CN113722096A - CPU frequency adjusting method, system, equipment and storage medium of edge computing node - Google Patents

CPU frequency adjusting method, system, equipment and storage medium of edge computing node Download PDF

Info

Publication number
CN113722096A
CN113722096A CN202110983338.3A CN202110983338A CN113722096A CN 113722096 A CN113722096 A CN 113722096A CN 202110983338 A CN202110983338 A CN 202110983338A CN 113722096 A CN113722096 A CN 113722096A
Authority
CN
China
Prior art keywords
cpu
frequency
working frequency
computing node
edge computing
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110983338.3A
Other languages
Chinese (zh)
Other versions
CN113722096B (en
Inventor
申连腾
李哲
黄天航
钱声攀
李凌
翟天一
底晓梦
张鑫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
Original Assignee
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, China Electric Power Research Institute Co Ltd CEPRI filed Critical State Grid Corp of China SGCC
Priority to CN202110983338.3A priority Critical patent/CN113722096B/en
Publication of CN113722096A publication Critical patent/CN113722096A/en
Application granted granted Critical
Publication of CN113722096B publication Critical patent/CN113722096B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F9/505—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 considering the load
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3206—Monitoring of events, devices or parameters that trigger a change in power modality
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234—Power saving characterised by the action undertaken
    • G06F1/324—Power saving characterised by the action undertaken by lowering clock frequency
    • 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]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5072—Grid computing
    • 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
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The invention provides a method, a system, equipment and a storage medium for adjusting CPU frequency of an edge computing node, wherein the method comprises the following steps: acquiring all influence factors for controlling the working frequency of the CPU, wherein the influence factors are determined by different service scenes; the invention can accurately adjust the CPU frequency according to the load condition, optimizes the CPU frequency adjusting mechanism of the edge computing node aiming at the characteristics of the edge computing scene, and realizes the purpose that the edge node can better complete the computing task and reduce the power consumption.

Description

CPU frequency adjusting method, system, equipment and storage medium of edge computing node
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, a system, a device, and a storage medium for adjusting a CPU frequency of an edge compute node.
Background
In the traditional power calculation, data collected by each power terminal is transmitted to a master station for unified centralized processing. In the ubiquitous power internet of things, various growing power terminal devices and service applications can generate massive data, the transmission and processing of the data can cause huge pressure on a master station, and the requirements of new service forms cannot be met due to high time delay and safety.
The edge calculation provides service nearby the user side, so that the analysis and processing of real-time data and the service requirement of low time delay are met, meanwhile, the data safety can be ensured, and the risk avoidance of a power grid is facilitated. Based on the advantages of edge computing, the method has a rich application scene in power. The method has rich application scenes in comprehensive energy management, real-time monitoring of power transmission lines, active low-voltage fault study and judgment and multi-station fusion.
However, edge computing has different technical features from cloud computing, and on one hand, a site where edge computing nodes are deployed generally cannot provide a stable power supply like a data center. The specification and redundancy of the power supply circuit are difficult to guarantee. Edge computing nodes cannot consume as much power as computing nodes within a cloud computing data center. On the other hand, the edge computing node is generally used for processing applications with high requirements for burstiness, real-time performance and time delay, so that the processing capability of the edge computing node needs to be well guaranteed. In general, the power consumption of the edge computing node needs to be reduced on the premise of effectively ensuring timely processing of a large number of burst tasks.
The CPU is a main power consumption unit in the server and is also the most important computing unit, and the CPU is focused on the analysis of the power consumption and performance of the edge computing node. The CPU performs various tasks by executing a series of machine instructions, the speed at which the instructions are executed being determined by the CPU frequency. The inventor analyzes the working mechanism of the CPU and designs a method which can increase the CPU frequency in time to complete the calculation task when the task load is large and reduce the CPU frequency and the power consumption of the edge calculation node when no task exists.
The edge computing node provides service nearby the user side, a large amount of computation is downloaded to the edge end to be completed, the pressure of the data center is reduced, the analysis and processing of real-time data and the service requirement of low time delay are met, the operation and maintenance cost is reduced, and the system efficiency is improved. However, the power supply of the edge computing node cannot be as stable and durable as that of the data center, so a better strategy is needed for adjusting the working frequency of the CPU of the edge computing node, and the purpose of reducing the power consumption of the edge computing node while meeting the computing requirement is achieved.
Disclosure of Invention
Aiming at the defects in the prior art, the invention designs a CPU frequency adjusting method, a system, equipment and a storage medium of an edge computing node, the invention can accurately adjust the CPU frequency according to the load condition, optimizes the CPU frequency adjusting mechanism of the edge computing node according to the characteristics of an edge computing scene, and achieves the purposes of better completing computing tasks by the edge node and reducing power consumption.
In order to achieve the purpose, the invention adopts the following technical scheme:
a CPU frequency adjusting method of an edge computing node comprises the following steps:
acquiring all influence factors for controlling the working frequency of the CPU, wherein the influence factors are determined by different service scenes;
and setting the adaptation range of the influence factor for each influence factor according to the characteristics of the service scene, and dynamically setting the CPU working frequency according to the adaptation range.
As a further improvement of the present invention, the impact factor includes one or more of network traffic, CPU utilization, disk IO traffic, CPU load, hardware information, or service information.
As a further improvement of the present invention, the determining of the impact factor by different service scenarios specifically includes:
for network intensive tasks, taking network flow as an influence factor for CPU frequency adjustment;
for the disk IO intensive task, taking the disk IO flow as an influence factor for CPU frequency adjustment;
for other edge calculation scenarios, the hardware information or the service information is used as an influence factor for determining the CPU frequency.
As a further improvement of the present invention, the dynamically setting the CPU operating frequency according to the adaptation range specifically includes:
for a network intensive task scene, combining the reference CPU utilization rate data and the network traffic data with corresponding CPU working frequency, and obtaining the current working frequency of the edge computing node according to the ratio of the real-time CPU utilization rate data, the network traffic data and the reference;
and for the disk IO intensive task scene, setting the adaptation range of the disk IO flow and the CPU utilization rate for each CPU working frequency, and dynamically setting the current working frequency of the edge computing node according to the adaptation range.
As a further improvement of the present invention, the obtaining of all the influence factors for controlling the CPU operating frequency is obtained by an IoT device using its own sensor acquisition; and the acquired influence factors send information to the edge computing node through the network.
As a further improvement of the invention, the set CPU working frequency is sent to the cloud computing node.
A CPU frequency adjustment system for an edge compute node, comprising:
the acquisition module is used for acquiring all influence factors for controlling the working frequency of the CPU, and the influence factors are determined by different service scenes;
and the control module is used for setting the adaptation range of the influence factors for each kind of influence factors according to the characteristics of the service scene and dynamically setting the CPU working frequency according to the adaptation range.
As a further improvement of the present invention, in the control module,
the determination of the impact factor by different service scenarios specifically includes:
for network intensive tasks, taking network flow as an influence factor for CPU frequency adjustment;
for the disk IO intensive task, taking the disk IO flow as an influence factor for CPU frequency adjustment;
for other edge calculation scenarios, the hardware information or the service information is used as an influence factor for determining the CPU frequency.
The dynamic setting of the CPU operating frequency according to the adaptation range is specifically:
for a network intensive task scene, combining the reference CPU utilization rate data and the network traffic data with corresponding CPU working frequency, and obtaining the current working frequency of the edge computing node according to the ratio of the real-time CPU utilization rate data, the network traffic data and the reference;
and for the disk IO intensive task scene, setting the adaptation range of the disk IO flow and the CPU utilization rate for each CPU working frequency, and dynamically setting the current working frequency of the edge computing node according to the adaptation range.
An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method of CPU frequency adjustment of the edge compute node when executing the computer program.
A computer-readable storage medium, storing a computer program which, when executed by a processor, implements the steps of the CPU frequency adjustment method of the edge compute node.
Compared with the prior art, the invention has the beneficial effects that:
the invention can more accurately control the CPU frequency of the edge computing node by acquiring all the relevant information for controlling the CPU working frequency. The method achieves the purposes of increasing the CPU frequency in time to meet the requirement of a calculation task when a sudden task occurs, automatically reducing the CPU frequency when no task occurs, and saving the power consumption of edge nodes. The invention can accurately adjust the CPU frequency according to the load condition, optimizes the CPU frequency adjusting mechanism of the edge computing node aiming at the characteristics of the edge computing scene, and achieves the purposes that the edge node can better complete the computing task and reduce the power consumption.
Drawings
FIG. 1 is a schematic flow chart of a CPU frequency adjustment method for edge compute nodes according to the present invention;
FIG. 2 is a block diagram of the edge calculation of the present invention;
FIG. 3 is a schematic diagram of an overall frame of the edge computing node CPU frequency modulation of the present invention;
FIG. 4 is a schematic diagram of a CPU frequency adjustment system of an edge computing node according to the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to the present invention.
Detailed Description
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The following detailed description is exemplary in nature and is intended to provide further details of the invention. Unless otherwise defined, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention.
The CPU is a key component for completing calculation tasks by the edge calculation node, and the working frequency of the CPU is a key index for determining the running speed and the power consumption of the CPU. The CPU frequency is increased, so that the CPU can complete the calculation task more quickly, more energy consumption is consumed, and the aim of saving the power consumption can be achieved. The adjustment of the current CPU frequency is realized by operating system software, and for a Linux system, the software only controls the CPU working frequency by monitoring the CPU utilization rate. When finding that the CPU utilization rate is increased, the system sets a higher working frequency for the CPU according to a set rule, and when the CPU utilization rate is reduced, sets a lower working frequency. This approach is applicable for most cases, but there are limitations for edge compute nodes that handle bursty large concurrent tasks. The method mainly shows that for a service scene with large burst flow, the method for adjusting the working frequency of the CPU by the utilization rate of the CPU can cause the frequency modulation action to lag behind the service. The reasons for hysteresis mainly include two types of delays: the delay of the service arrival time and the CPU utilization rate promotion time and the delay existing in the actual frequency modulation action. For the above reasons, for the scene of the burst large service, in order to ensure the service performance, a method of closing the CPU dynamic frequency modulation is generally adopted, that is, the CPU frequency is fixedly maintained at a higher value, so as to meet the requirement of processing the burst service. This practice necessarily causes an increase in power consumption of the edge computing nodes.
In order to achieve the purpose of reducing the average power consumption of the edge computing node and simultaneously processing the burst task in time, as shown in fig. 1, a first object of the present invention is to provide a method for adjusting the CPU frequency of the edge computing node, which includes the following steps:
acquiring all influence factors for controlling the working frequency of the CPU, wherein the influence factors are determined by different service scenes;
and setting the adaptation range of the influence factor for each influence factor according to the characteristics of the service scene, and dynamically setting the CPU working frequency according to the adaptation range.
The influence factors include one or more of network flow, CPU utilization rate, disk IO flow, CPU load, hardware information or service information.
On the basis of the CPU utilization rate, more related parameters are added to jointly determine the working frequency of the CPU.
The principle of influence factor selection is as follows:
for network intensive tasks, taking network flow as an influence factor for CPU frequency adjustment;
for the disk IO intensive task, taking the disk IO flow as an influence factor for CPU frequency adjustment;
for other edge calculation scenarios, the hardware information or the service information is used as an influence factor for determining the CPU frequency.
As a preferred embodiment, the dynamically setting the CPU operating frequency according to the adaptation range specifically includes:
for a network intensive task scene, combining the reference CPU utilization rate data and the network traffic data with corresponding CPU working frequency, and obtaining the current working frequency of the edge computing node according to the ratio of the real-time CPU utilization rate data, the network traffic data and the reference;
and for the disk IO intensive task scene, setting the adaptation range of the disk IO flow and the CPU utilization rate for each CPU working frequency, and dynamically setting the current working frequency of the edge computing node according to the adaptation range. Acquiring all influence factors for controlling the working frequency of the CPU, wherein the influence factors are acquired by an IoT device by utilizing a sensor of the IoT device; and the acquired influence factors send information to the edge computing node through the network.
And the set CPU working frequency is sent to the cloud computing node by the edge computing node.
As shown in fig. 2, the present invention further provides a CPU frequency adjustment system for an edge computing node, including:
the acquisition module is used for acquiring all influence factors for controlling the working frequency of the CPU, and the influence factors are determined by different service scenes;
and the control module is used for setting the adaptation range of the influence factors for each kind of influence factors according to the characteristics of the service scene and dynamically setting the CPU working frequency according to the adaptation range.
In the control module, the control module is used for controlling the operation of the motor,
the determination of the impact factor by different service scenarios specifically includes:
for network intensive tasks, taking network flow as an influence factor for CPU frequency adjustment;
for the disk IO intensive task, taking the disk IO flow as an influence factor for CPU frequency adjustment;
for other edge calculation scenarios, the hardware information or the service information is used as an influence factor for determining the CPU frequency.
The dynamic setting of the CPU operating frequency according to the adaptation range is specifically:
for a network intensive task scene, combining the reference CPU utilization rate data and the network traffic data with corresponding CPU working frequency, and obtaining the current working frequency of the edge computing node according to the ratio of the real-time CPU utilization rate data, the network traffic data and the reference;
and for the disk IO intensive task scene, setting the adaptation range of the disk IO flow and the CPU utilization rate for each CPU working frequency, and dynamically setting the current working frequency of the edge computing node according to the adaptation range.
Specifically, the collection module of the present invention is used for collecting information that can embody system load. In addition to the CPU utilization data that is currently in use, some information that is strongly related to the business features may also be collected.
For example:
for edge compute nodes running network intensive tasks, the network traffic of the nodes needs to be brought into the collection. For the edge computing node running the disk IO intensive task, the read-write flow of the disk needs to be brought into collection. Other data such as CPU load, memory utilization, etc. may be included as needed.
For network-intensive tasks, the network flow is used as an influence factor for CPU frequency adjustment, and two advantages are achieved. First, the CPU frequency can be adjusted in time. When the intensive network processing task arrives, the network flow is firstly promoted, then the CPU processes the data, and the CPU utilization rate is promoted. By incorporating network traffic into the impact factor, the frequency of the CPU can be controlled earlier. Secondly, the requirement on the CPU frequency can be evaluated more accurately, even if the network task with light calculation task amount is large, the CPU utilization rate cannot be greatly improved, and the network task can obtain better processing speed by improving the CPU frequency based on the network flow data under the condition.
For disk IO intensive tasks, similar benefits can be obtained by using IO traffic as an impact factor for CPU frequency adjustment.
For other specific edge calculation scenarios, other relevant hardware information or service information may be collected as a factor in determining the CPU frequency.
The control module is used for comprehensively determining the working frequency of the CPU, and the control module sets the adaptation range of the influence factor for each CPU working frequency according to different scenes. And the control module dynamically sets the CPU working frequency according to the adaptation scheme. For example:
and for the network intensive task scene, setting the adaptation range of the network flow and the CPU utilization rate for each CPU working frequency.
And for the disk IO intensive task scene, setting the adaptation range of the disk IO flow and the CPU utilization rate for each CPU working frequency.
The invention more accurately controls the CPU frequency of the edge computing node. The method achieves the purposes of increasing the CPU frequency in time to meet the requirement of a calculation task when a sudden task occurs, automatically reducing the CPU frequency when no task occurs, and saving the power consumption of edge nodes.
In order to make the objects, technical solutions and effects of the present invention clearer and clearer, the present invention is further described in detail by referring to the drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Examples
The invention aims to provide a method for adjusting the CPU working frequency of an edge computing node, so that the edge computing node can process burst tasks in time and reduce power consumption when no task exists.
Fig. 3 depicts the relationship of IoT devices, edge computing nodes, cloud computing nodes.
The IoT device utilizes its own sensors to gather useful information about the location. The information is sent to the edge compute node over the network. The edge computing node performs primary processing on the acquired information by utilizing the computing capability of the edge computing node. The collected information is firstly processed at the edge computing node, so that the data volume transmitted to the cloud computing node can be effectively reduced, the transmission cost is reduced, and the data security is guaranteed. Meanwhile, the response speed to the key information can be improved, and timely discovery and timely processing can be achieved. The cloud computing nodes are located in the cloud computing data center and far away from the edge computing nodes, and delay and cost of network transmission are high. The original information is processed by the edge computing node, and then only the processing result is sent to the cloud computing node, so that the transmission cost can be effectively reduced.
Fig. 4 is an overall framework of the present invention, and an IoT device sends collected information to an edge computing node through a network for processing. The acquisition module in the edge computing node acquires the state information of the edge computing node in real time, and the specific information may include network flow, CPU utilization rate, disk IO flow, CPU load and the like. For network intensive tasks, changes in network traffic can significantly impact the load on edge compute nodes. When the network flow is increased, the problem of task processing delay is caused by untimely increasing of the CPU working frequency. For such a scenario, the influence of the disk IO flow and the CPU load data on the evaluation of the load of the computing node is small, and the evaluation does not need to be considered.
The control module combines the CPU utilization rate data serving as the reference with the network flow data to comprehensively determine the current working frequency of the edge computing node.
Specifically, for a network intensive task scene, reference CPU utilization rate data and network traffic data are combined to correspond to CPU working frequency, and the current working frequency of an edge computing node is obtained according to the ratio of real-time CPU utilization rate data, network traffic data and the reference; for example, for a CPU working frequency of 2.5Ghz, the applicable range of the network traffic is set to be 1Mbit/s-900Mbit/s, the range of the CPU utilization rate is 50-40%, for a CPU working frequency of 2.4Ghz, the applicable range of the network traffic is set to be 899Kbit/s-800Kbit/s, the range of the CPU utilization rate is 39-30%, for a CPU working frequency of 2.3Ghz, the applicable range of the network traffic is set to be 799Kbit/s-700Kbit/s, the range of the CPU utilization rate is 29-20%, and so on. And the control module sets the working frequency of the CPU according to the current data of all the influence factors according to the data acquired by the acquisition module in real time.
A third object of the present invention is to provide an electronic device, as shown in fig. 5, including a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the CPU frequency adjustment method of the edge computing node when executing the computer program.
The CPU frequency adjusting method of the edge computing node comprises the following steps:
acquiring all influence factors for controlling the working frequency of the CPU, wherein the influence factors are determined by different service scenes;
and setting the adaptation range of the influence factor for each influence factor according to the characteristics of the service scene, and dynamically setting the CPU working frequency according to the adaptation range.
A fourth object of the present invention is to provide a computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the steps of the CPU frequency adjustment method of the edge computing node.
The CPU frequency adjusting method of the edge computing node comprises the following steps:
acquiring all influence factors for controlling the working frequency of the CPU, wherein the influence factors are determined by different service scenes;
and setting the adaptation range of the influence factor for each influence factor according to the characteristics of the service scene, and dynamically setting the CPU working frequency according to the adaptation range.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.

Claims (10)

1. A CPU frequency adjusting method of an edge computing node is characterized by comprising the following steps:
acquiring all influence factors for controlling the working frequency of the CPU, wherein the influence factors are determined by different service scenes;
and setting the adaptation range of the influence factor for each influence factor according to the characteristics of the service scene, and dynamically setting the CPU working frequency according to the adaptation range.
2. The method of claim 1,
the influence factors comprise one or more items of network flow, CPU utilization rate, disk IO flow, CPU load, hardware information or service information.
3. The method of claim 1,
the determination of the impact factor by different service scenarios specifically includes:
for network intensive tasks, taking network flow as an influence factor for CPU frequency adjustment;
for the disk IO intensive task, taking the disk IO flow as an influence factor for CPU frequency adjustment;
for other edge calculation scenarios, the hardware information or the service information is used as an influence factor for determining the CPU frequency.
4. The method of claim 1,
the dynamic setting of the CPU operating frequency according to the adaptation range is specifically:
for a network intensive task scene, combining the reference CPU utilization rate data and the network traffic data with corresponding CPU working frequency, and obtaining the current working frequency of the edge computing node according to the ratio of the real-time CPU utilization rate data, the network traffic data and the reference;
and for the disk IO intensive task scene, setting the adaptation range of the disk IO flow and the CPU utilization rate for each CPU working frequency, and dynamically setting the current working frequency of the edge computing node according to the adaptation range.
5. The method of claim 1,
acquiring all influence factors for controlling the working frequency of the CPU, wherein the influence factors are acquired by an IoT device by utilizing a sensor of the IoT device; and the acquired influence factors send information to the edge computing node through the network.
6. The method of claim 1,
and the set CPU working frequency is sent to the cloud computing node.
7. A CPU frequency adjustment system for an edge compute node, comprising:
the acquisition module is used for acquiring all influence factors for controlling the working frequency of the CPU, and the influence factors are determined by different service scenes;
and the control module is used for setting the adaptation range of the influence factors for each kind of influence factors according to the characteristics of the service scene and dynamically setting the CPU working frequency according to the adaptation range.
8. The system of claim 7,
in the control module, the control module is used for controlling the operation of the motor,
the determination of the impact factor by different service scenarios specifically includes:
for network intensive tasks, taking network flow as an influence factor for CPU frequency adjustment;
for the disk IO intensive task, taking the disk IO flow as an influence factor for CPU frequency adjustment;
for other edge calculation scenarios, the hardware information or the service information is used as an influence factor for determining the CPU frequency.
The dynamic setting of the CPU operating frequency according to the adaptation range is specifically:
for a network intensive task scene, combining the reference CPU utilization rate data and the network traffic data with corresponding CPU working frequency, and obtaining the current working frequency of the edge computing node according to the ratio of the real-time CPU utilization rate data, the network traffic data and the reference;
and for the disk IO intensive task scene, setting the adaptation range of the disk IO flow and the CPU utilization rate for each CPU working frequency, and dynamically setting the current working frequency of the edge computing node according to the adaptation range.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method of CPU frequency scaling of an edge compute node according to any one of claims 1 to 6 when executing the computer program.
10. A computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the CPU frequency adjustment method of an edge computing node according to any one of claims 1 to 6.
CN202110983338.3A 2021-08-25 2021-08-25 CPU frequency adjusting method, system, equipment and storage medium of edge computing node Active CN113722096B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110983338.3A CN113722096B (en) 2021-08-25 2021-08-25 CPU frequency adjusting method, system, equipment and storage medium of edge computing node

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110983338.3A CN113722096B (en) 2021-08-25 2021-08-25 CPU frequency adjusting method, system, equipment and storage medium of edge computing node

Publications (2)

Publication Number Publication Date
CN113722096A true CN113722096A (en) 2021-11-30
CN113722096B CN113722096B (en) 2023-09-12

Family

ID=78678025

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110983338.3A Active CN113722096B (en) 2021-08-25 2021-08-25 CPU frequency adjusting method, system, equipment and storage medium of edge computing node

Country Status (1)

Country Link
CN (1) CN113722096B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2166450A1 (en) * 2008-09-23 2010-03-24 Robert Bosch Gmbh A method to dynamically change the frequency of execution of functions within tasks in an ECU
CN103246340A (en) * 2012-02-06 2013-08-14 索尼公司 Device and method for dynamically adjusting frequency of central processing unit
CN104423529A (en) * 2013-08-30 2015-03-18 华为技术有限公司 CPU (central processing unit) state adjustment method and device
CN105049365A (en) * 2015-06-15 2015-11-11 国家计算机网络与信息安全管理中心 Adaptive frequency modulation energy-saving method for multi-core multi-thread intrusion detection device
CN107197323A (en) * 2017-05-08 2017-09-22 上海工程技术大学 A kind of network video-on-demand server and its application based on DVFS
CN111240835A (en) * 2020-01-06 2020-06-05 北京小米移动软件有限公司 CPU working frequency adjusting method, CPU working frequency adjusting device and storage medium
CN112162826A (en) * 2020-10-13 2021-01-01 杭州电子科技大学 Low-power-consumption lightweight virtualization method for edge computing

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2166450A1 (en) * 2008-09-23 2010-03-24 Robert Bosch Gmbh A method to dynamically change the frequency of execution of functions within tasks in an ECU
CN103246340A (en) * 2012-02-06 2013-08-14 索尼公司 Device and method for dynamically adjusting frequency of central processing unit
CN104423529A (en) * 2013-08-30 2015-03-18 华为技术有限公司 CPU (central processing unit) state adjustment method and device
CN105049365A (en) * 2015-06-15 2015-11-11 国家计算机网络与信息安全管理中心 Adaptive frequency modulation energy-saving method for multi-core multi-thread intrusion detection device
CN107197323A (en) * 2017-05-08 2017-09-22 上海工程技术大学 A kind of network video-on-demand server and its application based on DVFS
CN111240835A (en) * 2020-01-06 2020-06-05 北京小米移动软件有限公司 CPU working frequency adjusting method, CPU working frequency adjusting device and storage medium
CN112162826A (en) * 2020-10-13 2021-01-01 杭州电子科技大学 Low-power-consumption lightweight virtualization method for edge computing

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
ZIHAO LIU: "Optimized Task Offloading Policy in Given Sequence in Mobile Edge Computing", pages 1656 - 1660 *
王伏亮;李澄;李春鹏;陆玉军;陈颢;: "基于边缘计算的中低压配电网多类型传感器接入技术", no. 07, pages 17 - 21 *

Also Published As

Publication number Publication date
CN113722096B (en) 2023-09-12

Similar Documents

Publication Publication Date Title
CN107871164B (en) Fog computing environment personalized deep learning method
CN109714431A (en) A kind of edge calculations method and apparatus of Internet of Things intelligence sensor
CN103294521B (en) A kind of method reducing data center's traffic load and energy consumption
CN114340016B (en) Power grid edge calculation unloading distribution method and system
CN111199279A (en) Cloud edge calculation and artificial intelligence fusion method and device for police service industry
CN110688213B (en) Resource management method and system based on edge calculation and electronic equipment
CN105049485A (en) Real-time video processing oriented load-aware cloud calculation system
CN109547541B (en) Node low-overhead cooperation method based on filtering and distribution mechanism in fog computing environment
CN110213327A (en) A kind of resource regulating method based on edge calculations, apparatus and system
CN115689004A (en) Method and system for constructing multi-source virtual flexible aggregation and hierarchical cooperative control platform
CN112216061A (en) Rainwater condition monitoring and early warning method and system
CN116346819A (en) Industrial Internet system based on cloud edge cooperation
CN107092649A (en) A kind of topological replacement method of unaware towards real-time stream calculation
Cao et al. Research on intelligent traffic control model and simulation based on the internet of things and cloud platform
CN116028193B (en) Big data task dynamic high-energy-efficiency scheduling method and system for mixed part cluster
CN113722096A (en) CPU frequency adjusting method, system, equipment and storage medium of edge computing node
CN104796673A (en) Energy consumption optimization-oriented cloud video monitoring system task access method
CN103731484B (en) A kind of power save transmission method towards mobile cloud computing and middleware system
CN113238814A (en) MEC task unloading system and optimization method based on multiple users and classification tasks
CN105515844A (en) System for improving software defined network reliability
CN116225198A (en) CPU load control method and system
CN110647396A (en) Method for realizing intelligent application of end cloud cooperative low-power consumption and limited bandwidth
CN112214303A (en) Kubernetes cluster automatic scaling system
CN115269145A (en) High-energy-efficiency heterogeneous multi-core scheduling method and device for offshore unmanned equipment
CN112366693B (en) Power dispatching method and system for source network load storage multi-element coordination flexible control

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