A Novel Architecture of Metadata Management System Based on Intelligent Cache

This paper introduces a novel architecture of metadata management system based on intelligent cache called Metadata Intelligent Cache Controller （MICC）. By using an intelligent cache to control the metadata system, MICC can deal with different scenarios such as splitting and merging of queries into sub-queries for available metadata sets in local, in order to reduce access time of remote queries. Application can find results patially from local cache and the remaining portion of the metadata that can be fetched from remote locations. Using the existing metadata, it can not only enhance the fault tolerance and load balancing of system effectively, but also improve the efficiency of access while ensuring the access quality.

Multi-Level Web Cache Model Used in Data Grid Application

This paper proposed a novel multilevel data cache model by Web cache （MDWC） based on network cost in data grid. By constructing a communicating tree of grid sites based on network cost and using a single leader for each data segment within each region, the MDWC makes the most use of the Web cache of other sites whose bandwidth is as broad as covering the job executing site. The experiment result indicates that the MDWC reduces data response time and data update cost by avoiding network congestions while designing on the parameters concluded by the environment of application.

Dynamic Replication Strategies in Data Grid

Dynamic data replication is a technique used in data grid environments that helps to reduce access latency and network bandwidth utilization. Replication also increases data availability thereby enhancing system reliability. In this paper we discuss the issues with single-location strategies in large-scale data integration applications, and examine potential multiple-location schemes. Dynamic multiple-location replication is NP-complete in nature. We therefore transform the multiple-location problem into several classical mathematical problems with different parameter settings, to which efficient approximation algorithms apply experimental results indicate that unlike single-location strategies our multiple-location schemes are efficient with respect to access latency and bandwidth consumption, especially when the requesters of a data set are distributed over a large scale of locations.

Development of data acquisition and over-current protection systems for a suppressor-grid current with a neutral-beam ion source

Neutral beam injection is one of the effective auxiliary heating methods in magnetic-confinementfusion experiments. In order to acquire the suppressor-grid current signal and avoid the grid being damaged by overheating, a data acquisition and over-current protection system based on the PXI（PCI e Xtensions for Instrumentation） platform has been developed. The system consists of a current sensor, data acquisition module and over-current protection module. In the data acquisition module,the acquired data of one shot will be transferred in isolation and saved in a data-storage server in a txt file. It can also be recalled using NBWave for future analysis. The over-current protection module contains two modes： remote and local. This gives it the function of setting a threshold voltage remotely and locally, and the forbidden time of over-current protection also can be set by a host PC in remote mode. Experimental results demonstrate that the data acquisition and overcurrent protection system has the advantages of setting forbidden time and isolation transmission.

Big Data of Home Energy Management in Cloud Computing

A smart grid is the evolved form of the power grid with the integration of sensing,communication,computing,monitoring,and control technologies.These technologies make the power grid reliable,efficient,and economical.However,the smartness boosts the volume of data in the smart grid.To obligate full benefits,big data has attractive techniques to process and analyze smart grid data.This paper presents and simulates a framework to make sure the use of big data computing technique in the smart grid.The offered framework comprises of the following four layers:(i)Data source layer,(ii)Data transmission layer,(iii)Data storage and computing layer,and(iv)Data analysis layer.As a proof of concept,the framework is simulated by taking the dataset of three cities of the Pakistan region and by considering two cloud-based data centers.The results are analyzed by taking into account the following parameters:(i)Heavy load data center,(ii)The impact of peak hour,(iii)High network delay,and(iv)The low network delay.The presented framework may help the power grid to achieve reliability,sustainability,and cost-efficiency for both the users and service providers.

Spatial Interpolation of Daily Precipitation in China:1951-2005

Climate research relies heavily on good quality instrumental data; for modeling efforts gridded data are needed. So far, relatively little effort has been made to create gridded climate data for China. This is especially true for high-resolution daily data. This work, focuses on identifying an accurate method to produce gridded daily precipitation in China based on the observed data at 753 stations for the period 1951-2005. Five interpolation methods, including ordinary nearest neighbor, local polynomial, radial basis function, inverse distance weighting, and ordinary kriging, have been used and compared. Cross-validation shows that the ordinary kriging based on seasonal semi-variograms gives the best performance, closely followed by the inverse distance weighting with a power of 2. Finally the ordinary kriging is chosen to interpolate the station data to a 18 km× 18 km grid system covering the whole country. Precipitation for each 0.5°×0.5° latitude-longitude block is then obtained by averaging the values at the grid nodes within the block. Owing to the higher station density in the eastern part of the country, the interpolation errors are much smaller than those in the west （west of 100°E）. Excluding 145 stations in the western region, the daily, monthly, and annual relative mean absolute errors of the interpolation for the remaining 608 stations are 74%, 29%, and 16%, respectively. The interpolated daily precipitation has been made available on the internet for the scientific community.

PACS is only in the Beginning of Being Used as Clinical Research Tools

The PACS concept was introduced in 19821, after more than twenty years of technical advancements;it has become an integrated component of today’s healthcare delivery system.PACS is now in the beginning of being used as a clinical research tool.2Among others,this paper describes four PACS-based research activities: medical imaging informatics, medical imaging Data Grid, combining PACS and teleradiology operations, and computer-assisted detection and diagnosis(CAD). In medical imaging informatics (MII), we first introduce its infrastructure and the five layer of software architecture. The description of a new MII training program supported by the National Institute of Biomedical Imaging and Bioengineering (NIBIB), National institutes of Health (NIH), USA is followed. The training program accepts candidates with medical and or biomedical engineering background. The goal is to cross-train multi-disciplinary individuals to be future leaders in the field of medical imaging informatics. Grid computing is a new paradigm combining computing, networking, information and storage technologies to advance the conventional distributing computing to the next level. One resource in Grid Computing is the Data Grid. We describe the use of Data Grid concept in medical imaging applications based on the five layer of the open source Globus toolkit 4 (GT4). Three examples are given. First, a Data Grid specifically designed for PACS image backup and disaster recovery developed at the Imaging and Informatics Laboratory (IPI), USC is illustrated. The second application is for image-based clinical trials using three international sites at IPI, USC, USA; the PACS Lab, Hong Kong Polytechnic University, Hong Kong; and the Heart Institute, Sao Paulo, Brazil In combining PACS and teleradiology operations , a Data Grid model is proposed to combinetwo disjoint ,and yet ,daily used PACS and telera-diology operations as one integrated system in a large-scale enterprise level . Methods of combining workflows ,storage ,and reading of PACS and teleradiology i mages are detailed .The last work-in-progress research is the in-tegration of CAD results with daily PACS workflow. The integration methods are based on DICOMScreen Captured and Structured Report Stan-dards ; and several IHE (Integrating the Healthcare Enterprise) Workflow Profiles .

Attribute-based keyword search encryption for power data protection

To protect the privacy of power data,we usually encrypt data before outsourcing it to the cloud servers.However,it is challenging to search over the encrypted data.In addition,we need to ensure that only authorized users can retrieve the power data.The attribute-based searchable encryption is an advanced technology to solve these problems.However,many existing schemes do not support large universe,expressive access policies,and hidden access policies.In this paper,we propose an attributebased keyword search encryption scheme for power data protection.Firstly,our proposed scheme can support encrypted data retrieval and achieve fine-grained access control.Only authorized users whose attributes satisfy the access policies can search and decrypt the encrypted data.Secondly,to satisfy the requirement in the power grid environment,the proposed scheme can support large attribute universe and hidden access policies.The access policy in this scheme does not leak private information about users.Thirdly,the security analysis and performance analysis indicate that our scheme is efficient and practical.Furthermore,the comparisons with other schemes demonstrate the advantages of our proposed scheme.

Possible Impact of Spatial and Temporal Non-Uniformity in Land Surface Temperature Data on Trend Estimation

The present work investigates possible impact of the non-uniformity in observed land surface temperature on trend estimation, based on Climatic Research Unit （CRU） Temperature Version 4 （CRUTEM4） monthly temperature data-sets from 1900 to 2012. The CRU land temperature data exhibit remarkable non-uniformity in spatial and temporal features. The data are characterized by an uneven spatial distribution of missing records and station density, and dis-play a significant increase of available sites around 1950. Considering the impact of missing data, the trends seem to be more stable and reliable when estimated based on data with 〈 40% missing percent, compared to the data with above 40% missing percent. Mean absolute error （MAE） between data with 〈 40% missing percent and global data is only 0.011℃ （0.014℃） for 1900-50 （1951-2012）. The associated trend estimated by reliable data is 0.087℃ decade^-1 （0.186℃ decade^-l） for 1900-50 （1951-2012）, almost the same as the trend of the global data. However, due to non-uniform spatial distribution of missing data, the global signal seems mainly coming from the regions with good data coverage, especially for the period 1900-50. This is also confirmed by an extreme test conducted with the records in the United States and Africa. In addition, the influences of spatial and temporal non-uniform features in observation data on trend estimation are significant for the areas with poor data coverage, such as Africa, while insig-nificant for the countries with good data coverage, such as the United States.

Input database related uncertainty of Biome-BGCMuSo agroenvironmental model outputs

Gridded model assessments require at least one climatic and one soil database for carrying out the simulations.There are several parallel soil and climate database development projects that provide sufficient,albeit considerably different,observation based input data for crop model based impact studies.The input database related uncertainty of the Biome-BGCMuSo agro-environmental model outputs was investigated using three and four different gridded climatic and soil databases,respectively covering an area of nearly 100.000 km2 with 1104 grid cells.Spatial,temporal,climate and soil database selection related variances were calculated and compared for four model outputs obtained from 30-year-long simulations.The choice of the input database introduced model output variability that was comparable to the variability the year-to-year change of the weather or the spatial heterogeneity of the soil causes.Input database selection could be a decisive factor in carbon sequestration related studies as the soil carbon stock change estimates may either suggest that the simulated ecosystem is a carbon sink or to the contrary a carbon source on the long run.Careful evaluation of the input database quality seems to be an inevitable and highly relevant step towards more realistic plant production and carbon balance simulations.

Network and data location aware approach for simultaneous job scheduling and data replication in large-scale data grid environments

Data Grid integrates graphically distributed resources for solving data intensive scientific applications. Effective scheduling in Grid can reduce the amount of data transferred among nodes by submitting a job to a node, where most of the requested data files are available. Scheduling is a traditional problem in parallel and distributed system. However, due to special issues and goals of Grid, traditional approach is not effective in this environment any more. Therefore, it is necessary to propose methods specialized for this kind of parallel and distributed system. Another solution is to use a data replication strategy to create multiple copies of files and store them in convenient locations to shorten file access times. To utilize the above two concepts, in this paper we develop a job scheduling policy, called hierarchical job scheduling strategy （HJSS）, and a dynamic data replication strategy, called advanced dynamic hierarchical replication strategy （ADHRS）, to improve the data access efficiencies in a hierarchical Data Grid. HJSS uses hierarchical scheduling to reduce the search time for an appropriate computing node. It considers network characteristics, number of jobs waiting in queue, file locations, and disk read speed of storage drive at data sources. Moreover, due to the limited storage capacity, a good replica replacement algorithm is needed. We present a novel replacement strategy which deletes files in two steps when free space is not enough for the new replica： first, it deletes those files with minimum time for transferring. Second, if space is still insufficient then it considers the last time the replica was requested, number of access, size of replica and file transfer time. The simulation results show that our proposed algorithm has better performance in comparison with other algorithms in terms of job execution time, number of intercommunications, number of replications, hit ratio, computing resource usage and storage usage.

QoS-aware replica placement for data intensive applications

In recent years, with the rapid development of data intensive applications, data replication has become an enabling technology for the data grid to improve data availability, and reduce file transfer time and bandwidth consumption. The placement of replicas has been proven to be the most difficult problem that must be solved to realize the process of data replication. This paper addresses the quality of service （QoS） aware replica placement problem in data grid, and proposes a dynamic programming based replica placement algorithm that not only has a QoS requirement guarantee, but also can minimize the overall replication cost, including storage cost and communication cost. By simulation, experiments show that the replica placement algorithm outperforms an existing popular replica placement technique in data grid.

RTS-PGATS based approach for data-intensive scheduling in data grids

Grid computing is the combination of com- puter resources in a loosely coupled, heterogeneous, and geographically dispersed environment. Grid data are the data used in grid computing, which consists of large-scale data-intensive applications, producing and consuming huge amounts of data, distributed across a large number of machines. Data grid computing composes sets of independent tasks each of which require massive distributed data sets that may each be replicated on different resources. To reduce the completion time of the application and improve the performance of the grid, appropriate computing resources should be selected to execute the tasks and appropriate storage resources selected to serve the files required by the tasks. So the problem can be broken into two sub-problems： selection of storage resources and assignment of tasks to computing resources. This paper proposes a scheduler, which is broken into three parts that can run in parallel and uses both parallel tabu search and a parallel genetic algorithm. Finally, the proposed algorithm is evaluated by comparing it with other related algorithms, which target minimizing makespan. Simulation results show that the proposed approach can be a good choice for scheduling large data grid applications.

Element-Partition-Based Methods for Visualization of 3D Unstructured Grid Data

E lement- partition- based methods for visualization of 3D unstructured grid data are presented. First, partition schemes for common elements, including curvilinear tetrahedra, pentahedra, hexahedra, etc., are given, so that complex elements can be divided into several rectilinear tetrahedra, and the visualization processes can be simplified.Then, a slice method for cloud map and an iso-surface method based on the partition schemes are described.

Method for replica creation in data grids based on complex networks

In order to reduce makespan and storage consumption in data grids, a node selection model for replica creation is proposed. The model is based on the degree distribution of complex networks. We define two candidate replica nodes： a degree-based candidate pool and a frequency-based candidate pool, through which a degree-based candidate pool is defined in consideration of onsidering the access frequency; a candidate pool-based frequency is also defined. The data replica is copied to the node with the minimum Local cost in the two pools. Further, this paper presents and proves a replica creation theorem. A dynamic multi-replicas creation algorithm （DMRC） is also provided. Simulation results show that the proposed method may simultaneously reduce makespan and data used in space storage consumption.

Changes in daily extreme precipitation events in South China from 1961 to 2011

Based on the daily precipitation from a 0.5°×0.5° gridded dataset and meteorological stations during 1961-2011 released by National Meteorological Information Center, the reliability of this gridded precipitation dataset in South China was evaluated. Five precipitation indices recommended by the World Meteorological Organization （WMO） were selected to investigate the changes in precipitation extremes of South China. The results indicated that the bias between gridded data interpolated to given stations and the corresponding observed data is limited, and the proportion of the number of stations with bias between -10% and 0 is 50.64%. The correlation coefficients between gridded data and observed data are generally above 0.80 in most parts. The average of precipitation indices shows a significant spatial difference with drier northwest section and wetter southeast section. The trend magnitudes of the maximum 5-day precipitation （RX5day）, very wet day precipitation （R95）, very heavy precipitation days （R20mm） and simple daily intensity index （SDII） are 0.17 mm·a^-1, 1.14 mm·a^-1, 0.02 d·a^-1 and 0.01 mm·d^-1·a^-1, respectively, while consecutive wet days （CWD） decrease by -0.05 d·a^-1 during 1961-2011. There is spatial disparity in trend magnitudes of precipitation indices, and approximate 60.85%, 75.32% and 75.74% of the grid boxes show increasing trends for RX5day, SDII and R95, respectively. There are high correlations between precipitation indices and total precipitation, which is statistically significant at the 0.01 level.

1961-2013年青藏高原雪雨比变化（英文）

On the basis of two gridded datasets of daily precipitation and temperature with a spatial resolution of 0.5°×0.5°, and meteorological station data released by the National Meteorological Information Center （NMIC） during 1961-2013, the spatial and temporal variations of total amount of precipitation, amount of rainfall, amount of snowfall and snowfall/rainfall ratio （S/R） in the Tibetan Plateau （TP） are analyzed using Sen＇s slope, the Mann-Kendall mutation test, Inverse Distance Weighting （IDW） and the Morlet wavelet. Total amount of precipitation and amount of rainfall generally show statistically significant increasing trends of 0.6 mm·a^-1 and 1.3 mm·a^-1, respectively, while amount of snowfall and SIR have significant decreasing trends of-0.6 mm·a^-1 and -0.5% a^-1, respectively. In most regions, due to significant increasing trends in total amount of precipitation and amount of rainfall, and significant decreasing trends in amount of snowfall, SIR shows a decreasing trend in the TP. Abrupt changes in total amount of precipitation, amount of rainfall, amount of snowfall and S/R are detected for 2005, 2004, 1996 and 1998, respectively. Total amount of precipitation, amount of rainfall, amount of snowfall and SIR are concentrated in cycles of approximately 5 years, 10 years, 16 years and 20 years, respectively. The trend magnitudes for total amount of precipitation and amount of rainfall all show decreasing-to-increasing trends with elevation, while amount of snowfall and SIR show decreasing trends.

Reconstruction of cropland spatial patterns and its spatiotemporal changes over the 20th century on the Songnen Plain, Northeast China

We initially estimated the cropland area at county level using local historical documents for the Songnen Plain （SNP） in the 1910s and 1930s. We then allocated this cropland area to grid cells with a size of 1 km ×1 km, using a range of cultivation possibilities from high to low; this was based on topography and minimum distances to rivers, settlements, and traffic lines. Cropland areas for the 1950s were obtained from the Land Use Map of Northeast China, and map vectorization was performed with ArcGIS technology. Cropland areas for the 1970s, 1980s, 1990s, 2000s, and 2010s were retrieved from Landsat images. We found that the cropland areas were 4.92 ×10^4 km^2 and 7.60 ×10^4 km^2, accounting for 22.8% and 35.2% of the total area of the SNP in the 1910s and 1930s, respectively, which increased to 13.14 × 10^4 km^2, accounting for 60.9% in the 2010s. The cropland increased at a rate of 1.18 ×10^4 km^2 per decade from the 1910s to 1970s while it was merely 0.285 ×10^4 km^2 per decade from the 1970s to 2010s. From the 1910s to 1930s, new cultivation mainly occurred in the central SNP while, from the 1930s to 1970s, it was mainly over the western and northern parts. This spatially explicit reconstruction could be offered as primary data for studying the effects of changes in human-induced land cover based on climate change over the last century.

Framework for Grid Manufacturing

With the development of networked manufacturing, it is more and more imminent to solve prob-lems caused by inherent limitations of network technology, such as heterogeneity, collaboration collision, and decentralized control. This paper presents a framework for grid manufacturing, which neatly combines grid technology with the infrastructure of advanced manufacturing technology. The paper studies grid-oriented knowledge description and acquisition, and constructs a distributed knowledge grid model. The pa-per also deals with the protocol of node description in collaborative design, and describes a distributed col-laborative design model. The protocol and node technology leads to a collaborative production model for grid manufacturing. The framework for grid manufacturing offers an effective and feasible solution for the problems of networked manufacturing. The grid manufacturing will become an advanced distributed manu-facturing model and promote the development of advanced manufacturing technologies.

Massive Storage Systems

To accommodate the explosively increasing amount of data in many areas such as scientific computing and e-Business, physical storage devices and control components have been separated from traditional computing systems to become a; scalable, intelligent storage subsystem that, when appropriately designed, should provide transparent storage interface, effective data allocation, flexible and efficient storage management, and other impressive features. The design goals and desirable features of such a storage subsystem include high performance, high scalability, high availability, high reliability and high security. Extensive research has been conducted in this field by researchers all over the world, yet many issues still remain open and challenging. This paper studies five different online massive storage systems and one offiine storage system that we have developed with the research grant support from China. The storage pool with multiple network-attached RAIDs avoids expensive store-and-forward data copying between the server and storage system, improving data transfer rate by a factor of 2 3 over a traditional disk array. Two types of high performance distributed storage systems for local-area network storage are introduced in the paper. One of them is the Virtual Interface Storage Architecture （VISA） where VI as a communication protocol replaces the TCP/IP protocol in the system. VISA＇s performance is shown to achieve better than that of IP SAN by designing and implementing the vSCSI （VI-attached SCSI） protocol to support SCSI commands in the VI network. The other is a fault-tolerant parallel virtual file system that is designed and implemented to provide high I/O performance and high reliability. A global distributed storage system for wide-area network storage is discussed in detail in the paper, where a Storage Service Provider is added to provide storage service and plays the role of user agent for the storage system. Object based Storage Systems not only store data but also adopt the attributes and methods of objects that encapsulate the data. The adaptive policy triggering mechanism （APTM）, which borrows proven machine learning techniques to improve the scalability of object storage systems, is the embodiment of the idea about smart storage device and facilitates the self-management of massive storage systems. A typical offiine massive storage system is used to backup data or store documents, for which the tape virtualization technology is discussed. Finally, a domain-based storage management framework for different types of storage systems is presented in the paper.