CN106407460A - Distributed ionospheric model cloud service system and method - Google Patents
Distributed ionospheric model cloud service system and method Download PDFInfo
- Publication number
- CN106407460A CN106407460A CN201610883204.3A CN201610883204A CN106407460A CN 106407460 A CN106407460 A CN 106407460A CN 201610883204 A CN201610883204 A CN 201610883204A CN 106407460 A CN106407460 A CN 106407460A
- Authority
- CN
- China
- Prior art keywords
- server
- task
- web
- virtual
- small
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
Abstract
The invention discloses a distributed ionospheric model cloud service system and method. The system consists of a physical server and a virtual server, wherein the physical server consists of a computing-type server and a task-type server; the computing-type server is used for dense scientific computation; the task-type server is used for allocating tasks to the computing-type server and a small computing task virtual server; the virtual server consists of the small computing task virtual server and a Web server; the small computing task virtual server is used for low-consumption scientific computation for a small CPU (Central Processing Unit); the Web server is used for providing a Web network service; the physical server and the small computing task virtual server are connected with the task-type server; the task-type server is connected with the Web server in a one-way manner; and the Web server is oriented to a user and services for the user. The system is mounted as required, so that the system has the advantages of high performance, high safety, good expansibility, cost saving, universality and the like, can realize full-automatic operation, and requires no artificial management or operation.
Description
Technical field
The invention belongs to scientific algorithm and service technology field, it is related to a kind of distributed ionospheric model cloud service system
And method;Can be widely used in all kinds of subjects, the such as data processing of Global Ionospheric model automatization.
Background technology
IBM Corporation announced cloud computing plan in 2007, and the concept of cloud computing occurs in face of masses from this.Cloud computing
Describe a kind of extendible application program that can conduct interviews by internet." cloud application " uses in large-scale data
The server of the heart and powerful in function comes operational network application program and network service.And the server in cloud computing platform can
To be the server of physics or virtual server.User can be passed through by internet or mobile internet access equipment
Browser just can access cloud computing application program.Cloud computing service provider mainly includes traditional IT vendor, internet provides
Business and software vendor.Current cloud computing service mainly comprises some and Internet service allo cloud main frame, Yun Cun
Storage etc..And scientific calculating tends to rely on that hardware configuration is higher and expensive physical server, and generally calculate
Go out corresponding result and only download use, not provides convenient efficiently user service platform for relevant speciality personage.At present, generation
Big country of boundary competitively develops the research in respective supercomputer field.Scientific algorithm be strengthen national economic development, social development,
The important means in the fields such as scientific progress, national security and national defense construction.China's economic society fast development is to each science and engineering subject
Demand present new trend.Such as satellite navigation and location-based service are in automobile navigation and monitoring, valuables tracking etc.
Aspect has and is widely applied, and range of application expands continuous, has very big potentiality.This kind of service platform is except needing
The support of hardware is in addition it is also necessary to the powerful software service platform of One function just can make it implement.Research cloud computing era phase
Pass technology simultaneously sets up efficient scientific algorithm and service platform, and application service level and development for lifting scientific algorithm are based on
The application technology of scientific algorithm and service mode have highly important meaning, provide conventional scientific algorithm function for associated user
With a series of product and service.For Surveying Science and Technology, not yet there are complete scientific algorithm and related service system in the whole world
System.There are the CSRS-PPP of Canadian resource bureau, the GAPS-PPP of Canadian University of New Brunswick and U.S.'s jet-propulsion at present
The APPS-PPP in laboratory can provide the user free online service.These scientific algorithm are relative with the framework of service platform simple
Single, only the data that user submits to is carried out correlation computations and then result is fed back to user, the scientific algorithm function that it is related to
Comparison is single and scale is less, not yet forms powerful and perfect user service platform.Under normal circumstances, with calculating
The increase of function, also higher to the demand of physical server configuration, if the scientific algorithm task by substantial amounts of difference in functionality
It is installed on same physical server and will certainly cause nonidentity operation program fighting for thus leading to science meter to hardware resource
Calculation can not execute steadily in the long term, and if be installed in each calculating task on multiple physical servers, needs to expend substantial amounts of
Fund is used for purchasing hardware device.
Content of the invention
In order to solve the above problems, the invention provides a kind of distributed system being applied to scientific algorithm and service platform
And method.
The technology that the system of the present invention is adopted:A kind of distributed ionospheric model cloud service system it is characterised in that:
It is made up of physical server and virtual server;Described physical server is made up of calculation type server and Task server,
Described calculation type server is used for intensive scientific algorithm, described Task server by calculation type server and small-sized based on
Calculation task virtual server distributes task;Described virtual server is by small-sized calculating task virtual server and Web server group
Become, be respectively used to Small-sized C PU low consumption scientific algorithm and Web network service is provided;
Described physical server, small-sized calculating task virtual server are connected with described Task server respectively, described task
Type server and the unidirectional connection of Web server, described Web server user oriented, is user service.
Preferably, being provided with one or more virtual transfers between described Web server and described Task server
Server.
The method of the present invention be employed technical scheme comprise that:A kind of distributed ionospheric model cloud service method, it is special
Levy and be, comprise the following steps:
Step 1:Task server is according to prefabricated task scheduling to calculation type server and the virtual clothes of small-sized calculating task
Business device distribution task;
Step 2:Result of calculation information is sent to Web server by Task server in the form of a file;
Step 3:Web server reads the fileinfo receiving, and updates website;
Step 4:Up-to-date information is consulted in the website that user passes through in browser access Web server.
Preferably, result of calculation information described in step 2 includes ionospheric model coefficient, TEC figure, system are transported in real time
Row status information.
Preferably, consulting up-to-date information described in step 4 to include Global Ionospheric calculation result information, the quasi real time whole world
Real-time running state information in ionospheric map information, Global Ionospheric forecast model products information and Task server.
With respect to prior art, the invention has the beneficial effects as follows:
1st, high-performance, using the framework mode of physical server and virtual server combination, by intensive scientific algorithm part, little
Type CPU low consumption scientific algorithm and Web network service separate, and give full play to the calculating efficiency of physical server, it is to avoid all kinds of meters
Interfering so that system service can run steadily in the long term between calculation and Web service;
2nd, high security, physical server adopts unidirectional company with the virtual server installing small-sized calculating task with Web server
Connect mode, not region be directly facing user, such as security to be strengthened can also set up one or more virtual servers as transfer,
So that physical server and small-sized calculating class virtual server is immune against attacks, and Web server uses virtual server, can be fast
Speed easily makes mirror back-up, such as suffers from attack can be rapidly switched to other virtual images thus safeguards system continues safe fortune
OK;
3rd, good autgmentability, due to distributed system architecture, each server is relatively independent, such as need to add computing module
Or new service module can add corresponding physical server or virtual server on demand, do not affect original system operation;
4th, cost-effective, intensive scientific algorithm task is needed to be installed on physical server, and for other small-sized meters
Calculation task can be installed on virtual server, configures on demand, forms optimum organization, effectively cost-effective;
5th, universality, the present invention can purchase physical server and the virtual server of respective numbers according to the actual requirements, fit simultaneously
Intensive calculating task for all kinds of subjects and other small-sized calculating tasks, and the application of different subject different majors can be set up
Service platform, has outstanding general feature.
Brief description
Fig. 1:The system architecture schematic diagram of the embodiment of the present invention
Fig. 2:The method flow diagram of the embodiment of the present invention.
Specific embodiment
Understand for the ease of those of ordinary skill in the art and implement the present invention, below in conjunction with the accompanying drawings and embodiment is to this
Bright be described in further detail it will be appreciated that described herein enforcement example be merely to illustrate and explain the present invention, not
For limiting the present invention.
Ask for an interview Fig. 1, a kind of distributed ionospheric model cloud service system that the present invention provides, by physical server and void
Intend server composition;Physical server is made up of calculation type server and Task server, and calculation type server is used for intensive
Type scientific algorithm, Task server is used for distributing task to calculation type server and small-sized calculating task virtual server;Empty
Intend server be made up of small-sized calculating task virtual server and Web server, be respectively used to Small-sized C PU low consumption scientific algorithm with
And Web network service is provided;
Physical server, small-sized calculating task virtual server are connected with Task server respectively, Task server and Web
The unidirectional connection of server, Web server user oriented, is user service.
User browser is connected with Web server, Task server and the unidirectional connection of Web server.The present embodiment
Physical server is 1, is installed on Global Ionospheric solution to model and calculates program.The virtual server of the present embodiment be provided with multiple,
Including being installed on small-sized calculating task, such as quasi real time Global Ionospheric figure, Global Ionospheric forecast, and 1 Web server are used
To set up the website service platform of ionospheric model.
Ask for an interview Fig. 2, a kind of distributed ionospheric model cloud service method that the present invention provides, comprise the following steps:
1. the multiple server Programs being installed on calculating task execute corresponding science meter according to calculating task independently of one another
Calculation task;
2. Task server by the result of calculation such as information such as ionospheric model coefficient, TEC figure, system real-time running state with
The form of file is sent to Web server;
3.Web server waits and receives the fileinfos such as ionospheric model coefficient, TEC figure;
The fileinfo that 4.Web program reading Web service device receives, and update Website page;
5. user passes through the up-to-date information on browser access Web server reference service platform website, such as Global Ionospheric solution
Real time execution in calculation result, quasi real time Global Ionospheric figure, Global Ionospheric forecast model products and calculating task type server
State etc..
This enforcement adopts Ubuntu12.04 as the operating system of physical server in the present embodiment and virtual server,
And Demonstration Application of the present invention is completed using language such as C++, Fortran, Bash, PHP, HTML, CSS, JavaScript, XML, point
It is not:Realize the resolving of Global Ionospheric model Related product using C++, Fortran language, every including Global Ionospheric model
Day calculation result, quasi real time Global Ionospheric figure and Global Ionospheric forecast model products;(SuSE) Linux OS literary composition is realized using Bash
The operation of part aspect;Website service platform on Web server is completed using PHP, HTML, CSS, JavaScript, XML.
It should be appreciated that the part that this specification does not elaborate belongs to prior art.
It should be appreciated that the Global Ionospheric model application in specific embodiments described herein is only to this
Bright thought illustrates.Those skilled in the art of the present invention can to described be embodied as case do various
The modification of various kinds or supplement, but the thought without departing from the present invention or surmount claims say defined in scope.
Claims (5)
1. a kind of distributed ionospheric model cloud service system it is characterised in that:By physical server and virtual server group
Become;Described physical server is made up of calculation type server and Task server, and described calculation type server is used for intensity
Scientific algorithm, described Task server is used for distributing task to calculation type server and small-sized calculating task virtual server;
Described virtual server is made up of small-sized calculating task virtual server and Web server, is respectively used to Small-sized C PU low consumption science
Calculate and Web network service is provided;
Described physical server, small-sized calculating task virtual server are connected with described Task server respectively, described task
Type server and the unidirectional connection of Web server, described Web server user oriented, is user service.
2. distributed ionospheric model cloud service system according to claim 1 it is characterised in that:Described Web service
It is provided with one or more virtual transfer servers between device and described Task server.
3. a kind of distributed ionospheric model cloud service method is it is characterised in that comprise the following steps:
Step 1:Task server is according to prefabricated task scheduling to calculation type server and the virtual clothes of small-sized calculating task
Business device distribution task;
Step 2:Result of calculation information is sent to Web server by Task server in the form of a file;
Step 3:Web server reads the fileinfo receiving, and updates website;
Step 4:Up-to-date information is consulted in the website that user passes through in browser access Web server.
4. distributed ionospheric model cloud service method according to claim 3 it is characterised in that:Described in step 2
Result of calculation information includes ionospheric model coefficient, TEC figure, system real-time running state information.
5. distributed ionospheric model cloud service method according to claim 3 it is characterised in that:Described in step 4
Consult up-to-date information and include Global Ionospheric calculation result information, quasi real time Global Ionospheric figure information, Global Ionospheric forecast
Real-time running state information in product information and Task server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610883204.3A CN106407460A (en) | 2016-10-10 | 2016-10-10 | Distributed ionospheric model cloud service system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610883204.3A CN106407460A (en) | 2016-10-10 | 2016-10-10 | Distributed ionospheric model cloud service system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106407460A true CN106407460A (en) | 2017-02-15 |
Family
ID=59229151
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610883204.3A Pending CN106407460A (en) | 2016-10-10 | 2016-10-10 | Distributed ionospheric model cloud service system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106407460A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101072226A (en) * | 2006-12-30 | 2007-11-14 | 腾讯科技(深圳)有限公司 | Grid computing method and system |
CN102014042A (en) * | 2009-09-08 | 2011-04-13 | 中兴通讯股份有限公司 | Web load balancing method, grid server and system |
CN103164287A (en) * | 2013-03-22 | 2013-06-19 | 河海大学 | Distributed-type parallel computing platform system based on Web dynamic participation |
-
2016
- 2016-10-10 CN CN201610883204.3A patent/CN106407460A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101072226A (en) * | 2006-12-30 | 2007-11-14 | 腾讯科技(深圳)有限公司 | Grid computing method and system |
CN102014042A (en) * | 2009-09-08 | 2011-04-13 | 中兴通讯股份有限公司 | Web load balancing method, grid server and system |
CN103164287A (en) * | 2013-03-22 | 2013-06-19 | 河海大学 | Distributed-type parallel computing platform system based on Web dynamic participation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Panda et al. | The MVAPICH project: Evolution and sustainability of an open source production quality MPI library for HPC | |
CN104636187B (en) | Dispatching method of virtual machine in NUMA architecture based on load estimation | |
GB2604230A (en) | Liquid flow distribution using one or more neural networks | |
Pop et al. | ARMCO: Advanced topics in resource management for ubiquitous cloud computing: An adaptive approach | |
CN107533354A (en) | The performance state of the processing engine of control processor | |
CN105760227B (en) | Resource regulating method and system under cloud environment | |
Ashraf et al. | Empirical investigation: performance and power‐consumption based dual‐level model for exascale computing systems | |
Wienke et al. | Accelerators for technical computing: Is it worth the pain? a tco perspective | |
US20220413572A1 (en) | Hybrid cooling systems for datacenters | |
Kondru et al. | A Review of distributed supercomputing platforms using Blockchain | |
CN106407460A (en) | Distributed ionospheric model cloud service system and method | |
Li et al. | Distributed algorithms with theoretic scalability analysis of radial and looped load flows for power distribution systems | |
US20230126350A1 (en) | Non-volatile memory storage and interface | |
Wang et al. | Deadline and reliability aware multiserver configuration optimization for maximizing profit | |
US8775840B2 (en) | Virtualization in a multi-core processor (MCP) | |
US20230125892A1 (en) | Run-time configuration loading | |
Carabaş et al. | Energy-efficient virtualized clusters | |
Shrawankar et al. | Virtualization Technology for Cloud-Based Services | |
CN111736984A (en) | Method and system for sensing NUMA (non uniform memory access) distribution balance of PCIE (peripheral component interface express) equipment | |
Proctor et al. | Virtualizing the stampede2 supercomputer with applications to hpc in the cloud | |
US20230061162A1 (en) | Data center load supervisor | |
Ziagham Ahwazi et al. | VEDA-moVE DAta to balance the grid: research directions and recommendations for exploiting data centers flexibility within the power system | |
Pattnaik | Fundamentals of cloud computing | |
US20240094796A1 (en) | Techniques to modify processor performance | |
CN116991558B (en) | Computing power resource scheduling method, multi-architecture cluster, device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170215 |
|
RJ01 | Rejection of invention patent application after publication |