CN109460293B - Computing resource selection method under distributed computing environment in wireless cloud computing system - Google Patents
Computing resource selection method under distributed computing environment in wireless cloud computing system Download PDFInfo
- Publication number
- CN109460293B CN109460293B CN201811185348.7A CN201811185348A CN109460293B CN 109460293 B CN109460293 B CN 109460293B CN 201811185348 A CN201811185348 A CN 201811185348A CN 109460293 B CN109460293 B CN 109460293B
- Authority
- CN
- China
- Prior art keywords
- computing
- information
- information table
- unit
- user
- 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.)
- Active
Links
Images
Classifications
-
- 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
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- 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
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a computing resource selection method in a distributed computing environment in a wireless cloud computing system. In order to achieve the aim, an information table is designed for the CUs, the information of idle CUs of the system is stored in the information table, the terminal held by the user accesses the CUs in the system, and the accessed CUs select the idle CUs in the system to process the calculation request of the user according to the information stored in the information table. The method for selecting the computing resources in the wireless cloud computing system effectively reduces the waiting time of a user in the system, improves the system performance, and has guiding significance for selecting the computing resources in the wireless cloud computing system.
Description
Technical Field
The invention relates to a method for selecting distributed computing resources in a wireless cloud computing system, and belongs to the technical field of resource selection methods in wireless cloud computing.
Background
Cloud computing networks have rapidly developed in recent years, and share resources such as software, processing power, storage, and the like in an on-demand manner through the networks. With the development of the internet, researchers combine cloud computing technology with the internet to generate a new application mode, which is called mobile cloud computing. The mobile cloud is a mode that a mobile user terminal obtains required application in an on-demand and easily-extensible mode through a mobile internet. As an extension of cloud computing, in wireless cloud computing, a mobile terminal can perform data access at any time and any place, so that a user has better user experience when using an application program and accessing information through a mobile device in a mobile cloud computing environment.
However, it has been difficult for mobile devices to meet the needs of most mobile users due to their own size and weight constraints, resulting in computing power, memory capacity, and some of the functionality provided through remote internet services. Therefore, the characteristics of the cloud computing technology such as strong computing processing capacity and infinite storage capacity are utilized to provide better service for users. The wireless communication technology is combined with the mobile cloud computing, so that mobile equipment with limited capacity can select and utilize computing resources in remote cloud computing and can also utilize terminal resources with rich and idle peripheral resources nearby, and a network consisting of a small number of computing units with idle computing capacity and capable of providing computing services for mobile terminals of users in a limited range is a wireless cloud computing network researched by the invention. However, due to the randomness of the user accessing the system, the amount of tasks processed in the computing unit in the system is different, and problems such as too long delay of the request of the terminal in the system, and non-ideal system performance are generated.
Therefore, in the present invention, research will be conducted on a distributed computing resource selection method of a mobile terminal in a wireless cloud computing system.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to solve the problems that the task amount processed in a computing unit in a system is different due to the randomness of a user access system, the time delay of a terminal request in the system is too long, the system performance is not ideal and the like in the conventional cloud computing technology.
The technical scheme is as follows: the invention adopts the following technical scheme:
a computing resource selection method in a distributed computing environment in a wireless cloud computing system comprises the following steps:
(1) the system allocates an IP address to each CU, wherein the IP address is the unique identifier of a user in the system;
(2) each CU stores an information table containing the IP addresses and the idle degree of other CUs, and the information table gives the information of the CU with the larger idle degree in the system;
(3) a user randomly enters a certain position in a system range, a mobile terminal held by the user is accessed to a CU with the nearest distance, and a calculation request is sent to the CU;
(4) the CU receives a calculation request sent by the mobile terminal, and searches a stored information table for an idle CU;
(5) after the CU selects and processes the CU requested by the user according to the information table, if the CU selects the CU to process finally, the CU directly adds the calculation request of the user into a task which is queued for processing, if other CUs are selected to process, the calculation request is sent to the selected CU for processing according to the IP address of the selected CU, the CU which processes the calculation request of the mobile terminal sends a processing result to the CU accessed by the mobile terminal, and the accessed CU feeds back the processing result to the mobile terminal;
(6) the CU updates the state information of the CU, namely the task amount waiting for processing, to an information table of the CU at intervals; the CU judges whether the information stored in the information table contains the information of the CU or not, and if so, the latest state information of the CU is updated into the information table;
(7) in (6), if the information table stored by the CU does not contain the own state information, determining whether the information table already stores the information of N CUs, and if the information table is smaller than N, storing the own state information into the information table;
(8) in (7), if the information table has no information of itself and N records are already stored, comparing the free degree of itself with the free degree of the CU in the information table, and if the free degree is greater than the free degree of the CU stored in the information table, replacing the CU information with the minimum free degree with the state information of itself; if the idle degree stored in the information table is all larger than the idle degree of the information table, the information table is kept unchanged;
(9) and the CU sends the processing result of the calculation request to the CU accessed by the mobile terminal, and finally, the CU accessed by the terminal sends the calculation result to the mobile terminal of the user.
Further, in the step (3), the information of at most N CUs may be stored in the information table; too much information is stored, the memory of the CU is occupied, and the CU does not need to store the state information of all CUs in the system, so that the information table does not store the state information of all CUs, and the information table is designed to store the information of N CUs at most.
Further, in the step (4), a CU with the largest vacancy degree is queried first, and the IP address of the CU is obtained, if the CU is found to be far away, the CU is queried again for the largest vacancy value smaller than the vacancy value, the IP address of the CU is checked, if the CU is still far away, the query is continued, and finally, a CU which is close to the CU and is sufficiently vacant is selected to process the user request.
Further, in the step (4), the CU exchanges information table information with its neighboring nodes; and the CU exchanges the information table with the information table of the adjacent CU, and finally, the state information of the N CUs with larger idle degree in the two tables is stored in each table.
Further, the CU is divided into K blades by the system, each blade is an access point, and after a user calculation request enters the CU, the CU distributes the calculation request of one user to one blade; so at the same time, one CU can access the computation requests of K users at the same time. After the CU receives a calculation request of a user, the calculation request is added into the tasks waiting for processing, and after the blade finishes processing the calculation request, the CU selects one task from the tasks waiting for processing to be distributed to the blade.
The effective effect is as follows: compared with the prior art, the invention has the advantages that:
according to the distributed computing resource selection method in the wireless cloud computing system, the information table is designed, the information of the idle CU in the system is stored, the computing unit for processing the request is selected for the user, the time delay of the user in the system is effectively reduced, and the user experience is improved.
According to the distributed computing resource selection method in the wireless cloud computing system, the computing request is guided to the CU in the idle system, so that the computing resources in the system are utilized evenly, and the system performance is improved.
According to the distributed computing resource selection method in the wireless cloud computing system, the state information is continuously updated into the information table, and the information of the information table is continuously exchanged between adjacent CUs, so that the timeliness of the information table is guaranteed.
Drawings
FIG. 1 is a schematic diagram of a wireless cloud computing system model according to the present invention;
FIG. 2 is a table structure diagram of the present invention;
FIG. 3 is a flow diagram of the CU processing user request of the present invention;
FIG. 4 is a CU query information table flow diagram;
FIG. 5 is a CU update information table flow diagram.
Detailed description of the preferred embodiments
The following is further described with reference to the accompanying drawings.
Examples
The invention selects the computing resources in the system under the condition of distributed computing resources in a wireless cloud computing system, and the specific implementation steps are as follows:
the system is in practice generally designed as a base station and the CU is generally designed as a computer with both computing power and communication interfaces.
(1) The system allocates an IP address to each CU, such as 192.168.1.2-230, the following numerical values are determined according to the specific CU number, and the IP address is the unique identification of a user in the system;
(2) each CU stores an information table containing the IP addresses and the degree of idleness of other CUs, which gives information on the CU having a larger degree of idleness in the system, as shown in fig. 2. Because too much information is stored, the memory of the CU is occupied to be free, and the CU does not need to store the state information of all CUs in the system, the information table cannot store the state information of all CUs, and the information table stores the information of N CUs at most;
(3) a user randomly enters a certain position in a system range, a mobile terminal held by the user is accessed to a CU with the nearest distance, and a calculation request is sent to the CU;
(4) and the CU receives a calculation request sent by the terminal, inquires the stored information table and searches for idle CUs in the system. Firstly inquiring the CU with the largest idle degree, obtaining the IP address of the CU, inquiring the largest idle value smaller than the idle value again if the CU is far away, checking the IP address of the CU, continuing the inquiry if the CU is still far away, and finally selecting the CU which is close to the idle value and is enough to idle to process the user request;
(5) after the CU selects and processes the CU requested by the user according to the information table, if the CU selects the CU to process the CU, the CU directly adds the calculation request of the user into a task which is queued for processing, if other CUs are selected to process the CU, the calculation request is sent to the selected CU for processing according to the IP address of the selected CU, the CU which processes the calculation request of the terminal sends a processing result to the CU accessed by the terminal, and the accessed CU feeds back the processing result to the terminal;
(6) the CU in the system continuously processes user requests and has the possibility of user access at any time, so the idle degree of the nodes is continuously changed. The CU updates its status information, i.e. the amount of tasks waiting to be processed, to its own information table at intervals. The CU judges whether the information stored in the information table contains the information of the CU or not, and if so, the latest state information of the CU is updated into the information table;
(7) in (6), if the information table stored by the CU does not contain the own state information, determining whether the information table already stores the information of N CUs, and if the information table is smaller than N, storing the own state information into the information table;
(8) in (7), if the information table has no own information and N records are already stored, comparing the free degree of the information table with the free degree of the CU in the information table, and if the free degree is greater than the free degree of the CU stored in the information table, replacing the CU information with the minimum free degree with the own state information. If the idle degree stored in the information table is all larger than the idle degree of the information table, the information table is kept unchanged;
(9) a CU continuously exchanges information table information with its neighboring nodes in order to maintain state information of other CUs in the information table. In the known system, wireless communication can be carried out between adjacent CUs, the CUs exchange information tables with adjacent nodes, and finally, the state information of a plurality of CUs with larger idle degree in two tables is stored in each table;
(10) and dividing the CU into K blades, wherein each blade is an access point, and after the calculation request of the user enters the CU, the CU distributes the calculation request of one user to one blade. So at the same time, one CU can access the computation requests of K users at the same time. After the CU receives a calculation request of a user, the calculation request is added into the tasks waiting for processing, and after the blade finishes processing the calculation request, the CU selects one task from the tasks waiting for queuing to be distributed to the blade;
(11) and the CU sends the processing result of the calculation request to the CU accessed by the mobile terminal, and finally, the CU accessed by the terminal sends the calculation result to the mobile terminal of the user.
Claims (5)
1. A computing resource selection method under a distributed computing environment in a wireless cloud computing system is characterized in that: the method comprises the following steps:
(1) the system allocates an IP address to each calculation unit CU, wherein the IP address is the unique identification of a user in the system;
(2) each calculation unit CU stores an information table containing the IP addresses and the idle degree of other calculation units CU;
(3) a user randomly enters a certain position in a system range, a mobile terminal held by the user is accessed to a calculation unit CU closest to the user, and a calculation request is sent to the calculation unit CU;
(4) the method comprises the following steps that a calculating unit CU receives a calculating request sent by a mobile terminal, and searches a stored information table for an idle calculating unit CU;
(5) after the computing unit CU selects the computing unit CU for processing the user request according to the information table, if the computing unit CU selects the computing unit CU to process finally, the computing unit CU directly adds the computing request of the user into a task which is queued for processing, if other computing units CU are selected to process, the computing unit CU sends the computing request to the selected computing unit CU for processing according to the IP address of the selected computing unit CU, the computing unit CU for processing the computing request of the mobile terminal sends a processing result to the computing unit CU accessed by the mobile terminal, and the accessed computing unit CU feeds the processing result back to the mobile terminal;
(6) the calculation unit CU updates its status information, i.e. the amount of tasks waiting for processing, to its own information table at intervals; the calculation unit CU firstly judges whether the information stored in the information table contains the information of the calculation unit CU, and if the information contains the information of the calculation unit CU, the latest state information of the calculation unit CU is updated into the information table;
(7) in (6), if the information table stored by the calculation unit CU does not contain the own state information, it is determined whether the information table already stores information of N calculation units CU, and if less than N, the own state information is stored in the information table;
(8) in (7), if the information table has no own information and N records are already stored, comparing the own vacancy degree with the vacancy degree of the computing unit CU in the information table, and if the vacancy degree is greater than the vacancy degree of the computing unit CU stored in the information table, replacing the computing unit CU information with the minimum vacancy degree with own state information; if the idle degree stored in the information table is all larger than the idle degree of the information table, the information table is kept unchanged;
(9) and the calculation unit CU sends the processing result of the calculation request to the calculation unit CU accessed by the mobile terminal, and finally, the calculation unit CU accessed by the terminal sends the calculation result to the mobile terminal of the user.
2. The method for selecting computing resources in a distributed computing environment in a wireless cloud computing system according to claim 1, wherein: in the step (3), the information table stores information of at most N calculation units CU.
3. The method for selecting computing resources in a distributed computing environment in a wireless cloud computing system according to claim 1, wherein: in the step (4), the computing unit CU with the largest idle degree is queried first, the IP address of the computing unit CU is obtained, if the computing unit CU is far away, the computing unit CU queries the largest idle value smaller than the idle value again, the IP address of the computing unit CU is checked, if the computing unit CU is still far away, the querying is continued, and finally the computing unit CU which is close to the computing unit CU and is idle enough is selected to process the user request.
4. The method for selecting computing resources in a distributed computing environment in a wireless cloud computing system according to claim 1, wherein: in the step (4), the calculation unit CU exchanges information table information with the adjacent nodes; the calculation unit CU exchanges the information table with the information tables of the adjacent calculation units CU, and finally, the state information of the N calculation units CU with a large degree of vacancy in the two tables is stored in each table.
5. The method for selecting computing resources in a distributed computing environment in a wireless cloud computing system according to claim 1, wherein: the computing unit CU is divided into K blades by the system, each blade is an access point, and after a user computing request enters the computing unit CU, the computing unit CU distributes the computing request of one user to one blade; after receiving a computing request of a user, the computing unit CU adds the computing request to the tasks waiting for processing in line, and after the blade has processed one computing request, the computing unit CU selects one task from the tasks waiting in line to be allocated to the blade.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811185348.7A CN109460293B (en) | 2018-10-11 | 2018-10-11 | Computing resource selection method under distributed computing environment in wireless cloud computing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811185348.7A CN109460293B (en) | 2018-10-11 | 2018-10-11 | Computing resource selection method under distributed computing environment in wireless cloud computing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109460293A CN109460293A (en) | 2019-03-12 |
| CN109460293B true CN109460293B (en) | 2022-01-28 |
Family
ID=65607555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811185348.7A Active CN109460293B (en) | 2018-10-11 | 2018-10-11 | Computing resource selection method under distributed computing environment in wireless cloud computing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109460293B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109600421B (en) * | 2018-11-16 | 2021-02-26 | 国网江苏省电力有限公司南京供电分公司 | Method for selecting distributed computing resources in wireless cloud computing system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102882984A (en) * | 2012-10-24 | 2013-01-16 | 曲阜师范大学 | Method for balancing resource load of cloud computing platform |
| CN103699445A (en) * | 2013-12-19 | 2014-04-02 | 北京奇艺世纪科技有限公司 | Task scheduling method, device and system |
| CN105718364A (en) * | 2016-01-15 | 2016-06-29 | 西安交通大学 | Dynamic assessment method for ability of computation resource in cloud computing platform |
| CN105959395A (en) * | 2016-06-15 | 2016-09-21 | 徐州医科大学 | Cluster self-feedback type load balancing scheduling system and method |
| CN106020969A (en) * | 2016-05-05 | 2016-10-12 | 云神科技投资股份有限公司 | High-performance cloud computing hybrid computing system and method |
| US20170111210A1 (en) * | 2015-10-16 | 2017-04-20 | Wal-Mart Stores, Inc. | Sensor Data Analytics and Alarm Management |
-
2018
- 2018-10-11 CN CN201811185348.7A patent/CN109460293B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102882984A (en) * | 2012-10-24 | 2013-01-16 | 曲阜师范大学 | Method for balancing resource load of cloud computing platform |
| CN103699445A (en) * | 2013-12-19 | 2014-04-02 | 北京奇艺世纪科技有限公司 | Task scheduling method, device and system |
| US20170111210A1 (en) * | 2015-10-16 | 2017-04-20 | Wal-Mart Stores, Inc. | Sensor Data Analytics and Alarm Management |
| CN105718364A (en) * | 2016-01-15 | 2016-06-29 | 西安交通大学 | Dynamic assessment method for ability of computation resource in cloud computing platform |
| CN106020969A (en) * | 2016-05-05 | 2016-10-12 | 云神科技投资股份有限公司 | High-performance cloud computing hybrid computing system and method |
| CN105959395A (en) * | 2016-06-15 | 2016-09-21 | 徐州医科大学 | Cluster self-feedback type load balancing scheduling system and method |
Non-Patent Citations (2)
| Title |
|---|
| A Mobile Cloud Computing System for Emergency Management;Karan Mitra等;《IEEE Cloud Computing》;20141130;第1-9页 * |
| 基于智能空间的服务方法与技术应用研究;霍磊;《中国博士学位论文全文数据库》;中国学术期刊（光盘版）电子杂志社;20170815(第8期);第I140-1页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109460293A (en) | 2019-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109660607B (en) | Service request distribution method, service request receiving method, service request distribution device, service request receiving device and server cluster | |
| CN108900626B (en) | Data storage method, device and system in cloud environment | |
| CN111885216B (en) | DNS query method, device, equipment and storage medium | |
| CN109085999A (en) | data processing method and processing system | |
| CN106790552B (en) | A kind of content providing system based on content distributing network | |
| CN101136911A (en) | Method to download files using P2P technique and P2P download system | |
| CN110413845B (en) | Resource storage method and device based on Internet of things operating system | |
| TW201248418A (en) | Distributed caching and cache analysis | |
| CN111597259B (en) | Data storage system, method, device, electronic equipment and storage medium | |
| CN114051049A (en) | Proxy forwarding method of identifier, server and computer readable storage medium | |
| CN105975345A (en) | Video frame data dynamic equilibrium memory management method based on distributed memory | |
| WO2020094064A1 (en) | Performance optimization method, device, apparatus, and computer readable storage medium | |
| CN109460293B (en) | Computing resource selection method under distributed computing environment in wireless cloud computing system | |
| CN102325098B (en) | Group information acquisition method and system | |
| CN101141482B (en) | Network resource management system and method | |
| CN113037851B (en) | Method for cloud mobile phone system super-resolution based on storage implementation | |
| CN101431475B (en) | Settings of high-performance streaming media server and method for reading high-performance program | |
| CN106326143B (en) | A kind of caching distribution, data access, data transmission method for uplink, processor and system | |
| CN108377473B (en) | File content distribution method and device in D2D wireless cache network | |
| CN108259605B (en) | Data calling system and method based on multiple data centers | |
| CN103220363A (en) | Distributed network training resource management system based on cloud computing and scheduling method | |
| US10992743B1 (en) | Dynamic cache fleet management | |
| CN106815334A (en) | A kind of data query method and device for terminal | |
| CN112019451A (en) | Bandwidth allocation method, debugging network element, local cache server and computing equipment | |
| US10171991B2 (en) | Making subscriber data addressable as a device in a mobile data network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |