Architecture Design of Global Distributed Storage System for Data Grid

This paper describes the architecture of global distributed storage system for data grid. It focue on the management and the capability for the maximum users and maximum resources on the Internet, as well as performance and other issues.

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.

Note on Three Classes of Data Grid Operations

Traditional grid computing focuses on the movement of data to compute resources and the management of large scale simulations. Data grid computing focuses on moving the operations to the storage location and on operations on data collections. We present three types of data grid operations that facilitate data driven research: the manipulation of time series data, the reproducible execution of workflows, and the mapping of data access to software-defined networks. These data grid operations have been implemented as operations on collections within the NSF DataNet Federation Consortium project. The operations can be applied at the remote resource where data are stored, improving the ability of researchers to interact with large collections.

Prediction of three-dimensional ocean temperature in the South China Sea based on time series gridded data and a dynamic spatiotemporal graph neural network

Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related fields.Currently,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean temperature.Existing graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among data.In this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior knowledge.Temporal and spatial dependencies in the time series were then captured using temporal and graph convolutions.We also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid data.In this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea surface.We compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.

EASE-Grid投影风云卫星产品地理信息写入方法

风云卫星遥感数据服务网的卫星遥感产品数据集中,风云三系列气象卫星遥感产品数据集中很多采用的是等面积可伸缩地球网格(EASE-Grid)投影方式进行处理,实际应用中对使用者具有较高的数据处理能力要求,不利于遥感产品数据集的省级应用。基于数据集使用中的这些问题,该文以FY3D雪水当量数据集产品为例,采用程序化方法对EASE-Grid投影产品数据集的地理信息进行写入,通过构建地理坐标系参考对象和地理信息目录,将数据矩阵中写入地理信息并以GeoTiff格式文件输出。结果表明,经过该方法处理过的产品数据可与矢量文件实现准确的经纬度信息的匹配,降低了数据分析处理的难度。该方法具有较好的适用性,对于EASE-Grid的三种不同的投影方式均适用,可在一定程度上提高卫星遥感产品数据集的省级科研与应用水平。

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.

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.

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.

Gridding cropland data reconstruction over the agricultural region of China in 1820

Recent studies have demonstrated the importance of LUCC change with climate and ecosystem simulation, but the result could only be determined precisely if a high-resolution underlying land cover map is used. While the efforts based satellites have provided a good baseline for present land cover, what the next advancement in the research about LUCC change required is the development of reconstruction of historical LUCC change especially spatially-explicit historical dataset. Being different from other similar studies, this study is based on the analysis of historical land use patterns in the traditional cultivated region of China. Taking no account of the less important factors, altitude, slope and population patterns are selected as the major drivers of reclamation in ancient China, and used to design the HCGM （Historical Cropland Gridding Model, at a 60 km×60 km resolution）, which is an empirical model for allocating the historical cropland inventory data spatially to grid cells in each political unit. Then we use this model to reconstruct cropland distribution of the study area in 1820, and verify the result by prefectural cropland data of 1820, which is from the historical documents. The statistical analyzing result shows that the model can simulate the patterns of the cropland distribution in the historical period in the traditional cultivated region efficiently.

Application and research of global grid database design based on geographic information

Energy crisis and climate change have become two seriously concerned issues universally. As a feasible solution, Global Energy Interconnection(GEI) has been highly praised and positively responded by the international community once proposed by China. From strategic conception to implementation, GEI development has entered a new phase of joint action now. Gathering and building a global grid database is a prerequisite for conducting research on GEI. Based on the requirement of global grid data management and application, combining with big data and geographic information technology, this paper studies the global grid data acquisition and analysis process, sorts out and designs the global grid database structure supporting GEI research, and builds a global grid database system.

A Path-Based Approach for Data Aggregation in Grid-Based Wireless Sensor Networks

Sensor nodes in a wireless sensor network （WSN） are typically powered by batteries, thus the energy is constrained. It is our design goal to efficiently utilize the energy of each sensor node to extend its lifetime, so as to prolong the lifetime of the whole WSN. In this paper, we propose a path-based data aggregation scheme （PBDAS） for grid-based wireless sensor networks. In order to extend the lifetime of a WSN, we construct a grid infrastructure by partitioning the whole sensor field into a grid of cells. Each cell has a head responsible for aggregating its own data with the data sensed by the others in the same cell and then transmitting out. In order to efficiently and rapidly transmit the data to the base station （BS）, we link each cell head to form a chain. Each cell head on the chain takes turn becoming the chain leader responsible for transmitting data to the BS. Aggregated data moves from head to head along the chain, and finally the chain leader transmits to the BS. In PBDAS, only the cell heads need to transmit data toward the BS. Therefore, the data transmissions to the BS substantially decrease. Besides, the cell heads and chain leader are designated in turn according to the energy level so that the energy depletion of nodes is evenly distributed. Simulation results show that the proposed PBDAS extends the lifetime of sensor nodes, so as to make the lifetime of the whole network longer.

Research on Constructing Contoursfrom Regular Terrain GridsContaining Invalid Data

A new method for constructing contours from complicated terrain elevation grids containing invalid data is put forward. By using this method, the topological consistency of contours in groups can be maintained effectively and the contours can be drawn smoothly based on boundaries pre-searching and local correction. An experimental example is given to demonstrate that the contours constructed by this method are of good quality.

The data platform of national special environment and disaster field observation stations based on grid environment

The Data Platform of Resource and Environment—whose data mainly come from field observation stations,spatial observations,and internet service institutions—is the base of data analysis and model simulation in geoscience research in China.Among this integrated data platform,the tasks of the data platform of field observation stations are principally data collection,management,assimilation,and share service.Taking into consideration the distributing characteristics of the data sources and the service objects,the authors formulated the framework of the field observation stations' data platform based on the grid technology and designed its operating processes.The authors have further defined and analyzed the key functions and implementing techniques for each module.In a Linux operating system,validation tests for the data platform's function on data replication,data synchronization,and unified data service have been conducted under an environment that of the simulating field stations.

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.

Data Exchange in Grid Workflow

In existing web services-based workflow, data exchanging across the web services is centralized, the workflow engine intermediates at each step of the application sequence. However, many grid applications, especially data intensive scientific applications, require exchanging large amount of data across the grid services. Having a central workflow engine relay the data between the services would resu＇lts in a bottleneck in these cases. This paper proposes a data exchange model for individual grid workflow and multiworkflows composition respectively. The model enables direct communication for large amounts of data between two grid services. To enable data to exchange among multiple workflows, the bridge data service is used.

Operating Analysis and Data Mining System for Power Grid Dispatching

The dispatching center of power-grid companies is also the data center of the power grid where gathers great amount of operating information. The valuable information contained in these data means a lot for power grid operating management, but at present there is no special method for the management of operating data resource. This paper introduces the operating analysis and data mining system for power grid dispatching. The technique of data warehousing online analytical processing has been used to manage and analysis the great capacity of data. This analysis system is based on the real-time data of the power grid to dig out the potential rule of the power grid operating. This system also provides a research platform for the dispatchers, help to improve the JIT (Just in Time) management of power system.

基于CAMM和CLDAS的黄淮海冬小麦成熟期连阴雨时空特征

利用黄淮海地区2008—2023年的CLDAS数据和同期65个农业气象观测站的冬小麦花期、成熟期观测数据,订正机理性中国农业气象模式(CAMM)中发育模块(RAM)的参数,评估模式对冬小麦成熟期的模拟精度,而后重构格点化的历年成熟期日期,统计成熟期前6天后9天共16天的降水量和雨日数,随后基于连阴雨指标,研究连阴雨的时空分布特征。结果表明:(1)RAM模式对冬小麦成熟期具有较好的模拟能力,各站RMSE平均值为2.28±0.46 d,模拟值与实测值的R2为0.915。(2)黄淮海地区冬小麦成熟期降水量和雨日数均呈南北两端高中间低的空间分布格局,区域平均降水量为8.8~84.6 mm,平均值为31.9 mm,雨日数为1.0~9.1天,平均值为5.4天。(3)2008—2023年连阴雨灾害波动较大,其中2009、2013、2018和2023年较为严重,大致呈4~5年发生一次的周期性规律,且灾情呈加重的趋势。(4)连阴雨灾害在黄淮海地区北部很少发生,河北和山东交界处偶发,灾害高发重发区主要集中在河南省,尤其是郑州以南的驻马店和信阳一带最为严重,发生频率约为5年一遇,持续天数多在9天以上。

A Data Mining Algorithm Based on Distributed Decision-Tree in Grid Computing Environments

Recently, researches on distributed data mining by making use of grid are in trend. This paper introduces a data mining algorithm by means of distributed decision-tree,which has taken the advantage of conveniences and services supplied by the computing platform-grid,and can perform a data mining of distributed classification on grid.