CN111106946B - Method and system for reconstructing edge computing node of networking equipment - Google Patents
Method and system for reconstructing edge computing node of networking equipment Download PDFInfo
- Publication number
- CN111106946B CN111106946B CN201811266003.4A CN201811266003A CN111106946B CN 111106946 B CN111106946 B CN 111106946B CN 201811266003 A CN201811266003 A CN 201811266003A CN 111106946 B CN111106946 B CN 111106946B
- Authority
- CN
- China
- Prior art keywords
- networking equipment
- networking
- idle
- idle computing
- computing resources
- 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
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
- H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
-
- 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
- H04L67/34—Network arrangements or protocols for supporting network services or applications involving the movement of software or configuration parameters
-
- 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
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a method and a system for reconstructing edge computing nodes of networking equipment. The method comprises the following steps: acquiring idle computing resource information corresponding to the networking equipment through preset software in the networking equipment, and sending state information of the networking equipment to a scheduling server through a heartbeat protocol; calculating available idle calculation resources corresponding to the networking equipment according to the received state information of the networking equipment and preset algorithm logic; and dividing the work tasks to be calculated according to the available idle calculation resources of the networking equipment and a preset task scheduling algorithm, and distributing the divided work tasks to the corresponding networking equipment. The method for reconstructing the edge computing node of the networking equipment provided by the invention reconstructs the networking equipment into the edge computing node of the scheduling server, thereby not only effectively utilizing the idle computing resources of the networking equipment, but also solving the problem of insufficient computing capability of the scheduling server under large-scale complex tasks.
Description
Technical Field
The invention relates to the technical field of idle computing resource utilization of networking equipment, in particular to a method and a system for reconstructing an edge computing node of the networking equipment.
Background
Existing network-connectable devices are generally under-utilized, the time in an idle state accounts for or even exceeds 50%, for example, a home router is generally not powered off for 24 hours, but is generally used only when a person is at home, which causes the idle running or waste of resources.
On the other hand, the centralized computing power of the server is limited, a large amount of time is consumed for some complex computing tasks such as big data, picture processing, video transcoding and the like, if the tasks are divided into small units and distributed to the edge computing nodes, the computing tasks which can be completed by one server within 1 hour can be changed into the computing tasks which can be distributed to the N edge computing nodes and can be completed within 1 minute or less, and the overall efficiency is greatly improved. Therefore, a need exists for a method and system for improving the capacity of networked devices to serve as edge computing nodes, so that the server can make full use of the idle computing resources of the networked devices, and the problem of insufficient centralized computing power of the server is solved.
Disclosure of Invention
In order to solve the problems in the prior art, embodiments of the present invention provide a method and a system for reconstructing an edge computing node of a networking device. The technical scheme is as follows:
in one aspect, an embodiment of the present invention provides a method for reconstructing an edge computing node of a networking device, where the method includes:
through the software that predetermines in the networking device, acquire the idle computational resource information that the networking device corresponds to send the state information of networking device to dispatch server through the heartbeat protocol, the state information of networking device includes: the ID information and the idle computing resource information of the networking equipment are communicated and connected with the scheduling server through the Internet;
calculating available idle calculation resources corresponding to the networking equipment according to the received state information of the networking equipment and a preset algorithm logic;
dividing the work tasks to be calculated according to available idle computing resources of the networking equipment and a preset task scheduling algorithm, distributing the divided work tasks to the corresponding networking equipment, reforming the networking equipment into corresponding edge computing nodes, and assisting the scheduling server to perform computing processing on the work tasks.
In the method for reconstructing an edge computing node of a networking device according to the embodiment of the present invention, acquiring, by using software preset in the networking device, idle computing resource information corresponding to the networking device includes:
acquiring available proportion information of a processor and main frequency information of the processor corresponding to the networking equipment through software preset in the networking equipment;
and multiplying the available proportion of the processor of the obtained networking equipment by the main frequency of the processor to obtain the idle computing resource information corresponding to the networking equipment.
In the method for reconstructing an edge computing node of a networking device according to the embodiment of the present invention, the computing available idle computing resources corresponding to the networking device according to the received state information of the networking device and according to a preset algorithm logic includes:
acquiring an available proportion of idle computing resources corresponding to network equipment according to received idle computing resources of the networking equipment and preset algorithm logic, wherein the preset algorithm logic comprises the following steps: the corresponding relation between the free computing resources of the network equipment and the available proportion of the free computing resources corresponding to the free computing resources;
and multiplying the obtained available proportion of the idle computing resources by the idle computing resources of the network equipment to obtain the available idle computing resources corresponding to the network equipment.
In the method for reconstructing an edge computing node of a networking device according to the embodiment of the present invention, the preset task scheduling algorithm includes: any one of an equal calculation time splitting method, an equal calculation amount splitting method and a random splitting method;
the dividing of the work tasks to be calculated according to the available idle computing resources of the networking equipment and a preset task scheduling algorithm comprises the following steps:
dividing the work tasks to be calculated according to the mode that a plurality of networking devices to be distributed with the work tasks can finish calculation at the same time, or,
dividing the work task to be calculated according to a splitting mode with equal calculation amount, or,
and dividing the work tasks to be calculated according to a random splitting mode.
In the method for reconstructing an edge computing node of a networking device according to the embodiment of the present invention, the allocating the divided work tasks to the corresponding networking devices, reconstructing the networking devices into the corresponding edge computing nodes, and assisting the scheduling server to perform the computation processing of the work tasks includes:
and sending the task downloading address and the calculation result return address corresponding to the divided work task to corresponding networking equipment, so that the networking equipment can download the corresponding work task at the task downloading address, and feeding back the calculated result according to the calculation result return address.
In another aspect, an embodiment of the present invention provides a system for reconstructing an edge computing node of a networked device, where the system includes:
the networking equipment is used for acquiring idle computing resource information corresponding to the networking equipment through preset software, and sending the state information of the networking equipment to the scheduling server through a heartbeat protocol, wherein the state information of the networking equipment comprises: the ID information and the idle computing resource information of the networking equipment are communicated and connected with the scheduling server through the Internet;
the scheduling server is used for calculating available idle calculation resources corresponding to the networking equipment according to the received state information of the networking equipment and a preset algorithm logic;
the scheduling server is further used for dividing the work tasks to be calculated according to the available idle computing resources of the networking equipment and a preset task scheduling algorithm, distributing the divided work tasks to the corresponding networking equipment, transforming the networking equipment into corresponding edge computing nodes, and assisting the scheduling server in computing the work tasks.
In the system for reconstructing an edge computing node of a networking device according to the embodiment of the present invention, the networking device is further configured to obtain, through preset software, processor available ratio information and processor dominant frequency information corresponding to the networking device;
and the networking equipment is also used for obtaining the idle computing resource information corresponding to the networking equipment by multiplying the available proportion of the processor of the networking equipment by the main frequency of the processor.
In the system for reconstructing an edge computing node of a networked device according to the embodiment of the present invention, the scheduling server is further configured to obtain an available proportion of idle computing resources corresponding to the networked device according to the received idle computing resources of the networked device and a preset algorithm logic, where the preset algorithm logic includes: the corresponding relation between the free computing resources of the network equipment and the available proportion of the corresponding free computing resources;
the scheduling server is further configured to multiply the obtained available proportion of the idle computing resources by the idle computing resources of the network device to obtain available idle computing resources corresponding to the network device.
In the system for reconstructing an edge computing node of a networked device according to the embodiment of the present invention, the preset task scheduling algorithm includes: any one of an equal calculation time splitting method, an equal calculation amount splitting method and a random splitting method;
the scheduling server is further configured to divide the work tasks to be calculated according to a manner that a plurality of networked devices to which the work tasks are to be allocated can finish calculating at the same time, or,
dividing the work task to be calculated according to a splitting mode with equal calculated amount, or,
and dividing the work tasks to be calculated according to a random splitting mode.
In the system for reconstructing an edge computing node of a networking device according to the embodiment of the present invention, the scheduling server is further configured to send the task download address and the computation result return address corresponding to the divided work tasks to the corresponding networking device, so that the networking device downloads the corresponding work task at the task download address, and feeds back the computed result according to the computation result return address.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
acquiring idle computing resource information corresponding to the networking equipment through preset software in the networking equipment, and sending state information of the networking equipment to a scheduling server through a heartbeat protocol; then, according to the received state information of the networking equipment and a preset algorithm logic, calculating available idle calculation resources corresponding to the networking equipment; and finally, dividing the work tasks to be calculated according to available idle computing resources of the networking equipment and a preset task scheduling algorithm, distributing the divided work tasks to the corresponding networking equipment, reforming the networking equipment into corresponding edge computing nodes, and assisting the scheduling server to perform computing processing on the work tasks. Therefore, the networked equipment is reformed into the edge computing node of the scheduling server, so that the idle computing resources of the networked equipment can be effectively utilized, and the problem of insufficient computing capacity of the scheduling server under large-scale complex tasks is solved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for reconstructing an edge computing node of a networking device according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a system for reconstructing an edge computing node of a networking device according to a second embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Example one
An embodiment of the present invention provides a method for reconstructing an edge computing node of a networking device, which is suitable for utilizing idle computing resources of the networking device, and with reference to fig. 1, the method may include:
step S11, acquiring idle computing resource information corresponding to the networking equipment through preset software in the networking equipment, and sending the state information of the networking equipment to a scheduling server through a heartbeat protocol, wherein the state information of the networking equipment comprises: and the ID information and the idle computing resource information of the networking equipment are communicated and connected with the scheduling server through the Internet.
In this embodiment, many of the networked devices are not operated at full capacity, and sometimes even many computing resources are idle, and the idle computing resources of the networked devices are reported to the scheduling server through software preset in the networked devices, so that the idle computing resources can be reused by the scheduling server.
Specifically, the step S11 can be implemented as follows:
a1, acquiring available proportion information of a processor and dominant frequency information of the processor corresponding to the networking equipment through preset software in the networking equipment.
And b1, multiplying the available proportion of the processor of the obtained networking equipment by the main frequency of the processor to obtain the idle computing resource information corresponding to the networking equipment.
In this embodiment, the networking device may first obtain an available ratio of a processor (e.g., a CPU, a GPU, etc.) of the networking device, and multiply the available ratio by a main frequency of the processor to obtain an idle calculation frequency (in HZ, which is the number of executable instructions per second), that is, an idle calculation resource corresponding to the networking device. Then the networking device can carry the ID information and the idle computing resource information of the networking device in the heartbeat protocol information and report the information to the scheduling server, and the scheduling server can distribute computing tasks to the networking device after acquiring the idle computing capability of the networking device and utilize the idle computing resource of the networking device.
And S12, calculating available idle calculation resources corresponding to the networking equipment according to the received state information of the networking equipment and preset algorithm logic.
In this embodiment, the spare computing resources of the networking devices are not completely exhausted (the networking devices are not easy to run for a long time at full capacity), and therefore, the spare computing resources available to the networking devices need to be sorted out for utilization.
Specifically, the step S12 may be implemented as follows:
a2, obtaining the available proportion of the idle computing resources corresponding to the network equipment according to the received idle computing resources of the networking equipment and a preset algorithm logic, wherein the preset algorithm logic comprises: a correspondence between an idle computing resource of a network device and its corresponding idle computing resource availability proportion.
And b2, multiplying the obtained available proportion of the idle computing resources by the idle computing resources of the network equipment to obtain the available idle computing resources corresponding to the network equipment.
In this embodiment, the predetermined algorithm logic may be a form of gradient proportion, such as: the gradient proportion may be such that when 0-straw-L-straw-knot 100MHZ, the proportion of available idle computing resources is 50%, when 100MHZ-straw-L-straw-knot 300MHZ, the proportion of available idle computing resources is 60%, and so on, where L is the idle computing resources of the network device. Therefore, the available idle computing resources of the networking equipment are obtained by multiplying the idle computing resources of the networking equipment by the available proportion of the idle computing resources, the rationality of the utilization of the idle computing resources of the networking equipment is further ensured, and the residual resources are prevented from being exhausted.
And S13, dividing the work tasks to be calculated according to the available idle computing resources of the networking equipment and a preset task scheduling algorithm, distributing the divided work tasks to the corresponding networking equipment, reforming the networking equipment into corresponding edge computing nodes, and assisting the scheduling server to calculate the work tasks.
Specifically, in step S13, the preset task scheduling algorithm includes: any one of an equal calculation time splitting method, an equal calculation amount splitting method, and a random splitting method.
In the step S13, the work tasks to be calculated are divided according to the available idle computing resources of the networked devices and the preset task scheduling algorithm, which can be implemented in the following manner:
dividing the work tasks to be calculated according to the mode that a plurality of networking devices to be distributed with the work tasks can finish calculation at the same time, or,
dividing the work task to be calculated according to a splitting mode with equal calculation amount, or,
and dividing the work tasks to be calculated according to a random splitting mode.
In this embodiment, each of the networked devices has a different remaining computing capacity (i.e., available spare computing resources), such as networked device a, networked device B, and networked device C, which are 200MHZ, 500MHZ, and 1000MHZ, respectively; the unit of the calculation amount of the split task is HZ, wherein HZ represents that an instruction is executed once, and if the calculation amount of the work task to be calculated is 100MHZ, the task needs to execute 100M (M is an abbreviation of 100 ten thousand) instructions to complete.
Equal computation time splitting method: the method includes that a scheduling server divides a work task to be calculated into three calculation tasks a, B and C, the three calculation tasks a, B and C are respectively sent to equipment terminals A, B and C, the completion time of the three calculation tasks is the same, for example, 10 seconds, and the calculation amount of the a, B and C is 2000MHZ, 5000MHZ and 10000MHZ respectively.
Equal calculation amount splitting method: the method is that the scheduling server divides the work task to be calculated into tasks with the same calculation amount, such as the tasks with the calculation amount of 1000MHZ, and then the completion time of A, B and C is 5 seconds, 2 seconds and 1 second respectively.
A random splitting method: the method is that a scheduling server allocates random calculation amount to each networking device, for example, a is allocated with 100MHZ task, B is allocated with 50MHZ task, C is allocated with 500MHZ task, and the calculation amount of the tasks is random.
Further, in step S13, the divided work tasks are allocated to corresponding networking devices, the networking devices are modified into corresponding edge computing nodes, and the auxiliary scheduling server performs the computation processing of the work tasks, which may be implemented by the following method:
and sending the task downloading address and the calculation result return address corresponding to the divided work task to corresponding networking equipment, so that the networking equipment can download the corresponding work task at the task downloading address, and feeding back the calculated result according to the calculation result return address.
In the embodiment, the scheduling server divides the work tasks to be calculated and distributes the work tasks to the corresponding networking devices in a reasonable mode, and the scheduling server is assisted to calculate the work tasks through the available idle calculation resources of the networking devices, so that the idle calculation resources of the networking devices are effectively utilized, and the problem of insufficient calculation capacity of the server under large-scale complex tasks is solved.
The method comprises the steps that idle computing resource information corresponding to the networking equipment is obtained through software preset in the networking equipment, and state information of the networking equipment is sent to a scheduling server through a heartbeat protocol; then, according to the received state information of the networking equipment and a preset algorithm logic, calculating available idle calculation resources corresponding to the networking equipment; and finally, dividing the work tasks to be calculated according to available idle computing resources of the networking equipment and a preset task scheduling algorithm, distributing the divided work tasks to the corresponding networking equipment, reforming the networking equipment into corresponding edge computing nodes, and assisting the scheduling server to perform computing processing on the work tasks. Therefore, the networked equipment is reformed into the edge computing node of the scheduling server, so that the idle computing resources of the networked equipment can be effectively utilized, and the problem of insufficient computing capacity of the scheduling server under large-scale complex tasks is solved.
Example two
The embodiment of the present invention provides a system for reconstructing an edge computing node of a networking device, which executes the method described in the first embodiment, and with reference to fig. 2, the system may include: networking device 100, dispatch server 200, networking device 100 is through internet and dispatch server 200 communication connection.
The networking device 100 is configured to acquire, through preset software, idle computing resource information corresponding to the networking device, and send state information of the networking device to the scheduling server through a heartbeat protocol, where the state information of the networking device includes: ID information and free computing resource information for the networked devices.
In this embodiment, many of the networked devices are not operated at full capacity, and sometimes even many computing resources are idle, and the idle computing resources of the networked devices are reported to the scheduling server through software preset in the networked devices, so that the idle computing resources can be reused by the scheduling server.
And the scheduling server 200 is configured to calculate available idle calculation resources corresponding to the networking device according to the received state information of the networking device and according to a preset algorithm logic.
In this embodiment, the idle computing resources of the networked devices are not completely used up (the networked devices are not easy to run full-load computing for a long time), and therefore, the available idle computing resources of the networked devices need to be sorted out for utilization.
The scheduling server 200 is further configured to divide the work tasks to be calculated according to the available idle computing resources of the networking devices and a preset task scheduling algorithm, allocate the divided work tasks to the corresponding networking devices, modify the networking devices into corresponding edge computing nodes, and assist the scheduling server in performing computing processing on the work tasks.
In the embodiment, the scheduling server divides the work tasks to be calculated and distributes the work tasks to the corresponding networking devices in a reasonable mode, and the available idle computing resources of the networking devices are used for assisting the scheduling server in computing the work tasks, so that the idle computing resources of the networking devices are effectively utilized, and the problem that the computing capacity of the server is insufficient under large-scale complex tasks is solved.
Specifically, the networking device 100 is further configured to obtain, through preset software, processor available ratio information and processor dominant frequency information corresponding to the networking device;
the networking device 100 is further configured to obtain the idle computing resource information corresponding to the networking device by multiplying the processor availability ratio of the obtained networking device by the processor dominant frequency.
In this embodiment, the networking device may first obtain an available ratio of a processor (e.g., CPU, GPU, etc.) of the networking device, and multiply the available ratio by a main frequency of the processor to obtain an idle computation frequency (in HZ, i.e., the number of executable instructions per second), i.e., an idle computation resource corresponding to the networking device. And then the networking equipment can carry the ID information and the idle computing resource information of the networking equipment in the heartbeat protocol information and report the information to the scheduling server, and the scheduling server can distribute computing tasks to the networking equipment after acquiring the idle computing capacity of the networking equipment and utilize the idle computing resources of the networking equipment.
Further, the scheduling server 200 is further configured to obtain an available proportion of idle computing resources corresponding to the network device according to the received idle computing resources of the networking device and a preset algorithm logic, where the preset algorithm logic includes: a correspondence between free computing resources of a network device and their corresponding free computing resource availability ratios.
The scheduling server 200 is further configured to multiply the obtained available proportion of the idle computing resource by the idle computing resource of the network device to obtain an available idle computing resource corresponding to the network device.
In this embodiment, the predetermined algorithm logic may be a form of gradient proportion, such as: the gradient proportion may be such that when 0-straw-L-straw-knot 100MHZ, the proportion of available idle computing resources is 50%, when 100MHZ-straw-L-straw-knot 300MHZ, the proportion of available idle computing resources is 60%, and so on, where L is the idle computing resources of the network device. Therefore, the available idle computing resources of the networking equipment are obtained by multiplying the idle computing resources of the networking equipment by the available proportion of the idle computing resources, the idle computing resources of the networking equipment are further ensured to be reasonably utilized, and the residual resources are prevented from being exhausted.
Specifically, the preset task scheduling algorithm includes: any one of an equal calculation time splitting method, an equal calculation amount splitting method and a random splitting method;
the scheduling server 200 is further configured to divide the work task to be calculated according to a manner that a plurality of networked devices to which the work task is to be allocated can finish calculating at the same time, or,
dividing the work task to be calculated according to a splitting mode with equal calculation amount, or,
and dividing the work tasks to be calculated according to a random splitting mode.
In this embodiment, each of the networked devices has a different remaining computing capacity (i.e., available spare computing resources), such as networked device a, networked device B, and networked device C, which are 200MHZ, 500MHZ, and 1000MHZ, respectively; the unit of the calculation amount of the split task is HZ, and HZ represents that an instruction is executed once, and if the calculation amount of the work task to be calculated is 100MHZ, the task needs to be executed 100M (M is an abbreviation of 100 ten thousand) times of instructions to complete.
Equal computation time splitting method: the method includes that a scheduling server divides a work task to be calculated into three calculation tasks a, B and C, the three calculation tasks a, B and C are respectively sent to equipment terminals A, B and C, the completion time of the three calculation tasks is the same, for example, 10 seconds, and the calculation amount of the a, B and C is 2000MHZ, 5000MHZ and 10000MHZ respectively.
Equal calculation amount splitting method: the method is that the scheduling server divides the work task to be calculated into tasks with the same calculation amount, such as the tasks with the calculation amount of 1000MHZ, and then the completion time of A, B and C is 5 seconds, 2 seconds and 1 second respectively.
A random splitting method: the method is that a scheduling server allocates random calculation amount to each networking device, for example, a is allocated with 100MHZ task, B is allocated with 50MHZ task, C is allocated with 500MHZ task, and the calculation amount of the tasks is random.
Further, the scheduling server 200 is further configured to send the task download address and the calculation result return address corresponding to the divided work tasks to the corresponding networking device, so that the networking device downloads the corresponding work task at the task download address, and feeds back the calculated result according to the calculation result return address.
The method comprises the steps that idle computing resource information corresponding to the networking equipment is obtained through preset software in the networking equipment, and state information of the networking equipment is sent to a scheduling server through a heartbeat protocol; then, according to the received state information of the networking equipment and a preset algorithm logic, calculating available idle calculation resources corresponding to the networking equipment; and finally, dividing the work tasks to be calculated according to available idle computing resources of the networking equipment and a preset task scheduling algorithm, distributing the divided work tasks to the corresponding networking equipment, reforming the networking equipment into corresponding edge computing nodes, and assisting the scheduling server to perform computing processing on the work tasks. Therefore, the networked equipment is reformed into the edge computing node of the scheduling server, so that idle computing resources of the networked equipment can be effectively utilized, and the problem of insufficient computing capability of the scheduling server under large-scale complex tasks is solved.
The above-mentioned serial numbers of the embodiments of the present invention are only for description, and do not represent the advantages and disadvantages of the embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A method for reconstructing an edge computing node of a networked device, the method comprising:
through the software that predetermines in the networking device, acquire the idle computational resource information that the networking device corresponds to send the state information of networking device to dispatch server through the heartbeat protocol, the state information of networking device includes: the ID information and the idle computing resource information of the networking equipment are communicated with the scheduling server through the Internet;
according to the idle computing resource information in the received state information of the networking equipment and preset algorithm logic, acquiring the available proportion of idle computing resources corresponding to the idle computing resources of the networking equipment, multiplying the acquired available proportion of the idle computing resources by the idle computing resources of the networking equipment, and calculating to obtain the available idle computing resources corresponding to the networking equipment;
dividing the work tasks to be calculated according to available idle computing resources of the networking equipment and a preset task scheduling algorithm, sending task downloading addresses and computing result return addresses corresponding to the divided work tasks to the corresponding networking equipment, modifying the networking equipment into corresponding edge computing nodes, downloading the corresponding work tasks from the task downloading addresses for computing, and feeding back the computed results according to the computing result return addresses.
2. The method according to claim 1, wherein the obtaining of the idle computing resource information corresponding to the networking device through a preset software in the networking device comprises:
acquiring available proportion information of a processor and main frequency information of the processor corresponding to the networking equipment through software preset in the networking equipment;
and multiplying the available proportion of the processor of the obtained networking equipment by the main frequency of the processor to obtain the idle computing resource information corresponding to the networking equipment.
3. The method of claim 2, wherein the predetermined algorithmic logic comprises: a correspondence between an idle computing resource of a network device and its corresponding idle computing resource availability proportion.
4. The method of claim 1, wherein the pre-defined task scheduling algorithm comprises: any one of an equal calculation time splitting method, an equal calculation amount splitting method and a random splitting method;
the dividing of the work tasks to be calculated according to the available idle computing resources of the networking equipment and a preset task scheduling algorithm comprises the following steps:
dividing the work tasks to be calculated according to the mode that a plurality of networking devices to be distributed with the work tasks can finish calculation at the same time, or,
dividing the work task to be calculated according to a splitting mode with equal calculated amount, or,
and dividing the work tasks to be calculated according to a random splitting mode.
5. A networked device edge compute node reformation system, characterized by comprising:
the networking equipment is used for acquiring idle computing resource information corresponding to the networking equipment through preset software, and sending the state information of the networking equipment to the scheduling server through a heartbeat protocol, wherein the state information of the networking equipment comprises: the ID information and the idle computing resource information of the networking equipment are communicated with the scheduling server through the Internet;
the scheduling server is used for acquiring the available proportion of idle computing resources corresponding to the idle computing resources of the networking equipment according to the idle computing resource information in the received state information of the networking equipment and preset algorithm logic, multiplying the acquired available proportion of the idle computing resources by the idle computing resources of the networking equipment, and calculating to obtain the available idle computing resources corresponding to the networking equipment;
the scheduling server is further configured to divide the work tasks to be calculated according to the available idle computing resources of the networking devices and a preset task scheduling algorithm, send the task download addresses and the calculation result return addresses corresponding to the divided work tasks to the corresponding networking devices, modify the networking devices into corresponding edge computing nodes, download the corresponding work tasks from the task download addresses for calculation processing, and feed back the calculated results according to the calculation result return addresses.
6. The system of claim 5, wherein the networking device is further configured to obtain, through preset software, processor available ratio information and processor dominant frequency information corresponding to the networking device;
and the networking equipment is also used for obtaining the idle computing resource information corresponding to the networking equipment by multiplying the available proportion of the processor of the networking equipment by the main frequency of the processor.
7. The system of claim 6, wherein the predetermined algorithmic logic comprises: a correspondence between free computing resources of a network device and their corresponding free computing resource availability ratios.
8. The system of claim 5, wherein the pre-defined task scheduling algorithm comprises: any one of an equal calculation time splitting method, an equal calculation amount splitting method and a random splitting method;
the scheduling server is further configured to divide the work tasks to be calculated according to a manner that a plurality of networking devices to be assigned work tasks can be calculated at the same time, or,
dividing the work task to be calculated according to a splitting mode with equal calculated amount, or,
and dividing the work tasks to be calculated according to a random splitting mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811266003.4A CN111106946B (en) | 2018-10-29 | 2018-10-29 | Method and system for reconstructing edge computing node of networking equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811266003.4A CN111106946B (en) | 2018-10-29 | 2018-10-29 | Method and system for reconstructing edge computing node of networking equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111106946A CN111106946A (en) | 2020-05-05 |
| CN111106946B true CN111106946B (en) | 2022-12-30 |
Family
ID=70419583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811266003.4A Active CN111106946B (en) | 2018-10-29 | 2018-10-29 | Method and system for reconstructing edge computing node of networking equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111106946B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114064261A (en) * | 2020-08-07 | 2022-02-18 | 中国科学院沈阳自动化研究所 | Multi-dimensional heterogeneous resource quantification method and device based on industrial edge computing system |
| CN113590331A (en) * | 2021-08-05 | 2021-11-02 | 山东派盟网络科技有限公司 | Task processing method, control device and storage medium |
| CN114118444B (en) * | 2021-12-01 | 2024-04-12 | 杭州电子科技大学 | Method for reducing equipment idle running time in federal learning by using heuristic algorithm |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001014961A2 (en) * | 1999-08-26 | 2001-03-01 | Parabon Computation | System and method for the establishment and utilization of networked idle computational processing power |
| CN101931636A (en) * | 2009-06-25 | 2010-12-29 | 李冰 | Method for establishing Internet client running in peer-to-peer mode |
| CN103336719A (en) * | 2013-06-04 | 2013-10-02 | 江苏科技大学 | Distribution rendering system and method in P2P mode |
| 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 |
| CN104598425A (en) * | 2013-10-31 | 2015-05-06 | 中国石油天然气集团公司 | General multiprocessor parallel calculation method and system |
-
2018
- 2018-10-29 CN CN201811266003.4A patent/CN111106946B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001014961A2 (en) * | 1999-08-26 | 2001-03-01 | Parabon Computation | System and method for the establishment and utilization of networked idle computational processing power |
| CN101931636A (en) * | 2009-06-25 | 2010-12-29 | 李冰 | Method for establishing Internet client running in peer-to-peer mode |
| CN103336719A (en) * | 2013-06-04 | 2013-10-02 | 江苏科技大学 | Distribution rendering system and method in P2P mode |
| CN104598425A (en) * | 2013-10-31 | 2015-05-06 | 中国石油天然气集团公司 | General multiprocessor parallel calculation method and system |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111106946A (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111106946B (en) | Method and system for reconstructing edge computing node of networking equipment | |
| CN107688492B (en) | Resource control method and device and cluster resource management system | |
| CN106921754B (en) | Load balancing method, device, medium and electronic equipment of cluster system | |
| CN109117252B (en) | Method and system for task processing based on container and container cluster management system | |
| CN106656525B (en) | Data broadcasting system, data broadcasting method and equipment | |
| CN111158852A (en) | Training resource dynamic allocation method, system, terminal and storage medium | |
| WO2021159831A1 (en) | Programming platform user code running method, platform, node, device and medium | |
| CN114281521B (en) | Method, system, equipment and medium for optimizing deep learning heterogeneous resource communication efficiency | |
| CN112286688B (en) | Memory management and use method, device, equipment and medium | |
| CN112988344A (en) | Distributed batch task scheduling method, device, equipment and storage medium | |
| CN108028806A (en) | The method and apparatus that virtual resource is distributed in network function virtualization NFV networks | |
| CN116702885B (en) | Synchronous data parallel training control method, system, device, equipment and medium | |
| CN109426554B (en) | Timing implementation method and device for server | |
| CN107391221B (en) | Scheduling server, compiling server and distributed compiling method | |
| CN116048825A (en) | Container cluster construction method and system | |
| US11038957B2 (en) | Apparatus and method for efficient, coordinated, distributed execution | |
| CN110175078B (en) | Service processing method and device | |
| CN111835809A (en) | Work order message distribution method, work order message distribution device, server and storage medium | |
| WO2022111466A1 (en) | Task scheduling method, control method, electronic device and computer-readable medium | |
| CN115361382A (en) | Data processing method, device, equipment and storage medium based on data group | |
| CN109120704B (en) | Resource monitoring method, device and equipment of cloud platform | |
| CN114070855A (en) | Resource allocation method, resource allocation device, resource allocation system, and storage medium | |
| CN116112306B (en) | Decentralizing network interaction method, device, equipment and storage medium | |
| Chen et al. | Scheduling of job combination and dispatching strategy for grid and cloud system | |
| CN111061562B (en) | Software collaborative packaging method, system, terminal and storage medium |
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 | ||
| CB02 | Change of applicant information |
Address after: Room 201, Building A, No. 1 Qianwan Road, Qianhai Shenzhen-Hong Kong Cooperation Zone, Nanshan District, Shenzhen City, Guangdong Province Applicant after: Kingsoft Cloud (Shenzhen) Edge Computing Technology Co.,Ltd. Address before: Room 201, Building A, No. 1 Qianwan Road, Qianhai Shenzhen-Hong Kong Cooperation Zone, Nanshan District, Shenzhen City, Guangdong Province Applicant before: SHENZHEN YUNFAN ACCELERATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |