CN109451010B - Information interaction method between computers in local area network - Google Patents
Information interaction method between computers in local area network Download PDFInfo
- Publication number
- CN109451010B CN109451010B CN201811286696.3A CN201811286696A CN109451010B CN 109451010 B CN109451010 B CN 109451010B CN 201811286696 A CN201811286696 A CN 201811286696A CN 109451010 B CN109451010 B CN 109451010B
- Authority
- CN
- China
- Prior art keywords
- computer
- task
- main server
- shared
- space
- 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
-
- 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
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- 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
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
-
- 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
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1029—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers using data related to the state of servers by a load balancer
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Computer And Data Communications (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses an information interaction method among computers in a local area network, which comprises the following steps: s1, establishing a local area network, and setting a main server to enable each computer to establish data butt joint with the main server; s2, each computer sets a certain proportion of residual computation space as shared computation space, and sends the set proportion to the main server; s3, the main server establishes a distribution model of the time variation of the corresponding shared operation space of each computer in a unit day; s4, after receiving the operation task, any computer disassembles the operation task, and transmits each independent operation part and the corresponding operation amount to the main server; s5, the main server distributes tasks to the distribution model; and S6, the main task computer and other shared computation spaces respectively perform synchronous computation of computation tasks to complete the total computation tasks. When the method is applied, the interactive processing of data among computers in the local area network can be realized, and further the integrated utilization of computing resources is realized.
Description
Technical Field
The invention relates to the technical field of computer data processing, in particular to an information interaction method among computers in a local area network.
Background
With the development of computer technology and network technology, data information can be shared in a local area network formed by a plurality of computers, and simultaneously, with the development of multimedia technology, the complexity and the volume of data to be processed by each computer are higher and larger. The existing personal computer has limited data processing capacity, and if a huge and complicated data processing task is met, the operation of the personal computer is blocked or even down, so that inconvenience is brought to users.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an information interaction method among computers in a local area network, which can realize the interactive processing of data among the computers in the local area network during application, further realize the integrated utilization of computing resources and prevent the phenomenon of pause caused by overlarge computing amount of an individual computer.
The invention is realized by the following technical scheme:
a method for information interaction among computers in a local area network comprises the following steps:
s1, establishing a local area network, and arranging a main server in the local area network to enable each computer in the local area network to establish a data interaction channel with the main server;
s2, each computer in the local area network sends the change situation of the used operation space along with time to the main server in real time, sets a certain proportion of the residual operation space as a shared operation space, and sends the proportion of the set shared operation space to the residual operation space to the main server;
s3, the main server establishes a distribution model of the shared computation space of each computer changing with time within a unit day according to the change situation of the computation space used by each computer with time and the proportion of the set shared computation space to the rest computation space;
s4, after receiving the operation task, any computer in the LAN preliminarily analyzes the operation task, disassembles the task, separates out parts capable of being independently operated, estimates the operation amount of each independent operation part, and transmits each independent operation part and the corresponding operation amount to the main server;
s5, the main server adaptively matches each independent operation part transmitted by the main task computer and the corresponding operation amount with the distribution model, and selects the corresponding shared operation space to perform task distribution transmission of the independent operation part;
s6, the main task computer and other shared operation spaces distributed to the tasks respectively perform synchronous calculation of the operation tasks, the other shared operation spaces feed back the operation results to the main server in real time, and then the operation results are transmitted to the main task computer by the main server, and the main task computer completes the calculation of the total operation tasks by combining the operation process of the main task computer and the operation results of each independent operation part fed back by the other shared operation spaces.
Preferably, in step S1, a data interface is established between each computer in the lan and the host server through TCP/IP protocol.
Preferably, in step S2, the remaining computation space other than the shared computation space is used as the buffer computation space.
Preferably, in step S2, each computer also allocates a separate storage unit for storing the computing task to the shared computation space.
Preferably, in step S4, when the calculation task is disassembled, the collaborative optimization algorithm is used to decompose the total calculation task into several individual calculation parts, and the individual calculation parts are collaboratively optimized.
Preferably, each computer in the local area network sends each startup and shutdown information to the main server, and the main server dynamically marks the corresponding startup and shutdown information in the distribution model.
Preferably, the shared computing area of the shutdown computer is not considered when the main server performs task allocation.
Preferably, each computer in the local area network displays the task state of the shared computation space in real time, and optionally returns the distributed computation task to the main server before shutdown, and the distributed computation task is redistributed by the main server.
Preferably, in step S5, when the main server performs adaptive matching on each individual computation part task, the estimated computation amount and the required computation time of each individual computation part are determined, then each individual computation part is sequentially extracted according to the descending order of the estimated computation amount, and a shared computation space with the computation amount not less than the corresponding estimated computation amount in the required computation time period is selected for task allocation according to the distribution model.
Preferably, each computer in the local area network sends the change situation of the computation space used every day along with time to the main server in real time, the main server combines the change situation of the day with the existing distribution model to perform dynamic weighting adjustment on the distribution model, and the adjusted distribution model is used in the next day.
The invention has the following advantages and beneficial effects:
1. the information interaction method among the computers in the local area network can realize the interactive processing of data among the computers in the local area network, further realize the integrated utilization of computing resources and prevent the phenomenon of pause caused by overlarge computing amount of an individual computer.
2. The invention relates to an information interaction method among computers in a local area network.A buffer operation space is arranged in each computer operation unit in the local area network and is used for performing buffer operation on part of operation tasks exceeding the upper limit of a shared operation space, so that the computers assisting the operation are prevented from being blocked.
3. The invention relates to an information interaction method among computers in a local area network, which decomposes a total operation task into independent operation parts by adopting a cooperative optimization algorithm, synchronously and respectively calculates, and then synthesizes a final operation result, thereby improving the calculation efficiency.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a schematic diagram of the implementation steps of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Examples
As shown in fig. 1, a method for information interaction between computers in a local area network includes the following steps:
s1, establishing a local area network, and arranging a main server in the local area network to enable each computer in the local area network to establish a data interaction channel with the main server;
s2, each computer in the local area network sends the change situation of the used operation space along with time to the main server in real time, sets a certain proportion of the residual operation space as a shared operation space, and sends the proportion of the set shared operation space to the residual operation space to the main server;
s3, the main server establishes a distribution model of the shared computation space of each computer changing with time within a unit day according to the change situation of the computation space used by each computer with time and the proportion of the set shared computation space to the rest computation space;
s4, after receiving the operation task, any computer in the LAN preliminarily analyzes the operation task, disassembles the task, separates out parts capable of being independently operated, estimates the operation amount of each independent operation part, and transmits each independent operation part and the corresponding operation amount to the main server;
s5, the main server adaptively matches each independent operation part transmitted by the main task computer and the corresponding operation amount with the distribution model, and selects the corresponding shared operation space to perform task distribution transmission of the independent operation part;
s6, the main task computer and other shared operation spaces distributed to the tasks respectively perform synchronous calculation of the operation tasks, the other shared operation spaces feed back the operation results to the main server in real time, and then the operation results are transmitted to the main task computer by the main server, and the main task computer completes the calculation of the total operation tasks by combining the operation process of the main task computer and the operation results of each independent operation part fed back by the other shared operation spaces.
In step S1, a data interface is established between each computer in the lan and the host server via the TCP/IP protocol.
In step S2, the remaining computation spaces other than the shared computation space of each computer are used as buffer computation spaces for performing buffer computation on a part of the computation tasks exceeding the upper limit of the shared computation space.
In step S2, each computer is also assigned a separate storage unit for storing computing tasks for the shared computation space.
In step S4, when the calculation task is disassembled, the collaborative optimization algorithm is used to decompose the total calculation task into a plurality of individual calculation parts, and the individual calculation parts are collaboratively optimized.
The principle of the collaborative optimization algorithm is to decompose a complex objective function into simple sub-objective functions and then perform collaborative optimization on the sub-objective functions. Specifically, the collaborative optimization is to optimize each sub-target function and simultaneously comprehensively consider the results of other sub-target functions, so that the optimization results between the sub-target functions can be consistent. The consistency of the optimization result means that the value of each variable can be consistent in the optimization result of each sub-target function. In general, it can be demonstrated that an optimal solution is obtained if the values of the variables are consistent. The collaborative optimization algorithm has no local optimization problem and has very good convergence characteristics. The method well solves many practical nonlinear optimization and combination optimization problems. If the objective function is a function of n variables:
E(x1,x2,...,xn) Abbreviated as E (x),
the collaborative optimization algorithm first decomposes it into n simple sub-objective functions:
E(x)=E1(x)+E2(x)+...+En(x).
if each sub-targeting function is optimized separately, their results are difficult to achieve consistency. Such as the variable xiThe optimal solution values in the sub-targeting functions that contain it are difficult to be the same. For i 1, 2, if we take Ei(x) In the optimal solution of (1), xiAs the value of the variable, expressed as
Where X isiIs Ei(x) Set of variables of, Xi\xiSet of finger variables XiRemoval of element xi,It is difficult to be the optimal solution of the original objective function. In order to make the optimization results consistent among the sub-target functions, the collaborative optimization algorithm optimizes each sub-target function Ei(x) While considering the results of other sub-targeting functions:
the specific method is that each sub-objective function is corrected by numerical weighting according to the optimization results of other sub-objective functions as follows:
where lambda isk,wijAs a weighting coefficient, satisfies 0 ≦ λk,wijLess than or equal to 1. And then optimizing the modified sub-objective function, and iteratively placing the optimized result into the modified sub-objective function. The iterative equation of the collaborative optimization algorithm is as follows:
the collaborative optimization results make the value of each variable consistent in the optimization results of each sub-targeting function. If they are consistent, the optimized solution of the sub-objective function is the optimal solution.
Each computer in the local area network sends the startup and shutdown information to the main server every time, the main server dynamically marks the corresponding startup and shutdown information in the distribution model, and the shared operation area of the shutdown computer is not considered when the main server distributes tasks.
And each computer in the local area network displays the task state of the shared operation space in real time, and the distributed calculation tasks can be returned to the main server before shutdown and redistributed by the main server.
In step S5, when the main server performs adaptive matching of each individual computation part task, the estimated computation amount and the required computation time of each individual computation part are determined, then the individual computation parts are sequentially extracted according to the descending order of the estimated computation amount, and a shared computation space with the computation amount not less than the corresponding estimated computation amount in the required computation time period is selected for task allocation by referring to the distribution model.
Each computer in the local area network sends the change situation of the used operation space along with time to the main server in real time, the main server combines the change situation of the day with the existing distribution model to dynamically weight and adjust the distribution model, and the adjusted distribution model is used in the next day.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (7)
1. A method for information interaction among computers in a local area network is characterized by comprising the following steps:
s1, establishing a local area network, and arranging a main server in the local area network to enable each computer in the local area network to establish a data interaction channel with the main server;
s2, each computer in the local area network sends the change situation of the used operation space along with time to the main server in real time, sets a certain proportion of the residual operation space as a shared operation space, and sends the proportion of the set shared operation space to the residual operation space to the main server; taking the rest operation space except the shared operation space of each computer as a buffer operation space for carrying out buffer operation on part of operation tasks exceeding the upper limit of the shared operation area;
s3, the main server establishes a distribution model of the shared computation space of each computer changing with time within a unit day according to the change situation of the computation space used by each computer with time and the proportion of the set shared computation space to the rest computation space;
s4, after receiving the operation task, any computer in the LAN preliminarily analyzes the operation task, disassembles the task, separates out parts capable of being independently operated, estimates the operation amount of each independent operation part, and transmits each independent operation part and the corresponding operation amount to the main server;
s5, the main server adaptively matches each independent operation part transmitted by the main task computer and the corresponding operation amount with the distribution model, and selects the corresponding shared operation space to perform task distribution transmission of the independent operation part;
when the main server carries out adaptive matching on tasks of each individual operation part, firstly, the estimated operation amount and the required operation time of each individual operation part are determined, then, the individual operation parts are sequentially extracted according to the sequence of the estimated operation amount from large to small, and shared operation spaces with the operation amounts not smaller than the corresponding estimated operation amount in the required operation time period are selected according to the distribution model to carry out task allocation; each computer in the local area network sends the change situation of the used operation space along with time to a main server in real time, the main server combines the change situation of the current day with the existing distribution model to dynamically weight and adjust the distribution model, and the adjusted distribution model is used in the next day;
s6, the main task computer and other shared operation spaces distributed to the tasks respectively perform synchronous calculation of the operation tasks, the other shared operation spaces feed back the operation results to the main server in real time, and then the operation results are transmitted to the main task computer by the main server, and the main task computer completes the calculation of the total operation tasks by combining the operation process of the main task computer and the operation results of each independent operation part fed back by the other shared operation spaces.
2. The method of claim 1, wherein in step S1, the computers in the lan interface with the host server via TCP/IP protocol.
3. The method of claim 1, wherein in step S2, each computer further allocates a separate storage unit for storing the computing task to the shared computation space.
4. The method of claim 1, wherein in step S4, when the calculation task is disassembled, the cooperative optimization algorithm is used to decompose the total calculation task into several independent calculation parts, and the independent calculation parts are cooperatively optimized.
5. The method as claimed in claim 1, wherein each computer in the lan sends the startup and shutdown information to the host server, and the host server dynamically marks the corresponding startup and shutdown information in the distribution model.
6. The method as claimed in claim 5, wherein the shared operating area of the shutdown computer is not considered when the main server performs task allocation.
7. The method as claimed in claim 6, wherein the computers in the lan display the task status of the shared computation space in real time, and optionally return the assigned computation task to the main server before shutdown, and the computation task is redistributed by the main server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811286696.3A CN109451010B (en) | 2018-10-31 | 2018-10-31 | Information interaction method between computers in local area network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811286696.3A CN109451010B (en) | 2018-10-31 | 2018-10-31 | Information interaction method between computers in local area network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109451010A CN109451010A (en) | 2019-03-08 |
CN109451010B true CN109451010B (en) | 2021-08-17 |
Family
ID=65549704
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811286696.3A Active CN109451010B (en) | 2018-10-31 | 2018-10-31 | Information interaction method between computers in local area network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109451010B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111970342B (en) * | 2020-08-03 | 2024-01-30 | 江苏方天电力技术有限公司 | Edge computing system of heterogeneous network |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103428217A (en) * | 2013-08-19 | 2013-12-04 | 中国航空动力机械研究所 | Method and system for dispatching distributed parallel computing job |
CN104506600A (en) * | 2014-12-16 | 2015-04-08 | 苏州海博智能***有限公司 | Computation resource sharing method, device and system as well as client side and server |
CN106572042A (en) * | 2015-10-09 | 2017-04-19 | 华为技术有限公司 | Method and equipment for data transmission |
CN108427602A (en) * | 2017-02-14 | 2018-08-21 | 全球能源互联网研究院 | A kind of coordinated dispatching method and device of distributed computing task |
CN108446352A (en) * | 2018-03-09 | 2018-08-24 | 深圳市网信联动通信技术股份有限公司 | A kind of method and system of processing mass data |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5625853B2 (en) * | 2010-12-10 | 2014-11-19 | ソニー株式会社 | Distributed processing system, arithmetic device, arithmetic control device, arithmetic control method, arithmetic task completion probability calculation method, and program |
-
2018
- 2018-10-31 CN CN201811286696.3A patent/CN109451010B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103428217A (en) * | 2013-08-19 | 2013-12-04 | 中国航空动力机械研究所 | Method and system for dispatching distributed parallel computing job |
CN104506600A (en) * | 2014-12-16 | 2015-04-08 | 苏州海博智能***有限公司 | Computation resource sharing method, device and system as well as client side and server |
CN106572042A (en) * | 2015-10-09 | 2017-04-19 | 华为技术有限公司 | Method and equipment for data transmission |
CN108427602A (en) * | 2017-02-14 | 2018-08-21 | 全球能源互联网研究院 | A kind of coordinated dispatching method and device of distributed computing task |
CN108446352A (en) * | 2018-03-09 | 2018-08-24 | 深圳市网信联动通信技术股份有限公司 | A kind of method and system of processing mass data |
Also Published As
Publication number | Publication date |
---|---|
CN109451010A (en) | 2019-03-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107911478B (en) | Multi-user calculation unloading method and device based on chemical reaction optimization algorithm | |
CN111399933B (en) | DNN task unloading method and terminal in edge-cloud hybrid computing environment | |
CN105989374B (en) | Method and equipment for training model on line | |
Chen et al. | Learning-based resource allocation in cloud data center using advantage actor-critic | |
Dubey | Kernel methods for cooperative multi-agent contextual bandits | |
CN111475274A (en) | Cloud collaborative multi-task scheduling method and device | |
CN110362586B (en) | Multi-center biomedical data cooperative processing system and method without patient data sharing | |
CN106878415A (en) | The load-balancing method and device of data consumption | |
CN110401936A (en) | A kind of task unloading and resource allocation methods based on D2D communication | |
CN111260076A (en) | Block chain-based edge node training method, block chain and storage medium | |
CN109451010B (en) | Information interaction method between computers in local area network | |
US11106998B2 (en) | System with hybrid communication strategy for large-scale distributed deep learning | |
CN113672372B (en) | Multi-edge collaborative load balancing task scheduling method based on reinforcement learning | |
Hsu et al. | Cooperative convolutional neural network deployment over mobile networks | |
CN111601328B (en) | Mobile edge computing device and method | |
Phuoc Hung et al. | An adaptive procedure for task scheduling optimization in mobile cloud computing | |
Wang et al. | Joint power control and task offloading in collaborative edge–cloud computing networks | |
Zhang et al. | Qoe-oriented mobile virtual reality game in distributed edge networks | |
Tang et al. | Exploring the interactions of communication, computing and caching in cloud RAN under two timescale. | |
CN110392377A (en) | A kind of 5G super-intensive networking resources distribution method and device | |
CN113254215B (en) | Data processing method and device, storage medium and electronic equipment | |
CN112506644B (en) | Task scheduling method and system based on cloud edge-side hybrid computing mode system | |
CN111818119B (en) | Improved spider cluster-based data service resource optimization scheduling method | |
CN113015144B (en) | Social perception combined calculation task network parameter optimization method and system | |
CN114006816B (en) | Mobile cloud computing task unloading and resource allocation method and system under uncertain condition |
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 |