CN101315424A - Multi-satellite remote sensing data integrated parallel ground pretreatment system - Google Patents
Multi-satellite remote sensing data integrated parallel ground pretreatment system Download PDFInfo
- Publication number
- CN101315424A CN101315424A CNA2008101350473A CN200810135047A CN101315424A CN 101315424 A CN101315424 A CN 101315424A CN A2008101350473 A CNA2008101350473 A CN A2008101350473A CN 200810135047 A CN200810135047 A CN 200810135047A CN 101315424 A CN101315424 A CN 101315424A
- Authority
- CN
- China
- Prior art keywords
- layer
- processing
- task
- data
- performance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Multi Processors (AREA)
Abstract
The invention relates to an integrated parallel ground preprocessing system for multi-satellite remote sensed data. The system comprises a hardware layer, a system supporting layer, a data processing and expanding layer, a task managing and dispatching layer and a user processing function combining layer, wherein the hardware layer provides hardware support for the preprocessing system; the system supporting layer provides a software support environment for the system; the data processing and expanding layer is provided with abstract function interfaces and public function combinational logics of various satellites and various sensors; the task managing and dispatching layer is used for realizing task dispatching and flow management; and the user processing function combining layer provides simple and practical flow combination interfaces for users. The preprocessing system has the advantages that the users can conveniently and uniformly expand processing, memory and network communication capacities of the system without modifying the processing program, thereby increasing the operating speed of the program; when new satellite remote sensed data enter the system and require processing, archiving, product production and distribution, function expansion can be completed only by adding processing modules of corresponding data into the system according to a certain template.
Description
Technical field
The present invention relates to preconditioning technique field, remotely-sensed data ground, particularly a kind of high-performance multi-satellite remote sensing data ground pretreatment system based on parallel machine gang fight structure.
Background technology
Remote sensing satellite ground pretreatment system is the system ensemble that collection satellite data file and management, data pre-service and product are created on one, is the important support system of earth observation from space system, be the incident space data obtain and Ground Application between tie.Develop rapidly along with infotech and sensor technology, satellite remote-sensing image spatial resolution, spectral resolution and temporal resolution improve greatly, the data acquisition amount increases 100-400 doubly on the star, corresponding data processing calculated amount has also increased 1000-10000 doubly, at the pressure of mass data processing like this, be restricted aspect the performance expansion based on traditional ground pretreatment system of minicomputer or workstation platform.Along with available remote sensing satellite quantity and corresponding remote sensor kind thereof constantly increase, and the degree of depth and range that people use remotely-sensed data constantly propose new requirement, remote sensing satellite ground pretreatment system is faced with new challenges and demand aspect reconstruction property and multiple product processing power flexibly, people wish to finish as much as possible the processing demands of oneself in pretreatment system, remote sensing satellite ground pretreatment system is being restricted aspect the function expansion.
Be the urgent problems that solve of needs how, be necessary to provide a kind of in performance and the multi-satellite remote sensing data integrated floor treatment method of function aspects favorable expandability satisfying the pretreated requirement of remotely-sensed data aspect performance and the function expansion.
Summary of the invention
The object of the present invention is to provide a kind of multi-satellite remote sensing data integrated parallel ground pretreatment system, solve the multistage product of many satellite datas, mass data fast processing problem.
The technical scheme that realizes the object of the invention is:
A kind of multi-satellite remote sensing data integrated parallel ground pretreatment system comprises:
Hardware layer, the hardware support that it provides pretreatment system comprises storage system and hardware facilities such as gigabit Ethernet or the contour performance network system of infiniband such as commercialization Network of Workstation, SAN/NAS;
The system support layer, the system software back-up environment is provided, the expansion of system performance, the remotely-sensed data pre-service is complicated computation-intensive, data-intensive and network-intensive type is used, and different processing capacities is to calculating, the requirement of storage and network performance also is not quite similar, this system realizes parallel computation by orthogonal design, parallel storage, the parallel network load blocks, make system at handling property, network performance, the memory property aspect can independently be expanded, and can be according to data processing characteristics complex optimum three performance, processing to data, the filing of data and production and distribution provide powerful system performance support, make and expansion of system performance height and efficient operation have reached the requirement of expanding as required at aspect of performance;
The data processing extension layer has the abstraction function interface of multiple satellite multiple sensors and public function combinations logic, and the concrete Processing Algorithm of all kinds of satellites and sensor realizes by the means of inheriting and add, and has guaranteed that algorithm function expands as required;
The task management dispatch layer, realize task scheduling and workflow management, pass through integrated high performance job scheduling system and Workflow Management System at this layer, realized the balanced and flow processing ability of operating load of multiple processing capacity, at described Workflow Management System, same flow process can be loaded twice and finish jointly task handling, is used to each phase process task to generate the relevant parameters file for the first time, is used to carry out each phase process task for the second time and finishes specific processing capacity.
User's processing capacity combination layer, for the user provides the path combination that is simple and easy to usefulness interface, the user can make up the treatment scheme that comprises multiple functions such as data processing, filing, production and distribution of various complexity.
Beneficial effect of the present invention: by the expansion of data processing function extension layer and user's processing capacity combination layer, realized the as required expansion of system in function aspects, not only can increase new multi-satellite remote sensing data Processing Algorithm and function, can also make up various basic processing functions, make the user can arbitrarily customize the Remote Sensing Data Processing flow process, satisfy the specific data processing demand of user; Have wide-open operation platform, at aspect of performance, the user just can make things convenient for processing, storage, the network communications capability of balanced expanding system under the situation of not revising handling procedure, improve the travelling speed of program; In function aspects, when new satellite remote sensing date enters system and needs processing, filing, production and distribution, only need processing module with corresponding data according to finishing function expansion in certain template adding system.
Description of drawings
With reference to the accompanying drawings the embodiment of the invention is described in further detail below.
Fig. 1 is the system architecture synoptic diagram of the embodiment of the invention.
Embodiment
As shown in Figure 1, the described multi-satellite remote sensing data integrated parallel ground pretreatment system of the embodiment of the invention comprises hardware layer, system support layer, data processing extension layer, task management dispatch layer and user's processing capacity combination layer; Wherein hardware layer provides the hardware support of pretreatment system, comprises storage system and hardware facilities such as gigabit Ethernet or the contour performance network system of infiniband such as commercialization Network of Workstation, SAN/NAS; The system support layer, the system software back-up environment is provided, pay attention to the expansion of system performance, realize parallel computation, parallel storage, parallel network load blocks by orthogonal design, the system that makes can independently expand aspect handling property, network performance, the memory property, and can be according to data processing characteristics complex optimum three performance, the parallel computation module comprises MPI, OpenMP, PVM etc., parallel memory module comprises PVFS, Lustre, StorNext etc., and the offered load module comprises the dispositions method of related softwares such as LVS, BigIP; At the data processing extension layer, have the abstraction function interface of multiple satellite multiple sensors and public function combinations logic, the concrete Processing Algorithm of all kinds of satellites and sensor realizes by the means of inheriting and adds, and guarantees that algorithm function expands as required; At task management and dispatching layer, realize task scheduling and workflow management, by integrated high performance job scheduling system and Workflow Management System, realize the balanced and flow processing ability of operating load of multiple processing capacity at this layer; At user's processing capacity combination layer, for the user provides the path combination that is simple and easy to usefulness interface, the user can make up the treatment scheme that comprises multiple functions such as data processing, filing, production and distribution of various complexity.
Generally the user submits to task to system, task scheduling layer in the system is received task, the explanation task is a workflow, submit to the Workflow Management layer of task scheduling layer, by the Workflow Management layer task is resolved into the stage task, submit to the job scheduling layer, the job scheduling layer is dispatched to interim task on the computing node in the group of planes according to the loading condition in the group of planes, the calculation task of execute phase task.The execution of workflow layer Control work stream repeats to call the despatching work that the task management layer carries out phased mission, up to the fixed task of the single gauge of finishing the work.
The user can increase new flow of task in original system.As former flow process be that the zero level data are obtained, systems radiate correction, system's geometry correction, output products then, need before systems radiate is proofreaied and correct, increase the operation of removing band now.Real-time method is very simple, and the user defines at user's sub-definite treatment scheme layer and comprises that the zero level data obtain, go band, systems radiate correction, system's geometry correction, the workflow of output products then, this workflow and a task name binding.When submitting this task name from now on to, just can carry out has increased the Processing tasks that removes band.
The user can increase the processing capacity of new satellite load data in original system.Can handle the processing of " No. one, Beijing " moonlet data as existing system, to increase the processing of " environment and disaster monitoring forecast moonlet " load now, the user only need be according to the interface of " data-processing interface abstract design layer " regulation, increase the processing capacity of new satellite data at " processing capacity specific implementation layer ", this function will be loaded in this pretreatment system automatically, realize the function expansion that many satellite datas are handled.
Task is the treatment scheme that is formed by a series of stage subtasks (functional module) organic assembling.Be to realize the dirigibility requirement of Utility Satellite ground pretreatment system to the data treatment scheme, the task management dispatch layer has been introduced dirigibility and the extensibility that workflow mechanism maximizes the system data treatment scheme.This treatment scheme is described with the xml file layout, deposits with the configuration file form, and therefore dynamic load when operation task can realize " hot plug " of functional component module in flow chart of data processing.Be that the Workflow Management layer will utilize self engine that description document is resolved, and each phased mission in the flow process handled according to the rule that pre-defines.In flow chart of data processing, same flow process can be loaded twice and finish task handling jointly.Be used to for the first time each phase process task to generate the relevant parameters file, be used to carry out each phase process task for the second time and finish specific processing capacity.Simultaneously, can set up the checkpoint as required on stream, handle with detection-phase whether correct execution is finished, pass through the flow process of detection, the follow-up task function of check point will no longer be performed, and the task management dispatch layer also provides self-defined checkpoint to detect the expanded function of content and crash handling strategy.System is in task processes, and the user can intervene (hang up, recover, cancel) effectively thereby the flow processing state is realized effective control, the management to task in the system.Task is handled simultaneously, and system is log information such as recording processing progress intactly, and the operator can check that flow of task handles operation informations such as progress and state by graphic interface.
For the flow chart of data processing that combines by a series of phased missions, workflow engine will resolve to the whole phased missions in each task new independently operation and be committed to the system task dispatch server, and obtain the job number of each new operation correspondence in dispatch server.System will be according to this job number inquiry job scheduling progress and status information subsequently, also can utilize this operation of hanging up, recover, cancel, reform of this job number according to dispatch command simultaneously.The task scheduling subsystem is supported task priority and task concurrency.Management service in the dispatch server will be put into the task scheduling pond to all task requests, simultaneously the scheduling strategy service is passed in the task requests instruction, policy service will be according to the available computational resources loading condition, to task in the task pool according to the priority order dispatch, the system that is assigned to executes the task according to the operation node that the predefine policy selection goes out.Move node simultaneously and also self loading condition is fed back to the scheduling strategy service, thereby the task scheduling subsystem can be realized load balancing automatically between computational resource regular.For realizing that to the quick pretreated characteristic of satellite data the task scheduling subsystem provides two kinds of Parallel Task Scheduling strategies to realize the rational energy of highest point.The task little to calculated amount (as: zero level data processing, product issue etc.), system adopt the parallel scheduling strategy of task level; For computation-intensive tasks such as algorithm complexity or big data quantity processing (as: wave band registration etc.), system then adopts the algorithm level paralleling tactic.Though the common tasks scheduling mechanism based on a group of planes can be realized dynamic load leveling between each computing node, but for be treated to main calculating with big data quantity, usually can cause also that large-scale data moves between each node, cause the system handles performance decrease, even become a bottleneck in the high performance parallel computation.Move influence to system performance for eliminating data, system is being made of group of planes deploy parallel file system each computing node.This can not only be avoided extensive move of data between computing node effectively, the time of data distribution and recovery in all right high performance parallel computation of shortening greatly, and the raising system is based on the efficient of the parallel processing algorithm concurrent reading and writing data of parallel computation.
Claims (3)
1, a kind of multi-satellite remote sensing data integrated parallel ground pretreatment system is characterized in that, comprising:
Hardware layer, the hardware support that it provides pretreatment system comprises storage systems such as commercialization Network of Workstation, SAN/NAS and such as the high performance network system of gigabit Ethernet or infiniband;
The system support layer, the expansion of system software back-up environment and system performance is provided, realize parallel computation, parallel storage, parallel network load blocks by orthogonal design, the system that makes can independently expand aspect handling property, network performance, the memory property, and can be according to data processing characteristics complex optimum three performance, provide powerful system performance support to the filing of the processing of data, data and production and distribution, make and expansion of system performance height and efficient operation have reached the requirement of expanding as required at aspect of performance;
The data processing extension layer has the abstraction function interface of multiple satellite multiple sensors and public function combinations logic, and the concrete Processing Algorithm of all kinds of satellites and sensor realizes by the means of inheriting and add, and has guaranteed that algorithm function expands as required;
The task management dispatch layer is realized task scheduling and workflow management, is integrated with job scheduling system and Workflow Management System at this layer, the balanced and flow processing ability with the operating load of realizing multiple processing capacity;
User's processing capacity combination layer, for the user provides the path combination that is simple and easy to usefulness interface, the user can make up the treatment scheme that comprises multiple functions such as data processing, filing, production and distribution of various complexity.
2, multi-satellite remote sensing data integrated parallel ground pretreatment system according to claim 1, it is characterized in that: in described system support layer, described parallel computation module comprises MPI, OpenMP, PVM, described parallel memory module comprises PVFS, Lustre, StorNext, and described offered load module comprises the dispositions method of LVS, BigIP.
3, multi-satellite remote sensing data integrated parallel ground pretreatment system according to claim 1 and 2, it is characterized in that: in the described Workflow Management System of task management and dispatching layer, same flow process can be loaded twice and finish jointly task handling, be used to for the first time each phase process task to generate the relevant parameters file, be used to carry out each phase process task for the second time and finish specific processing capacity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008101350473A CN101315424B (en) | 2008-07-29 | 2008-07-29 | Multi-satellite remote sensing data integrated parallel ground pretreatment system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008101350473A CN101315424B (en) | 2008-07-29 | 2008-07-29 | Multi-satellite remote sensing data integrated parallel ground pretreatment system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101315424A true CN101315424A (en) | 2008-12-03 |
| CN101315424B CN101315424B (en) | 2011-06-08 |
Family
ID=40106498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2008101350473A Expired - Fee Related CN101315424B (en) | 2008-07-29 | 2008-07-29 | Multi-satellite remote sensing data integrated parallel ground pretreatment system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101315424B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101783009A (en) * | 2010-03-25 | 2010-07-21 | 中国科学院对地观测与数字地球科学中心 | Method for constructing geometric correction of expandable multi-satellite multi-sensor remote sensing images |
| CN102393815A (en) * | 2011-07-13 | 2012-03-28 | 中国科学院遥感应用研究所 | Parallel processing method of remote sensing operation |
| CN102521681A (en) * | 2011-11-18 | 2012-06-27 | 中国科学院对地观测与数字地球科学中心 | Remote sensing data quality monitoring system with extensible function and performance |
| CN102521687A (en) * | 2011-12-01 | 2012-06-27 | 中国资源卫星应用中心 | Miniaturized universal platform for preprocessing remote-sensing satellite data |
| CN103677761A (en) * | 2013-12-11 | 2014-03-26 | 中国资源卫星应用中心 | Quick satellite remote sensing data processing system |
| CN104484230A (en) * | 2014-12-31 | 2015-04-01 | 中国科学院遥感与数字地球研究所 | Multiple satellite data centre workflow scheduling algorithm on basis of near data calculation principle |
| CN104537125A (en) * | 2015-01-28 | 2015-04-22 | 中国人民解放军国防科学技术大学 | Remote-sensing image pyramid parallel building method based on message passing interface |
| CN105094982A (en) * | 2014-09-23 | 2015-11-25 | 航天恒星科技有限公司 | Multi-satellite remote sensing data processing system |
| WO2015180000A1 (en) * | 2014-05-26 | 2015-12-03 | 中国科学院长春光学精密机械与物理研究所 | Comprehensive management system for platform and payload integrated satellite |
| CN106909452A (en) * | 2017-03-06 | 2017-06-30 | 中国科学技术大学 | Concurrent program runtime parameter optimization method |
| CN107465900A (en) * | 2017-08-22 | 2017-12-12 | 长光卫星技术有限公司 | A kind of preprocess method suitable for large area array sub-meter grade remote sensing video image unit |
| CN109150281A (en) * | 2017-06-27 | 2019-01-04 | 航天恒星科技有限公司 | Ground satellite station automatic operating method |
| CN110941463A (en) * | 2019-11-13 | 2020-03-31 | 中国科学院遥感与数字地球研究所 | Remote sensing satellite data preprocessing multistage product self-driven system |
| CN111722635A (en) * | 2020-06-05 | 2020-09-29 | 北京空间飞行器总体设计部 | Method for parallel processing tasks of remote sensing satellite and remote sensing satellite system |
| CN114465652A (en) * | 2021-12-22 | 2022-05-10 | 中国科学院空天信息创新研究院 | Universal extensible remote sensing satellite data real-time quick-look processing and scheduling system |
| CN117311137A (en) * | 2023-11-28 | 2023-12-29 | 十方星链(苏州)航天科技有限公司 | Automatic operation method, system and computer equipment of satellite measurement, operation and control equipment |
| CN117311951A (en) * | 2023-11-29 | 2023-12-29 | 齐鲁空天信息研究院 | Multi-star data automation task processing system and method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1831555B (en) * | 2005-03-10 | 2011-05-11 | 中国煤炭地质总局航测遥感局 | Processing method for local correction of remote sensing image |
| CN1924610A (en) * | 2005-09-01 | 2007-03-07 | 中国林业科学研究院资源信息研究所 | Method for inversing forest canopy density and accumulating quantity using land satellite data |
| CN100510773C (en) * | 2006-04-14 | 2009-07-08 | 武汉大学 | Single satellite remote sensing image small target super resolution ratio reconstruction method |
-
2008
- 2008-07-29 CN CN2008101350473A patent/CN101315424B/en not_active Expired - Fee Related
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101783009A (en) * | 2010-03-25 | 2010-07-21 | 中国科学院对地观测与数字地球科学中心 | Method for constructing geometric correction of expandable multi-satellite multi-sensor remote sensing images |
| CN102393815A (en) * | 2011-07-13 | 2012-03-28 | 中国科学院遥感应用研究所 | Parallel processing method of remote sensing operation |
| CN102521681A (en) * | 2011-11-18 | 2012-06-27 | 中国科学院对地观测与数字地球科学中心 | Remote sensing data quality monitoring system with extensible function and performance |
| CN102521687A (en) * | 2011-12-01 | 2012-06-27 | 中国资源卫星应用中心 | Miniaturized universal platform for preprocessing remote-sensing satellite data |
| CN102521687B (en) * | 2011-12-01 | 2014-12-24 | 中国资源卫星应用中心 | Miniaturized universal platform for preprocessing remote-sensing satellite data |
| CN103677761A (en) * | 2013-12-11 | 2014-03-26 | 中国资源卫星应用中心 | Quick satellite remote sensing data processing system |
| CN103677761B (en) * | 2013-12-11 | 2016-09-21 | 中国资源卫星应用中心 | A kind of quick processing system of satellite remote sensing date |
| WO2015180000A1 (en) * | 2014-05-26 | 2015-12-03 | 中国科学院长春光学精密机械与物理研究所 | Comprehensive management system for platform and payload integrated satellite |
| CN105094982A (en) * | 2014-09-23 | 2015-11-25 | 航天恒星科技有限公司 | Multi-satellite remote sensing data processing system |
| CN104484230A (en) * | 2014-12-31 | 2015-04-01 | 中国科学院遥感与数字地球研究所 | Multiple satellite data centre workflow scheduling algorithm on basis of near data calculation principle |
| CN104484230B (en) * | 2014-12-31 | 2019-03-15 | 中国科学院遥感与数字地球研究所 | More satellite data central task stream dispatching algorithms based on nearly data calculating principle |
| CN104537125B (en) * | 2015-01-28 | 2017-11-14 | 中国人民解放军国防科学技术大学 | A kind of remote sensing image pyramid parallel constructing method based on message passing interface |
| CN104537125A (en) * | 2015-01-28 | 2015-04-22 | 中国人民解放军国防科学技术大学 | Remote-sensing image pyramid parallel building method based on message passing interface |
| CN106909452B (en) * | 2017-03-06 | 2020-08-25 | 中国科学技术大学 | Parallel program runtime parameter optimization method |
| CN106909452A (en) * | 2017-03-06 | 2017-06-30 | 中国科学技术大学 | Concurrent program runtime parameter optimization method |
| CN109150281B (en) * | 2017-06-27 | 2021-12-28 | 航天恒星科技有限公司 | Automatic operation method for satellite ground station |
| CN109150281A (en) * | 2017-06-27 | 2019-01-04 | 航天恒星科技有限公司 | Ground satellite station automatic operating method |
| CN107465900A (en) * | 2017-08-22 | 2017-12-12 | 长光卫星技术有限公司 | A kind of preprocess method suitable for large area array sub-meter grade remote sensing video image unit |
| CN110941463A (en) * | 2019-11-13 | 2020-03-31 | 中国科学院遥感与数字地球研究所 | Remote sensing satellite data preprocessing multistage product self-driven system |
| CN111722635A (en) * | 2020-06-05 | 2020-09-29 | 北京空间飞行器总体设计部 | Method for parallel processing tasks of remote sensing satellite and remote sensing satellite system |
| CN114465652A (en) * | 2021-12-22 | 2022-05-10 | 中国科学院空天信息创新研究院 | Universal extensible remote sensing satellite data real-time quick-look processing and scheduling system |
| CN114465652B (en) * | 2021-12-22 | 2023-11-14 | 中国科学院空天信息创新研究院 | General extensible remote sensing satellite data real-time quick-viewing processing scheduling system |
| CN117311137A (en) * | 2023-11-28 | 2023-12-29 | 十方星链(苏州)航天科技有限公司 | Automatic operation method, system and computer equipment of satellite measurement, operation and control equipment |
| CN117311137B (en) * | 2023-11-28 | 2024-02-20 | 十方星链(苏州)航天科技有限公司 | Automatic operation method, system and computer equipment of satellite measurement, operation and control equipment |
| CN117311951A (en) * | 2023-11-29 | 2023-12-29 | 齐鲁空天信息研究院 | Multi-star data automation task processing system and method |
| CN117311951B (en) * | 2023-11-29 | 2024-03-01 | 齐鲁空天信息研究院 | Multi-star data automation task processing system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101315424B (en) | 2011-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101315424B (en) | Multi-satellite remote sensing data integrated parallel ground pretreatment system | |
| Zhou | Lsf: Load sharing in large heterogeneous distributed systems | |
| CN102831011B (en) | A kind of method for scheduling task based on many core systems and device | |
| CN102063336B (en) | Distributed computing multiple application function asynchronous concurrent scheduling method | |
| CN102096596B (en) | Cloud computing service Cache system based on internal memory template of virtual machine | |
| CN1987794B (en) | Method and apparatus for improving block allocation times in a computer system | |
| CN102360309B (en) | Scheduling system and scheduling execution method of multi-core heterogeneous system on chip | |
| CN102169505A (en) | Recommendation system building method based on cloud computing | |
| CN100553214C (en) | Mobile virtual environment system | |
| CN102880510A (en) | Parallel programming method oriented to data intensive application based on multiple data architecture centers | |
| CN102222174A (en) | Gene computation system and method | |
| Bosilca et al. | Performance portability of a GPU enabled factorization with the DAGuE framework | |
| CN104239555A (en) | MPP (massively parallel processing)-based parallel data mining framework and MPP-based parallel data mining method | |
| Choi et al. | Data-locality aware scientific workflow scheduling methods in HPC cloud environments | |
| Khoo et al. | A multi-dimensional scheduling scheme in a Grid computing environment | |
| Lacoste et al. | Sparse direct solvers with accelerators over DAG runtimes | |
| CN103299277A (en) | Gpu system and processing method thereof | |
| Srirama et al. | Migrating scientific workflows to the cloud: through graph-partitioning, scheduling and peer-to-peer data sharing | |
| Raii et al. | Efficient clustering model for utilization of processor’s capacity in distributed computing system | |
| Huang et al. | A novel multi-CPU/GPU collaborative computing framework for SGD-based matrix factorization | |
| Liu et al. | Bspcloud: A programming model for cloud computing | |
| Zheng et al. | Building and Dynamically Managing Workflows for Processing Remote Sensing Data in Distributed High-Throughput Environment | |
| Jacob et al. | Performance analysis of Hadoop map reduce on eucalyptus private cloud | |
| Liu | Multisite Management of Data-intensive Scientific Workflows in the Cloud | |
| Berriman et al. | High-performance compute infrastructure in astronomy: 2020 is only months away |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20110608 Termination date: 20200729 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |