao National Laboratoryfor Marine Science and TechnologyQingdaoChina

与人为强迫引起的全球变暖相比,末次间冰期是轨道强迫引起的过去80万年来最暖的一个间冰期,但鲜有人研究末次间冰期中北非季风的响应.因此,本文基于CMIP6多模式模拟结果对比研究了末次间冰期和SSP5-8.5情景下北非季风的响应,发现末次间... 详细信息

与人为强迫引起的全球变暖相比,末次间冰期是轨道强迫引起的过去80万年来最暖的一个间冰期,但鲜有人研究末次间冰期中北非季风的响应.因此,本文基于CMIP6多模式模拟结果对比研究了末次间冰期和SSP5-8.5情景下北非季风的响应,发现末次间冰期下北非季风平均降水及其降水变率均远大于SSP5-8.5情景下的结果.轨道强迫导致的北大西洋暖于南大西洋增加了北非季风环流和平均降水,同时,南北大西洋海温梯度变化通过增强热带北大西洋的海气相互作用增大了海温梯度和撒哈拉低压的变率,从而增强了北非季风降水变率.

关键词：北非季风降水变率末次间冰期全球变暖

来源：评论

学校读者我要写书评

暂无评论

Toward activity mapping for Artifact-Centric business process

引用

International Journal of u- and e- Service, Science and Technology 2016年第6期9卷 421-432页

作者： Yin, Yuyu Zhu, Zhengshuang Gao, Min Song, Aihua College of Electrical Engineering Zhejiang University HangzhouZhejiang310027 China School of Computer Science and Technology Hangzhou Dianzi University HangzhouZhejiang310018 China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education HangzhouZhejiang310018 China

The existing method of task mapping between process models is mostly based on the similarity of labels to get the similarity between tasks, which is affected by a single factor and easy to cause errors. This paper proposes a task mapping method for Artifact-Centric business process analyzes the data operation in business process execution. At first we add the description of data operation to EZ-Flow model. Secondly select the similar artifact attributes of the two business artifact by whole artifacts similarity calculation and based them to calculate two tasks’ similarity by label similarity, artifact operation similarity and context similarity calculations. Finally, the task mapping comes from the optimal selection of tasks’ similarities. Experimental results verify the effectiveness of the method, and show that the method reflects the data operation characteristics of business process model, as artifact task mapping of the process model provides a feasible method. © 2016 SERSC.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm 29

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

29th IEEE International Conference on Parallel and Distributed systems, ICPADS 2023

作者： Zeng, Yan Huang, Chengchuang Ni, Yijie Zhou, Chunbao Zhang, Jilin Wang, Jue Zhou, Mingyao Xue, Meiting Zhang, Yunquan Hangzhou Dianzi University School of Computer Science and Technology Hangzhou310018 China Ministry of Education Key Laboratory for Modeling and Simulation of Complex Systems Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Hangzhou Dianzi University School of ITMO Joint Institute Hangzhou310018 China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing100086 China HuaWei China Institute of Computing Technology of the Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing100086 China

ISBN: (纸本)9798350330717

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network's dataflow graph and device cluster's topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method. © 2023 IEEE.

关键词： Auto-Parallel Distributed machine learning Genetic algorithm Integer linear programming Model parallelism

来源：评论

学校读者我要写书评

暂无评论

Virtual Page Behavior Based Page Management Policy for Hybrid Main Memory in Cloud Computing

Virtual Page Behavior Based Page Management Policy for Hybri...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Jie Huang Xuan Zhang Guangjie Han Gangyong Jia Huizi Liyou Jian Wan Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou China Department of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Department of Information & Communication Systems Hohai University Chanqzhou China School of Information and Electronic Engineering Zhejiang University of Science and Technology Hangzhou

ISBN: (纸本)9781509056972

A new generation memory, Non-Volatile Memory (NVM), such as Phase-Change Memory (PCM), has been adopted together with DRAM in the main memory to form the hybrid main memory for low energy consumption and high capacity. The biggest challenge of hybrid memory is how to decrease the average memory access cost for the higher cost of NVM's read/write operation. Currently, most researches are based on migration. However, the page migration itself is a high cost operation. And the migration based policy produces many migration operations, which induces high cost in memory access. Therefore, in order to decrease the cost, we present a virtual page behavior based page management policy (VBPM) in this paper. According to the virtual pages' behavior, we allocate virtual pages into DRAM or PCM physical pages correspondingly. The whole process is migration independent. The experimental results show our VBPM decreases the average memory access time by 24%, moreover, VBPM improves real-time performance in critical path.

关键词： Phase change materials Random access memory Memory management Algorithm design and analysis Resource management Nonvolatile memory Cloud computing

来源：评论

学校读者我要写书评

暂无评论

simulation of Centennial-Scale Drought Events over Eastern China during the Past 1500 Years

引用

Journal of Meteorological Research 2017年第1期31卷 17-27页

作者： Weiyi SUN Jian LIU Zhiyuan WANG key laboratory for virtual geographic environment(nanjing normal university) ministry of educationstate key laboratory cultivation base of geographical environment evolution(jiangsu province)School of Geography ScienceNanjing Normal UniversityNanjing 210023 Jiangsu Provincial Key Laboratory for Numerical Simulation of Large Scale Complex Systems School of Mathematical ScienceNanjing Normal UniversityNanjing 210023 Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing 210023

The characteristics and causes of centennial-scale drought events over eastern China during the past 1500 years were explored based on simulations of the Community Earth System Model （CESM）. The results show that centenni- al-scale drought events over eastern China occurred during the periods of 622-735 （Drought period 1, D1） and 1420-1516 （Drought period 2, D2） over the past 1500 years, which is comparable with climate proxy data. In D1, the drought center occurred in northern China and the Yangtze River valley; however, in southern China, precipitation was much more than usual. In D2, decreased precipitation was found across almost the whole region of eastern China. The direct cause of these two drought events was the weakened East Asian summer monsoon, and the specif- ic process was closely linked to the air-sea interaction of the Indo-Pacific Ocean. In DI, regions of maximum cool- ing were observed over the western Pacific, which may have led to anomalous subsidence, weakening the Walker cir- culation, and reducing the northward transport of water vapor. Additionally, upward motion occurred over southern China, strengthening convection and increasing precipitation. In D2, owing to the decrease in the SST, subsidence dominated the North Indian Ocean, blocking the low-level cross-equatorial flow, enhancing the tropical westerly an- omalies, and reducing the northward transport of moisture. Additionally, descending motion appeared in eastern China, subsequently decreasing the precipitation over the whole region of eastern China. The anomalous cooling of the Indo-Pacific Ocean SST may have been caused by the persistently low solar irradiation in D1; whereas, in D2, this characteristic may have been influenced not only by persistently low solar irradiation, but frequent volcanic erup- tions too.

关键词： CESM centennial-scale drought eastern China East Asian summer monsoon

来源：评论

学校读者我要写书评

暂无评论

A Travel Time Prediction Method for Urban Road Traffic Sensors Data

A Travel Time Prediction Method for Urban Road Traffic Senso...

引用

International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)

作者： Guangyu Zhu Kang Song Peng Zhang Ministry of Education Key Laboratory of System Control and Information Processing Shanghai China MOE Key Laboratory for Transportation Complex Systems- Theory and Technology Beijing Jiaotong University Beijing China Beijing Municipality Key Laboratory of Urban Traffic Operation Simulation and Decision Support Beijing China

Travel time parameters obtained from road traffic sensors data play an important role in traffic management practice. In this paper, a travel time analysis and prediction model was established for urban road traffic sensors data based on the change point analysis algorithm and ARIMA model. Firstly, time series of travel time parameters were clustered by using change point mining algorithm after traffic sensors data preprocessing. Then, a travel time prediction model was established based on ARIMA model. Finally, the model was verified with high accuracy through simulation by using multiple sets of data and analysis of its practicability was done.

关键词： Predictive models Data models Roads Time series analysis Detectors Analytical models

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：