Edge computing power optimization method and device based on Internet of Things, and electronic equipment

By allocating and adjusting the business tasks and partitioning processing of the edge processing server, the problem of low utilization of edge processing servers is solved, extending the service life of the server and improving efficiency.

CN118916160APending Publication Date: 2024-11-08CHINA MOBILE GRP GUANGDONG CO LTD +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410966747.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The utilization rate of edge processing servers is low, resulting in short service life, affecting the maintenance and efficiency of servers.

Method used

By obtaining the service queue of the edge processing server, assigning business tasks to multiple servers for partition processing, and adjusting partition division and task allocation according to the load coefficient and business queue prediction coefficient, ensuring that the load balancing and processing time of each server are close.

Benefits of technology

Improves the utilization rate of edge processing servers, extends the service life of the server, and avoids overuse and aging of servers.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118916160A_ABST
    Figure CN118916160A_ABST
Patent Text Reader

Abstract

The invention relates to an edge computing power optimization method and device based on the Internet of Things and electronic equipment. The method comprises the following steps: acquiring a service queue of a first edge processing server; processing a first part of business after the business queue by the first edge processing server; transmitting a second part after the service queue to a second edge processing server for processing; wherein the first part of services and the second part of services are selected from the services after the service queue according to a preset proportion. Therefore, the adjustment of the queue length of the edge processing server can be realized, so that each edge processing server can reach an approximate processing time length, and a certain edge processing server is prevented from being overused. By adopting the method provided by the embodiment of the invention, the utilization rate of the edge processing server can be improved, the aging speed of part of the edge processing server can be slowed down, the maintenance of the edge processing server is facilitated, and the service life of the edge processing server is prolonged.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technology, and in particular to an edge computing power optimization method, device and electronic device based on the Internet of Things. Background Art

[0002] In related technologies, edge computing is a distributed computing model that moves computing and data processing capabilities close to the source of data, which can provide faster, real-time and efficient computing capabilities and is suitable for application scenarios that require low latency, high reliability and data privacy. However, the amount of data uploaded by IoT devices connected to edge processing servers is not fixed, and the intensity of computing tasks of different edge processing servers is different. It is often the case that some edge processing servers work for a long time while others are idle. Over time, this will lead to low utilization of edge processing servers, accelerate the aging of some edge processing servers, and be unfavorable to the maintenance of edge processing servers, affecting the service life of edge processing servers. Summary of the invention

[0003] The present disclosure provides an edge computing power optimization method, device and electronic device based on the Internet of Things to at least solve the technical problems of low utilization and short service life of edge processing servers in related technologies. The technical solution of the present disclosure is as follows:

[0004] According to a first aspect of an embodiment of the present disclosure, a method for optimizing edge computing power based on the Internet of Things is provided, comprising:

[0005] Obtaining a service queue of a first edge processing server;

[0006] Processing the first part of the services after the service queue by the first edge processing server;

[0007] The second part after the service queue is transmitted to the second edge processing server for processing; wherein the first part of services and the second part of services are selected from the services after the service queue according to a preset ratio.

[0008] In a possible implementation manner, the processing, by the first edge processing server, the first portion of services after the service queue includes:

[0009] In the business processed by the first edge processing server, subtasks of the business are assigned to the first partition of the first edge processing server for batch processing;

[0010] The last batch of some subtasks in the batch-processed subtasks is selected and transmitted to the second partition processing of the third edge processing server; wherein the third edge processing server and the first edge processing server are the same edge processing server or two separate edge processing servers.

[0011] In a possible implementation, the method further includes:

[0012] Obtain operating temperature data for each edge processing server;

[0013] Determining a load factor of each edge processing server according to the operating temperature data of each edge processing server;

[0014] Determining whether to adjust the division of the first partition of the edge processing server according to the load factor of each edge processing server;

[0015] When it is determined that the division of the first partition of the edge processing server needs to be adjusted, some computing nodes are divided from the first partition of the edge processing server as a third partition.

[0016] In a possible implementation manner, judging whether to adjust the division of the first partition of the edge processing server according to the load factor of each edge processing server includes:

[0017] The load factor Load obtained by the i-th edge processing server i , with the first preset load factor and a second preset load factor Make comparisons;

[0018] like Then adjusting the division of the first partition of the i-th edge processing server;

[0019] like The division of the first partition of the i-th edge processing server is not adjusted;

[0020] like Then the number of computing nodes in the third partition of the i-th edge processing server is reset to zero.

[0021] In a possible implementation, the method further includes:

[0022] Obtain business data of each edge processing server;

[0023] Determining a service queue prediction coefficient of each edge processing server according to the service data of each edge processing server;

[0024] The service queue of the edge processing server is adjusted according to the service queue prediction coefficient.

[0025] In a possible implementation manner, adjusting the service queue of the current edge processing server according to the service queue prediction coefficient includes:

[0026] Get the queue prediction coefficient Bp of the i-th edge processing server corresponding to the m edge processing servers i ;

[0027] Calculate the queue prediction coefficient Bp corresponding to the m edge processing servers i The difference between the maximum and minimum values ​​in ;

[0028] If the difference is greater than or equal to the critical value, part of the services at the end of the current queue of the edge processing server corresponding to the maximum value are adjusted to the end of the current queue of the edge processing server corresponding to the minimum value according to the difference.

[0029] According to a second aspect of an embodiment of the present disclosure, there is provided an edge computing power optimization device based on the Internet of Things, comprising:

[0030] A service acquisition module, used to acquire a service queue of a first edge processing server;

[0031] A service adjustment module, configured to allow the first edge processing server to process a first portion of services after the service queue;

[0032] A computing power optimization module is used to transmit the second part after the business queue to the second edge processing server for processing; wherein the first part of the business and the second part of the business are selected from the business after the business queue according to a preset ratio.

[0033] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0034] processor;

[0035] a memory for storing instructions executable by the processor;

[0036] In which, the processor is configured to execute the instructions to implement the edge computing computing power optimization method based on the Internet of Things as described in any one of the first aspects.

[0037] According to a fourth aspect of an embodiment of the present disclosure, a storage medium is provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the edge computing computing power optimization method based on the Internet of Things as described in any one of the first aspects.

[0038] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the edge computing computing power optimization method based on the Internet of Things as described in any one of the first aspects.

[0039] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0040] In an embodiment of the present disclosure, the service queue of the first edge processing server is obtained; the first part of the services after the service queue is processed by the first edge processing server; the second part after the service queue is transmitted to the second edge processing server for processing; wherein the first part of the services and the second part of the services are selected from the services after the service queue according to a preset ratio. In this way, the queue length of the edge processing server can be adjusted so that each edge processing server can achieve a similar processing time, avoiding overuse of a certain edge processing server. In this way, the utilization rate of the edge processing server can be improved, the aging speed of some edge processing servers can be slowed down, which is beneficial to the maintenance of the edge processing server and increases the service life of the edge processing server.

[0041] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0043] Figure 1 It is a flow chart of an edge computing power optimization method based on the Internet of Things shown in an embodiment of the present disclosure.

[0044] Figure 2 It is a block diagram of an edge computing power optimization device based on the Internet of Things shown in an embodiment of the present disclosure.

[0045] Figure 3 It is a block diagram of an electronic device shown in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0047] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0048] The following is a detailed description of the edge computing computing power optimization method, device and electronic device based on the Internet of Things provided by the embodiments of the present disclosure in conjunction with the accompanying drawings.

[0049] Figure 1 1 is a flow chart of an edge computing power optimization method based on the Internet of Things shown in an embodiment of the present disclosure. The edge computing power optimization method based on the Internet of Things can be applied to a server, for example, a server cluster or a single server. Figure 1 As shown, the edge computing power optimization method based on the Internet of Things can include the following steps.

[0050] S101: Obtain a service queue of a first edge processing server.

[0051] In the embodiment of the present disclosure, the service queue of the first edge processing server may be obtained first. Exemplarily, the edge processing server may have multiple services, and the service queue may include multiple services. It is understandable that the first edge processing server may be any edge processing server in the edge computing system, and the edge computing system may include multiple edge processing servers, which may also be referred to as edge servers, edge processing devices, etc.

[0052] S102: The first edge processing server processes the first part of the services after the service queue.

[0053] In the embodiment of the present disclosure, after obtaining the service queue of the first edge processing server, a portion of the services behind the service queue (i.e., the first portion) can be handed over to the current first edge processing server for processing. It can be understood that a portion of the services (i.e., the first portion of services) can be selected from the back end of the service queue according to a preset ratio and handed over to the current edge processing server for processing. The preset ratio can be set according to actual needs.

[0054] S103: Transmit the second part after the service queue to the second edge processing server for processing.

[0055] In the disclosed embodiment, a portion of the services (i.e., the second portion of services) may be selected from the back end of the service queue according to a preset ratio and handed over to another edge processing server (i.e., the second edge processing server) for processing. The second portion of services may also be selected from the services behind the service queue according to a preset ratio, and the preset ratio may be set according to actual needs. In this way, when the edge processing server is processing multiple services, the queue length of each edge processing server may be adjusted so that each edge processing server can achieve a similar processing time, thereby avoiding overuse of a certain edge processing server.

[0056] In an embodiment of the present disclosure, the service queue of the first edge processing server is obtained; the first part of the services after the service queue is processed by the first edge processing server; the second part after the service queue is transmitted to the second edge processing server for processing; wherein the first part of the services and the second part of the services are selected from the services after the service queue according to a preset ratio. In this way, the queue length of the edge processing server can be adjusted so that each edge processing server can achieve a similar processing time, avoiding overuse of a certain edge processing server. In this way, the utilization rate of the edge processing server can be improved, the aging speed of some edge processing servers can be slowed down, which is beneficial to the maintenance of the edge processing server and increases the service life of the edge processing server.

[0057] In a possible implementation, processing the first portion of services after the service queue by the first edge processing server includes:

[0058] In the business processed by the first edge processing server, subtasks of the business are assigned to the first partition of the first edge processing server for batch processing;

[0059] The last batch of some subtasks is selected from the subtasks processed in batches, and transmitted to the second partition of the third edge processing server for processing; wherein the third edge processing server and the first edge processing server are the same edge processing server or two separate edge processing servers.

[0060] In an embodiment of the present disclosure, when the first part of the business after the business queue is processed by the first edge processing server, the subtasks of the business can be handed over to a partition (i.e., the first partition) of the first edge processing server for batch processing. The first partition can be a partition in the edge processing server for business processing, and each edge processing server can include at least two partitions, such as a first partition and a second partition. For subtasks processed in batches, the last batch of some subtasks can be selected from the subtasks processed in batches, and the last batch of these subtasks can be transmitted to the second partition of the third edge processing server for processing. Exemplarily, the selection method of some subtasks can be set according to actual needs. It can be understood that if the second partition used to process the last batch of subtasks belongs to the same edge processing server as the first partition, that is, the first edge processing server and the third edge processing server are the same, then they can be directly transmitted; if the second partition used to process another part of the subtasks does not belong to the same edge processing server as the first partition, that is, the first edge processing server and the third edge processing server are not the same, then they can be transmitted through a wireless transmission unit. In this way, the last batch of some subtasks selected from the subtasks processed in batches can be transmitted to the second partition of an edge processing server for processing. In this way, the utilization rate of each partition can be optimized, thereby improving processing efficiency and optimizing the utilization rate of computing power.

[0061] In a possible implementation, the edge computing computing power optimization method based on the Internet of Things provided by the embodiment of the present disclosure may also include:

[0062] Obtain operating temperature data for each edge processing server;

[0063] Determining a load factor of each edge processing server based on the operating temperature data of each edge processing server;

[0064] Determining whether to adjust the division of the first partition of the edge processing server according to the load factor of each edge processing server;

[0065] When it is determined that the division of the first partition of the edge processing server needs to be adjusted, some computing nodes are divided from the first partition of the edge processing server as a third partition.

[0066] In the embodiment of the present disclosure, the edge processing server can also be monitored to obtain the operating temperature data of each edge processing server, such as the actual measured temperature. The load factor of each edge processing server can also be calculated based on the operating temperature data of each edge processing server. The calculation formula of the load factor can be shown as formula (1).

[0067]

[0068] Among them, Load i represents the load factor of the ith edge processing server, where σ1 and σ2 represent the preset weight coefficients, is the measured temperature of the ith edge processing server, is the standard temperature set by the i-th edge processing server, It is the temperature change within the preset time period based on the current time. is the preset temperature change for the ith edge processing server, exp is a logarithmic function based on experience, is a piecewise function with values ​​of ±1. When the value is positive on the contrary Combined with formula (2), it can be seen that the load coefficient is obtained based on the current temperature and the current temperature change. When the current temperature change is in the same direction as the preset temperature change, the load coefficient is positively affected by both the current temperature and the current temperature change. That is, the larger the current temperature change is and the preset temperature change is, the larger the load coefficient is. Considering the current temperature change while considering the current temperature can take the temperature change trend into consideration and improve the accuracy of judgment. When the current temperature change is in a different direction from the preset temperature change, the preset temperature change is generally positive, which means that the current edge processing server is in a state of rapid cooling. Specifically, according to formula (2), the larger the preset temperature change is, the smaller the load coefficient is. In other words, the load coefficient can accurately reflect the different load states of the edge processing server.

[0069] Then, the load coefficient of each edge processing server can be used to determine whether to adjust the division of the first partition of the edge processing server. For example, it can be determined whether the first partition needs to be divided according to the size of the load coefficient, that is, a new partition, namely, the third partition, is further divided from the first partition. If it is determined that the division of the first partition of the edge processing server needs to be adjusted, some computing nodes can be divided from the first partition of the edge processing server as the third partition. It should be noted that in the process of dividing some computing nodes from the first partition as the third partition, a numerical selection can be made through a comparison table according to the value of the load coefficient of the edge processing server, so as to set the number of computing nodes in the third partition. The comparison table can be set according to the demand; the number of computing nodes in multiple second partitions is different, so that different second partitions can adapt to different batches and perform calculations more flexibly. In this way, after adjusting the division of the first partition according to the load coefficient, an idle third partition can be divided, and the load state of the current edge processing server can be reduced through the third partition, the load coefficient can be reduced, and the temperature of the edge processing server can be reduced, thereby improving the service life of the edge processing server.

[0070] In a further possible implementation manner, determining whether to adjust the division of the first partition of the edge processing server according to the load factor of each edge processing server includes:

[0071] The load factor Load obtained by the i-th edge processing server i , with the first preset load factor and a second preset load factor Make comparisons;

[0072] like Then adjust the division of the first partition of the i-th edge processing server;

[0073] like The division of the first partition of the i-th edge processing server is not adjusted;

[0074] like Then the number of computing nodes in the third partition of the i-th edge processing server is reset to zero.

[0075] In the embodiment of the present disclosure, when determining whether to adjust the division of the first partition of the edge processing server according to the load coefficient of each edge processing server, a preset load coefficient may be obtained, including a first preset load coefficient and a second preset load factor and The load factor Load obtained by the ith edge processing server can be set based on empirical data. i , with the first preset load factor and a second preset load factor For comparison. Then the division of the first partition of the th edge processing server can be adjusted; if If , the number of computing nodes in the third partition of the ith edge processing server can be reset to zero, which means returning the computing nodes divided from the first partition to the first partition. It can be understood that the above process can be performed on each edge processing server.

[0076] In a possible implementation, the edge computing computing power optimization method based on the Internet of Things provided by the embodiment of the present disclosure may also include:

[0077] Obtain business data of each edge processing server;

[0078] Determine a service queue prediction coefficient of each edge processing server according to service data of each edge processing server;

[0079] The service queue of the edge processing server is adjusted according to the service queue prediction coefficient.

[0080] In the embodiment of the present disclosure, the edge processing server can also be monitored to obtain the service data of each edge processing server. According to the service data of each edge processing server, the service queue prediction coefficient of each edge processing server is calculated. The queue prediction coefficient of the service queue can be calculated as follows: among the m edge processing servers, for the i-th edge processing server, n consecutive prediction cycles are obtained based on the current time point; the queue prediction coefficient can be calculated as shown in formula (2).

[0081]

[0082] Among them, Bp i represents the queue prediction coefficient of the ith edge processing server, where n is the number of prediction periods, t j is the jth period in the n prediction periods, F(t) is the distribution function set according to the arrival rate of the basic service flow and the arrival rate of the random service flow, F(t j ) is the predicted value obtained by the distribution function F(t) in the jth period, μ(t) is the preset reference table function, μ(t j ) is the batch quantity prediction value selected based on the jth cycle selected by the lookup table function, C j is the preset standard value. It is the preset computing power coefficient of the ith edge processing server, which is set based on the computing power of the ith edge processing server.

[0083] Then, the service queue of the edge processing server can be adjusted according to the service queue prediction coefficient, so that the queue prediction coefficient of each queue after adjustment is close. In this way, the completion time of each current service queue can be close, wherein the queue prediction coefficient is predicted based on a distribution function set based on multiple prediction cycles and the basic service flow arrival rate and the random service flow arrival rate, and it also takes into account the need to split the service, so that the queue prediction coefficient digitized by formula (2) represents the queue length waiting for processing of each edge processing server, realizing digital regulation and control with higher control efficiency.

[0084] In a further possible implementation, adjusting the service queue of the current edge processing server according to the service queue prediction coefficient includes:

[0085] Get the queue prediction coefficient Bp of the i-th edge processing server corresponding to the m edge processing servers i ;

[0086] Calculate the queue prediction coefficient Bp corresponding to m edge processing servers i The difference between the maximum and minimum values ​​in ;

[0087] If the difference is greater than or equal to the critical value, part of the services at the end of the current queue of the edge processing server corresponding to the maximum value are adjusted to the end of the current queue of the edge processing server corresponding to the minimum value according to the difference.

[0088] In the embodiment of the present disclosure, when adjusting the service queue of the current edge processing server according to the service queue prediction coefficient, the queue prediction coefficient Bp of the i-th edge processing server corresponding to the m edge processing servers can be obtained when the prediction period is the same. i , determine the queue prediction coefficient Bp i Then, the queue prediction coefficient Bp corresponding to the m edge processing servers can be calculated i The difference between the maximum value and the minimum value in is the difference. The difference is then compared with the critical value to determine whether the difference is greater than or equal to the critical value. The critical value can be set in advance according to the needs. If the difference is greater than or equal to the critical value, part of the business at the end of the current queue of the edge processing server corresponding to the maximum value can be adjusted to the end of the current queue of the edge processing server corresponding to the minimum value according to the difference. On the contrary, if the difference is less than the critical value, no adjustment is made.

[0089] In order to make the edge computing power optimization method based on the Internet of Things provided by the embodiment of the present disclosure clearer, it is explained below with reference to the following examples. The edge computing power optimization method based on the Internet of Things provided in this embodiment can be applied to an edge computing power optimization system based on the Internet of Things, and the edge computing power optimization system based on the Internet of Things may include: an edge processing module, an Internet of Things monitoring module, an analysis module and a central module. Among them, the edge processing module includes an edge processing server, a computing power allocation unit, a queue management unit and a wireless transmission unit; the edge processing server includes multiple computing nodes, and the computing power allocation unit divides the multiple computing nodes into a first partition and a second partition. Among them:

[0090] The queue management unit is used to adjust the queue of the current edge processing server. The adjustment process includes handing over a part of the business behind the queue to the current edge processing server for processing, and transmitting the other part to another edge processing server for processing. The queue management unit hands over the subtasks to the first partition of the current edge processing server for batch processing in the business handed over to the current edge processing server, and selects the last batch of some subtasks in the batch processed subtasks to be transmitted to the second partition of an edge processing server for processing. It can be understood that if the second partition used to process another part of the subtasks belongs to the same edge processing server as the first partition, it is directly transmitted. If the second partition used to process another part of the subtasks does not belong to the same edge processing server as the first partition, it is transmitted through a wireless transmission unit. Multiple splitting of the business and processing by different edge computing servers can also improve data security.

[0091] When the edge processing server is processing multiple businesses, by adjusting the queue length of each edge processing server, each edge processing server can achieve a similar processing time to avoid overuse of a certain edge processing server. In addition, the last batch of some subtasks in the batch processing subtasks can be selected and transmitted to the second partition of an edge processing server for processing. In this way, the utilization rate of each partition can be optimized, thereby improving processing efficiency and optimizing the utilization of computing power.

[0092] The IoT monitoring module is used to monitor the edge processing server and obtain the operating temperature data and business data of the edge processing server;

[0093] An analysis module, used to obtain a service queue prediction coefficient based on service data obtained by each edge processing server, and to obtain a load coefficient based on operating temperature data;

[0094] A queue management unit, used to adjust the queue of the current edge processing server according to the service queue prediction coefficient, so that the queue prediction coefficient values ​​of each queue after adjustment are close;

[0095] The queue management unit is used to determine whether to adjust the division of the first partition according to the load factor, and after determining that the division of the first partition needs to be adjusted, divide part of the computing nodes in the first partition as the third partition.

[0096] The process of obtaining the service queue prediction coefficient may include:

[0097] In edge processing servers, for the ith edge processing server, obtain ith continuous prediction cycles based on the current time point; calculate the queue prediction coefficient by formula (2). Adjust the queue of the current edge processing server according to the service queue prediction coefficient, including: when the number of prediction cycles is the same, obtain the queue prediction coefficient Bp of the ith edge processing server corresponding to the m edge processing servers i ; The queue prediction coefficient Bp corresponding to the m edge processing servers iThe maximum value in is compared with the minimum value to obtain the difference; the difference is compared with the critical value. If the difference is greater than or equal to the critical value, then according to the difference, several services at the end of the current queue of the edge processing server corresponding to the maximum value are moved to the end of the current queue of the edge processing server corresponding to the minimum value; if the difference is less than the critical value, no adjustment is made. After adjusting the queue of the current edge processing server, the queue prediction coefficient values ​​of each queue are close, so that the completion time of each queue is close, wherein the queue prediction coefficient is predicted based on a distribution function set based on multiple prediction cycles and the arrival rate of the basic business flow and the arrival rate of the random business flow, and it is also considered that the business needs to be split, so that the queue prediction coefficient used in the numeralization of formula (2) represents the queue length waiting for processing of each edge processing server, realizing digital regulation and control with higher control efficiency.

[0098] The process of obtaining the load coefficient includes: for the i-th edge processing server, calculating the load coefficient by formula (1).

[0099] The process of determining whether to adjust the division of the first partition according to the load coefficient includes: obtaining the load coefficient Load i , and the preset and For comparison, and The setting is based on empirical data; if Then it is determined that the division of the first partition of the i-th edge processing server needs to be adjusted; if It is determined that there is no need to adjust the division of the first partition of the i-th edge processing server; it should be noted that in the process of dividing some computing nodes from the first partition as the third partition, according to Load i The value of is selected through the reference table to set the number of computing nodes in the third partition; if The number of computing nodes in the third partition is reset to zero, which means returning the computing nodes from the first partition to the first partition. The number of computing nodes in multiple second partitions is different, so that different second partitions can adapt to different batches and perform calculations more flexibly.

[0100] After the division of the first partition is adjusted according to the load coefficient, an idle third partition can be divided. The third partition can be used to reduce the load state of the current edge processing server, reduce the load coefficient, and reduce the temperature of the edge processing server, thereby increasing the service life of the edge processing server. The load coefficient is obtained based on the current temperature and the current temperature change through formula (1). When the current temperature change and the preset temperature change are in the same direction, the load coefficient is positively affected by both the current temperature and the current temperature change. That is, the larger the current temperature change and the preset temperature change, the larger the load coefficient. Considering the current temperature change while considering the current temperature change can take the temperature change trend into consideration, thereby improving the judgment accuracy. When the current temperature change and the preset temperature change are in different directions, the preset temperature change is generally positive, which means that the current edge processing server is in a state of rapid cooling. Specifically, according to formula (1), the larger the preset temperature change, the smaller the load coefficient. That is, the load coefficient can accurately reflect the different load states of the edge processing server.

[0101] The edge processing module is preset with an information base. The edge processing module adds identification information to each received business and each business split batch from the preset information base. The content of the preset information base of each wireless transmission unit is different. Different subtasks and batches of the same task have the same identification information as the task. The central module includes a central computing unit and a central storage unit. After receiving subtasks and batches with identification information, the central storage unit stores the subtasks and batches with different identification information in different storage addresses.

[0102] Based on the same inventive concept, the embodiment of the present disclosure also provides an edge computing power optimization device based on the Internet of Things, such as Figure 2 As shown, Figure 2 is a block diagram of an edge computing power optimization device based on the Internet of Things according to an exemplary embodiment. Figure 2 , the edge computing power optimization device 200 based on the Internet of Things may include:

[0103] A service acquisition module 210 is used to acquire a service queue of a first edge processing server;

[0104] A service adjustment module 220, configured to allow the first portion of services after the service queue to be processed by the first edge processing server;

[0105] The computing power optimization module 230 is used to transmit the second part after the business queue to the second edge processing server for processing; wherein the first part of the business and the second part of the business are selected from the business after the business queue according to a preset ratio.

[0106] In a possible implementation, the service adjustment module 220 is configured to:

[0107] In the business processed by the first edge processing server, subtasks of the business are assigned to the first partition of the first edge processing server for batch processing;

[0108] The last batch of some subtasks in the batch-processed subtasks is selected and transmitted to the second partition processing of the third edge processing server; wherein the third edge processing server and the first edge processing server are the same edge processing server or two separate edge processing servers.

[0109] In a possible implementation, the method further includes:

[0110] A data acquisition module, used to obtain operating temperature data of each edge processing server;

[0111] A load factor calculation module, configured to determine a load factor of each edge processing server according to the operating temperature data of each edge processing server;

[0112] A partition division determination module, configured to determine whether to adjust the division of the first partition of the edge processing server according to the load factor of each edge processing server;

[0113] The partition adjustment module is used to divide part of the computing nodes in the first partition of the edge processing server as a third partition when it is determined that the division of the first partition of the edge processing server needs to be adjusted.

[0114] In a possible implementation manner, the module for determining partition division is used to:

[0115] The load factor Load obtained by the i-th edge processing server i , with the first preset load factor and a second preset load factor Make comparisons;

[0116] like Then adjusting the division of the first partition of the i-th edge processing server;

[0117] like The division of the first partition of the i-th edge processing server is not adjusted;

[0118] like Then the number of computing nodes in the third partition of the i-th edge processing server is reset to zero.

[0119] In a possible implementation, the method further includes:

[0120] A business data module is used to obtain business data of each edge processing server;

[0121] A prediction coefficient calculation module, used to determine a service queue prediction coefficient of each edge processing server according to the service data of each edge processing server;

[0122] The queue adjustment module is used to adjust the service queue of the edge processing server according to the service queue prediction coefficient.

[0123] In a possible implementation, the queue adjustment module is used to:

[0124] Get the queue prediction coefficient Bp of the i-th edge processing server corresponding to the m edge processing servers i ;

[0125] Calculate the queue prediction coefficient Bp corresponding to the m edge processing servers i The difference between the maximum and minimum values ​​in ;

[0126] If the difference is greater than or equal to the critical value, part of the services at the end of the current queue of the edge processing server corresponding to the maximum value are adjusted to the end of the current queue of the edge processing server corresponding to the minimum value according to the difference.

[0127] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0128] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a storage medium and a computer program product.

[0129] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device 300 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0130] like Figure 3As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0131] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0132] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as an edge computing power optimization method based on the Internet of Things. For example, in some embodiments, the edge computing power optimization method based on the Internet of Things may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the edge computing power optimization method based on the Internet of Things described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to execute an edge computing power optimization method based on the Internet of Things by any other appropriate means (for example, by means of firmware).

[0133] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] The program code of the computer program product for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0135] In the context of the present disclosure, a storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A storage medium may be a machine-readable signal medium or a machine-readable storage medium. Storage media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. More specific examples of storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0136] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0137] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0138] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0139] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0140] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for optimizing edge computing power based on the Internet of Things, characterized in that: include: Obtaining a service queue of a first edge processing server; Processing the first part of the services after the service queue by the first edge processing server; The second part after the service queue is transmitted to the second edge processing server for processing; wherein the first part of services and the second part of services are selected from the services after the service queue according to a preset ratio.

2. The edge computing power optimization method based on the Internet of Things according to claim 1 is characterized in that: The first edge processing server processes the first part of the services after the service queue, including: In the business processed by the first edge processing server, subtasks of the business are assigned to the first partition of the first edge processing server for batch processing; The last batch of some subtasks in the batch-processed subtasks is selected and transmitted to the second partition processing of the third edge processing server; wherein the third edge processing server and the first edge processing server are the same edge processing server or two separate edge processing servers.

3. The edge computing power optimization method based on the Internet of Things according to claim 1 is characterized in that: The method further comprises: Obtain operating temperature data for each edge processing server; Determining a load factor of each edge processing server according to the operating temperature data of each edge processing server; Determining whether to adjust the division of the first partition of the edge processing server according to the load factor of each edge processing server; When it is determined that the division of the first partition of the edge processing server needs to be adjusted, some computing nodes are divided from the first partition of the edge processing server as a third partition.

4. The edge computing power optimization method based on the Internet of Things according to claim 3 is characterized in that: The determining whether to adjust the division of the first partition of the edge processing server according to the load factor of each edge processing server includes: The load factor Load obtained by the i-th edge processing server o , with the first preset load factor and a second preset load factor Make comparisons; like Then adjusting the division of the first partition of the i-th edge processing server; like The division of the first partition of the i-th edge processing server is not adjusted; like Then the number of computing nodes in the third partition of the i-th edge processing server is reset to zero.

5. The edge computing power optimization method based on the Internet of Things according to any one of claims 1 to 4, characterized in that: The method further comprises: Obtain business data of each edge processing server; Determining a service queue prediction coefficient of each edge processing server according to the service data of each edge processing server; The service queue of the edge processing server is adjusted according to the service queue prediction coefficient.

6. The edge computing power optimization method based on the Internet of Things according to claim 5 is characterized in that: The adjusting the service queue of the current edge processing server according to the service queue prediction coefficient includes: Get the queue prediction coefficient Bp of the i-th edge processing server corresponding to the m edge processing servers i ; Calculate the queue prediction coefficient Bp corresponding to the m edge processing servers i The difference between the maximum and minimum values ​​in ; If the difference is greater than or equal to the critical value, part of the services at the end of the current queue of the edge processing server corresponding to the maximum value are adjusted to the end of the current queue of the edge processing server corresponding to the minimum value according to the difference.

7. An edge computing power optimization device based on the Internet of Things, characterized in that: include: A service acquisition module, used to acquire a service queue of a first edge processing server; A service adjustment module, configured to allow the first edge processing server to process a first portion of services after the service queue; A computing power optimization module is used to transmit the second part after the business queue to the second edge processing server for processing; wherein the first part of the business and the second part of the business are selected from the business after the business queue according to a preset ratio.

8. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the edge computing power optimization method based on the Internet of Things as described in any one of claims 1 to 6.

9. A storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the edge computing power optimization method based on the Internet of Things as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the edge computing power optimization method based on the Internet of Things as described in any one of claims 1 to 6 is implemented.

Citation Information

Cited By

  • Data transmission method and system of industrial edge gateway

    CN119316424A