Search

In largely distributed clusters, computing nodes are geographically deployed in various computing sites. Information processed in a distributed cluster is shared among a group of distributed processes or users by virtue of messages passing protocols (e.g. message passing interface — MPI) running on the Internet. Because of the open accessible nature of the Internet, data encryption for these large-scale distributed clusters becomes a non-trivial and challenging problem. To address this issue, we enhanced the security of the MPI (Message Passing Interface) protocol by encrypting and decrypting messages sent and received among computing nodes. In this study we focused on MPI rather than other protocols because MPI is one of the most popular communication protocols for cluster computing environments. From among a variety of MPI implementations, we picked MPICH2 developed by the Argonne National Laboratory. The design goal of MPICH2 — a widely used MPI implementation — is to combine portability with high performance. We integrated encryption algorithms into the MPICH2 library so that data confidentiality of MPI applications could be readily preserved without a need to change the source codes of the MPI applications. since we provide a security enhanced MPI-library with the standard MPI interfact, data communications of a conventional MPI program can be secured without converting the program into the corresponding secure version. We used Sandia Micro Benchmark and Intel MPI Benchmarks to evaluate and compared the performance of original MPICH2 and Enhanced Security MPICH2. According to the performance evaluation, ES-MPICH2 provides secured Message Passing Interface by sacrificing reasonable system performance.

Storage of raster metadata is a key topic in spatial database. Although there are a few of abstract standards on raster metadata, there is not implement standard about it. This paper concludes three storage models implemented in current spatial databases and discusses their advantages and disadvantages. After that analyzing, the paper proposes a mixed storage method which is used the relational table to store structured metadata and used XML to store non-structured metadata, and gives its implementation solution.

this paper research on spatial information service laws of development and application from angle of model and put forward the basic conception of spatial information service model basing on information service model. It presents a complete structure of model, and detailedly explains elements, the main characteristics and principles of interaction. Consider that the reciprocity between the various elements is the main inner factor which can produce a variety of different services type, and thus lead to different spatial information services with a variety of different forms. At last this paper accord to the relationship between the inner factor and elements to bring forward the abstract services classification results which currently can cover almost all the spatial information service types, and give theoretical support.

Using the monthly averaged NOAA AVHRR sea surface temperature data from January 1985 to December 2008, this paper extracted the monthly averaged position of western Pacific warm pool eastern edge in El Nino, La Nina and normal months. The averaged position during normal months is seasonal distribution with the shape of ‘****’, in which there were three inflexions locating about along 9°N latitude, equator and 15°S latitude, and the seasonal changes of eastern edge along the equator inflexion is not same dramatic as along 9°N and 15°S latitude. While in the duration of ENSO, the zonal displacement anomalies to eastward/westward along the equator are more sensitive than other regions to analyze the relationships with ENSO. In addition, based on the correlation analysis, the paper addressed the temporal response of ENSO to zonal displacement anomalies of WPWP eastern edge.

MapReduce has become an important distributed processing model for large-scale data-intensive applications like data mining and web indexing. Hadoop-an open-source implementation of MapReduce is widely used for short jobs requiring low response time. The current Hadoop implementation assumes that computing nodes in a cluster are homogeneous in nature. Data locality has not been taken into account for launching speculative map tasks, because it is assumed that most maps are data-local. Unfortunately, both the homogeneity and data locality assumptions are not satisfied in virtualized data centers. We show that ignoring the data-locality issue in heterogeneous environments can noticeably reduce the MapReduce performance. In this paper, we address the problem of how to place data across nodes in a way that each node has a balanced data processing load. Given a dataintensive application running on a Hadoop MapReduce cluster, our data placement scheme adaptively balances the amount of data stored in each node to achieve improved data-processing performance. Experimental results on two real data-intensive applications show that our data placement strategy can always improve the MapReduce performance by rebalancing data across nodes before performing a data-intensive application in a heterogeneous Hadoop cluster.

Cluster storage systems are essential building blocks for many high-end computing infrastructures. Although energy conservation techniques have been intensively studied in the context of clusters and disk arrays, improving energy efficiency of cluster storage systems remains an open issue. To address this problem, we describe in this paper an approach to implementing an energy-efficient cluster storage system or ECOS for short. ECOS relies on the architecture of cluster storage systems in which each I/O node manages multiple disks - one buffer disk and several data disks. Given an I/O node, the key idea behind ECOS is to redirect disk requests from data disks to the buffer disk. To balance I/O load among I/O nodes, ECOS might redirect requests from one I/O node into the others. Redirecting requests is a driving force of energy saving, and the reason is two-fold. First, ECOS makes an effort to keep buffer disks active while placing data disks into standby in a long time period to conserve energy. Second, ECOS reduces the number of disk spin downs/ups in I/O nodes. The idea of ECOS was implemented in a Linux cluster, where each I/O node contains one buffer disk and two data disks. Experimental results show that ECOS improves the energy efficiency of traditional cluster storage systems where buffer disks are not employed. Adding one extra buffer disk into each I/O node seemingly has negative impact on energy saving. Interestingly, our results indicate that ECOS equipped with extra buffer disks is more energy efficient than the same cluster storage system without the buffer disks. The implication of the experiments is that using existing data disks in I/O nodes to perform as buffer disks can achieve even higher energy efficiency.

The Popular Disk Concentration (PDC) technique and the Massive Array of Idle Disks (MAID) technique are two effective energy saving schemes for parallel disk systems. The goal of PDC and MAID is to skew I/O load towards a few disks so that other disks can be transitioned to low power states to conserve energy. I/O load skewing techniques like PDC and MAID inherently affect reliability of parallel disks because disks storing popular data tend to have high failure rates than disks storing cold data. To achieve good tradeoffs between energy efficiency and disk reliability, we first present a reliability model to quantitatively study the reliability of energy-efficient parallel disk systems equipped with the PDC and MAID schemes. Then, we propose a novel strategy—disk swapping—to improve disk reliability by alternating disks storing hot data with disks holding cold data. We demonstrate that our disk-swapping strategies not only can increase the lifetime of cache disks in MAID-based parallel disk systems, but also can improve reliability of PDC-based parallel disk systems.

Modeling and representing spatio-temporal process is the key foundation for analyzing geographic phenomenon and acquiring spatio-temporal high-level knowledge. Spatio-temporal representation methods with bottom-up approach based on object modeling view lack of explicit definition of geographic phenomenon and finer-grained representation of spatio-temporal causal relationships. Based on significant advances in data modeling of spatio-temporal object and event, aimed to represent discrete regional dynamic phenomenon composed with group of spatio-temporal objects, a regional spatio-temporal process description method using Top-Down Hierarchical approach (STP-TDH) is proposed and a data organization structure based on relational database is designed and implemented which builds up the data structure foundation for carrying out advanced data utilization and decision-making. The land use application case indicated that process modeling with top-down approach was proved to be good with the spatio-temporal cognition characteristic of our human, and its hierarchical representation framework can depict dynamic evolution characteristic of regional phenomenon with finer-grained level and can reduce complexity of process description.

Being short of evolution mechanisms, theories of spatio-temporal representation and modeling have great challenges to describe and represent the continuity and gradual geographical entities, still less deeper information retrievals and knowledge mining. The spatio-temporal dynamic semantics, which contains geographical entities, changes of entities and evolution mechanisms, is presented. According to the intrinsic process characteristics of dynamic entities, a hierarchical semantics structure and process object sequences included by level are given. This paper describes the process relationships and behaviors, and formalizes them into evolution operators, which subdivide into the process recurrence operators and recurrence ones. Based on the object-oriented technologies, the evolution operators are integrated into process object sequences, and a process-oriented dual representation framework on process objects' recurrence and recursion (DRF-PORR) is presented as well. And finally, as a case study, the typical oceanographic phenomena are taken to carry out the case modeling.

This chapter discusses Open Source databases including two modes of spatial data management, two different key standards for spatial databases, the leading Open Source databases including MySQL, PostgreSQL, FireBird, Ingres and MaxDB, and summarises extending methods and the use of PostGIS and MySQL.

In this paper, we investigate the use of a family of transform domains in embedding hidden data.A new date hiding scheme that is based a pair of unmatched orthogonal transforms has been developed. The hidden message signal is transmitted via the residual channel of two different parameterized slant transforms. The properties of residual channel of parameterized slant transforms are characterized and performance of proposed scheme have been analyzed and simulated. We also discuss on the performance of the scheme and basis selection.

Integrative management of massive spatio-temporal data and the relevant capabilities for time series analysis are important research targets of new generation GIS software architecture. At present, solid developments are imperatively needed in technology for effective organization and storage of massive spatio-temporal data. Oriented to spatio-temporal multi-dimension structure, a massive spatio-temporal data seamless organization and storage model based on spatio-temporal partition (STP), spaito-temporal clustering (STC) is presented, and the test on single table of 2GB to 60 GB shows that integration of STP and STC can improve performance of spaito-temporal search effectively.

The spatial data are processed via editing, query and other complicated analysis with spatial arithmetic operators provided by Oracle Spatial and SQL. In general, abnormal conditions will not occur in the operation with spatial arithmetic operators. In case the number of points of a polygon reaches 60000 or the number of inner rings of a polygon exceeds 200, errors may occur in the intersection overlay operation for spatial geometrical data and the connection between the system and Oracle database will be interrupted. For specific situation of GIS application in China, a polygon of a single parcel, as may occur in land resource investigati on, sometimes includes 90000 points, even exceeding 120000 points, and the number of inner rings may far exceed 200. A bug is discovered by the authors in the application of spatial overlay analysis on the national city and county administrative map and national land use map at scale of 1:4000000. After a lot of tests and discuss with Ora cle Corporation, the bug is finally confirmed by

With the fast development of GIS technology and improvement of the GIS application technology,higher requirements have been put forward to the spatial database connectivity and accessibility.This study first proposes a comparative analysis on cross-sectoral large-scale shared connection to spatial database,thus to point out the hard-to-achieve synchronization updating during different data types conversion.Direct data access model cannot be fully compliance with the data type updating.The spatial extension model of the relational database is dissatisfactory in performances as well as professional spatial analysis.The support of Web Service model is insufficient for non-standard spatial data types;the protocols provided by software providers are of great specificity and difficulty to be extended by third parties.Then in this article,the interfaces of heterogeneous databases connectivity are analyzed deeply.Currently there are two categories of interfaces which are the relational database access interfaces and spatial database standard interfaces.Based on the analysis,the article proposes the 'Opening Geospatial Database Connectivity(OGDC)' interfaces mechanism and specifications to provide a completely new model that a series of standard interfaces provided by several GIS platform software providers is jointly realized by database providers or data providers based on these standard interfaces.Detailed introductions are presented for the OGDC designs,technical features,implementation techniques,and applications.Finally,the feasibility and advantages of these proposed standards and specifications are demonstrated by a prototype using the OGDC from the domestic-developed distributed spatial database software 'BeyonDB'.And the prototype shows that OGDC could perfectly take account of the functionality,the efficiency and the usability of the spatial database connectivity,thus to provide a new application model for the standardized sharing and continual utilizing of the heterogeneous spatial database.