CN117478681B - Recursive server state monitoring method based on edge calculation - Google Patents
Recursive server state monitoring method based on edge calculation Download PDFInfo
- Publication number
- CN117478681B CN117478681B CN202311798152.6A CN202311798152A CN117478681B CN 117478681 B CN117478681 B CN 117478681B CN 202311798152 A CN202311798152 A CN 202311798152A CN 117478681 B CN117478681 B CN 117478681B
- Authority
- CN
- China
- Prior art keywords
- processing
- data
- coefficient
- index
- difficulty
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004364 calculation method Methods 0.000 title claims abstract description 38
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 171
- 230000005540 biological transmission Effects 0.000 claims abstract description 31
- 238000009826 distribution Methods 0.000 claims description 30
- 230000008569 process Effects 0.000 claims description 27
- 238000004891 communication Methods 0.000 claims description 7
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 11
- 238000003860 storage Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1021—Server selection for load balancing based on client or server locations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1029—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers using data related to the state of servers by a load balancer
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1036—Load balancing of requests to servers for services different from user content provisioning, e.g. load balancing across domain name servers
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Complex Calculations (AREA)
Abstract
The invention discloses a recursive server state monitoring method based on edge calculation, and particularly relates to the technical field of networks. And comprehensively calculating the processing difficulty coefficient and the processing performance coefficient to obtain a result value, and helping to confirm which edge devices are suitable for processing the data source. In addition, the data transmission distance between the edge equipment and the data source is analyzed through the transmission distance index, so that the edge equipment which is close to the data source and has enough processing capacity is selected, further, the data transmission delay can be reduced, the timeliness and the accuracy of data processing are ensured, the data processing burden of a central server is lightened, and the data processing efficiency and the system performance under the edge computing environment are significant.
Description
Technical Field
The invention relates to the technical field of networks, in particular to a recursive server state monitoring method based on edge calculation.
Background
The recursive server is a domain name resolution server and is responsible for converting a domain name input by a user into a corresponding IP address, so that the user can access websites and services on the Internet, the recursive server is in a middle position in a hierarchical structure of the DNS, and information required by domain name resolution is mainly acquired by querying other DNS servers.
In the conventional method of monitoring the recursive servers, it is highly dependent on the central server to process all the monitored data centrally, which easily causes network bandwidth bottlenecks and overload of the central server. Due to the lack of a distributed task allocation mechanism, monitoring data may be delayed in the transmission process, which affects real-time performance and accuracy. In addition, the traditional method does not effectively utilize the computing resources of the network edge nodes, so that the potential of the edge devices is not fully utilized, the problems of insufficient computing capacity and slow response speed are faced, and the quality and the practicability of the monitoring result are reduced.
In order to solve the above problems, a technical solution is now provided.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks of the prior art, the embodiment of the present invention provides that, by collecting the data source of the monitoring server and combining the data distribution index and the data complexity index, a processing difficulty coefficient is established to measure the complexity and difficulty of data source analysis, and further, the processing performance coefficient and the transmission distance index of the edge device are considered, so as to evaluate the performance condition of the edge device. The process difficulty coefficient and the process performance coefficient are then comprehensively calculated to obtain a result value, which helps to confirm which edge devices are suitable for processing the data source. In addition, the data transmission distance between the edge device and the data source is analyzed through the transmission distance index, so that the edge device which is close to the data source and has enough processing capacity is selected, and the problems in the background art are solved.
In order to achieve the above purpose, the present invention provides the following technical solutions:
step S100, collecting a data source of a monitoring server, collecting space information and structure information of the data source, comprehensively processing and calculating the space information and the structure information to obtain a processing difficulty coefficient, analyzing the processing difficulty coefficient to generate a difficulty level signal, wherein the difficulty level signal comprises a height difficulty signal and a low difficulty signal;
step S200, collecting the dominable information and the distance information of the edge equipment, wherein the dominable information comprises a processing performance coefficient, and analyzing the processing performance coefficient to generate a display signal and a hidden signal;
and step S300, comprehensively calculating the processing difficulty coefficient and the processing performance coefficient to obtain a result value, counting edge equipment which accords with the result value smaller than a result threshold, and sequencing the first sequence according to the transmission distance index from small to large to be marked as processing equipment.
In a preferred embodiment, the spatial information comprises a data distribution index and the structural information comprises a data complexity index.
In a preferred embodiment, the data distribution index acquisition logic is:
step a11, collecting data points of the spatial attribute of the data source, and ensuring that each data point comprises corresponding spatial attribute information; the data source is used for acquiring the running state data of the server in unit time;
step a12, calculating to obtain a kernel function, wherein the calculation formula is as follows:
；
in the method, in the process of the invention,representing the kernel function at variable +.>Values on spatial properties, +.>Is a variable, is，/>Spatial properties of data points, wherein->，/>Index representing data point, and->Is a positive integer which is used for the preparation of the high-voltage power supply,/>is a bandwidth parameter, +.>Is the location where the density needs to be calculated;
step a13, for each spatial attribute, calculating the value of the kernel function on the attribute value, and adding the kernel function values of all the data points to obtain an estimated density, namely kernel density estimation, wherein the calculation formula is as follows:
；
；
in the method, in the process of the invention,representing the position of the computation on the spatial properties +.>A density estimate at.
Step a14, calculating the position on the time attribute according to the calculation formulaIs to be spatially attributed to the position +.>Density estimate and position on time attribute +.>And (3) adding and averaging the density estimation values of the data to obtain a data distribution index.
In a preferred embodiment, the data complexity index acquisition logic is:
step a21, counting attributes and data points of a data source;
step a22, pairing each attribute in pairs to analyze and calculate mutual information, wherein the calculation formula is as follows:
wherein->Representing attribute->And attribute->Is expressed by simultaneous consideration of +.>And->Probability distribution of (2);
and a step a23 of comparing the mutual information value with the mutual information threshold value, counting the number of the mutual information value which is larger than or equal to the mutual information threshold value, namely the number with stronger nonlinear relation, and calculating the ratio of the number with stronger nonlinear relation to the total number of times of calculating the nonlinear relation to obtain the data complexity index.
In a preferred embodiment, the data distribution index and the data complexity index are comprehensively analyzed and calculated to obtain the processing difficulty coefficient, and the calculation formula is as follows:wherein->For the treatment difficulty coefficient>Data distribution index, data complexity index, < ->Preset proportional coefficients of data distribution index and data complexity index respectively, and +.>Are all greater than 0;
comparing the processing difficulty coefficient with a processing difficulty threshold, if the processing difficulty coefficient is greater than or equal to the processing difficulty threshold, indicating that higher performance and resources are needed for processing the data, and generating a high difficulty signal; if the processing difficulty coefficient is smaller than the processing difficulty threshold, the processing difficulty coefficient indicates that the performance and the resources of processing equipment required for processing the data are lower, and a low-difficulty signal is generated.
In a preferred embodiment, the dominance information comprises a processing performance coefficient and the distance information comprises a transmission distance index.
In a preferred embodiment, the processing coefficient of performance acquisition logic is:
step b11, obtaining basic information of a processor of the edge equipment, including clock frequency, core number, thread number and current load condition, wherein the information can be obtained through an operating system or a hardware monitoring tool;
step b12, for each processor, using its clock frequency, number of cores and number of threads to calculate theoretical peak performance, the calculation method is as follows:
theoretical peak performance = clock frequency (GHz) x number of cores x number of threads
Step b13, considering the concurrency factor of each processor, i.e. the number of tasks or threads that each processor can process simultaneously, for each processor, considering the task and process load situation currently running on that processor, if the processor is already executing other tasks, the dominating performance will be limited by the current load, multiplying the theoretical peak performance of each processor by the concurrency factor, and adjusting according to the current load situation to calculate the supportable amount of each processor, the calculation formula is as follows:
branching amount = theoretical peak performance x concurrency factor x (1-load percentage)
Step b14, collecting a plurality of supportable quantities in the time t, calculating a manageable average value, comparing the manageable average value with a manageable threshold value, and if the manageable average value is larger than the manageable threshold value, calculating standard deviations of the plurality of supportable quantities, namely processing performance coefficients;
comparing the processing performance coefficient with a processing performance threshold, and if the processing performance coefficient is smaller than the processing performance threshold, indicating that the edge equipment has higher controllable processing capacity in unit time, and generating a display signal; if the processing performance coefficient is greater than or equal to the processing performance threshold, the processing capability and the processing stability of the edge equipment are lower, and a hidden signal is generated.
In a preferred embodiment, the transmission distance index acquisition logic is:
step c1, constructing a weighted directed graph according to network topology information, wherein nodes represent devices or nodes, edges represent communication links for connecting the devices, and weights represent communication distances;
step c2, initializing a distance array for recording the shortest distance from the data source node to each node, and a marking array for marking whether the node has been accessed. Initializing a distance array to infinity, wherein the distance of the data source node is 0, and the mark array is initialized to an unaccessed state;
step c3, selecting a node with the smallest distance from the non-accessed nodes as a current node;
step c4, traversing neighbor nodes of the current node, and updating values in the distance array if the distance from the current node to the neighbor nodes is smaller than the values recorded in the distance array;
step c5, marking the current node as accessed;
step c6, repeating the steps of selecting the minimum distance node, updating the distance and marking the node until the edge equipment is accessed;
step c7, generating a shortest path from the data source to the edge device through the distance array and the structure of the graph, wherein the calculation formula of the length of the shortest path is as follows:wherein->Is the length of the shortest path, i.e. transmission distance index,/->Is the number of nodes on the path, < >>Is the>Distance of the segment edges.
In a preferred embodiment, the result value is obtained by comprehensively analyzing and calculating the processing difficulty coefficient and the processing performance coefficient, and the calculation formula is as follows:wherein->For the result value->The treatment difficulty coefficient and the treatment performance index are respectively +.>The processing difficulty threshold value and the processing performance threshold value are respectively +.>Respectively->Is a preset proportional coefficient of>Greater than 0->Less than 0.
In a preferred embodiment, if the result value is greater than or equal to the result threshold, it indicates that the edge device cannot process the data source and does not generate a signal; if the result value is smaller than the result threshold, the edge equipment can process the data source, the edge equipment meeting the requirement is counted, the first order is marked as processing equipment according to the order of the transmission distance indexes from small to large, and the processing equipment feeds back the processing result after the processing is completed and gathers the processing result to the central server.
The recursive server state monitoring method based on edge calculation has the technical effects and advantages that:
by collecting the data source of the monitoring server, the data distribution index and the data complexity index are comprehensively considered to establish a processing difficulty coefficient, so that the complexity and difficulty of data source analysis are quantified. Further, the processing performance coefficient and the transmission distance index of the edge device are considered, and the performance condition of the edge device is evaluated by these indexes. And then, comprehensively calculating the processing difficulty coefficient and the processing performance coefficient to obtain a result value, thereby being beneficial to determining which edge devices have the capability of processing the data source. In addition, the data transmission distance between the edge device and the data source is analyzed by using the transmission distance index. Finally, the edge equipment which has enough processing capacity and is nearer to the data source is conveniently screened out, so that the computing resources of the network edge node are utilized to the greatest extent; and further, delay in the data transmission process can be effectively reduced, the instantaneity and the accuracy of data processing are guaranteed, and meanwhile, the data processing pressure of the central server is obviously reduced. The method is beneficial to optimizing the data processing and analysis flow under the edge computing environment and improving the performance and efficiency of the system.
Drawings
Fig. 1 is a flow chart of a recursive server state monitoring method based on edge calculation according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples
Fig. 1 shows a recursive server state monitoring method based on edge calculation, which specifically includes the following steps:
step S100, collecting a data source of a monitoring server, collecting space information and structure information of the data source, comprehensively processing and calculating the space information and the structure information to obtain a processing difficulty coefficient, analyzing the processing difficulty coefficient to generate a difficulty level signal, wherein the difficulty level signal comprises a height difficulty signal and a low difficulty signal;
step S200, collecting the dominable information and the distance information of the edge equipment, wherein the dominable information comprises a processing performance coefficient, and analyzing the processing performance coefficient to generate a display signal and a hidden signal;
and step S300, the processing difficulty coefficient and the processing performance coefficient are integrated to obtain a result value, the result value is smaller than a result threshold value, and the first edge equipment is marked as processing equipment according to the transmission distance index.
The step S100 specifically includes the following steps:
the spatial information includes a data distribution index and the structural information includes a data complexity index.
The data distribution index acquisition logic is as follows:
step a11, collecting data points of the spatial attribute of the data source, and ensuring that each data point comprises corresponding spatial attribute information; the data source is used for acquiring the running state data of the server in unit time;
step a12, calculating to obtain a kernel function, wherein the calculation formula is as follows:
；
in the method, in the process of the invention,representing the kernel function at variable +.>Empty at the positionValues on inter-attribute,/->Is a variable, is，/>Spatial properties of data points, wherein->，/>Index representing data point, and->Is a positive integer>Is a bandwidth parameter, +.>Is where the density needs to be calculated.
Step a13, for each spatial attribute, calculating the value of the kernel function on the attribute value, and adding the kernel function values of all the data points to obtain an estimated density, namely kernel density estimation, wherein the calculation formula is as follows:
；
；
in the method, in the process of the invention,representing the position of the computation on the spatial properties +.>A density estimate at.
Step a14, calculating the position on the time attribute according to the calculation formulaIs to be spatially attributed to the position +.>Density estimate and position on time attribute +.>And (3) adding and averaging the density estimation values of the data to obtain a data distribution index.
The data distribution index is used for representing the integration level of the distribution characteristics of the data in space and time, namely the aggregation degree of the data points in the two dimensions, and is used for representing the overall distribution condition of the data, and the larger the data distribution index is, the more concentrated and aggregated the data are distributed in time and space, so that the difficulty of data processing is increased, the difficulty of data following and processing is increased, and the edge equipment with better performance is required to perform analysis processing; the smaller the data distribution index, the more dispersed the data is in the two dimensions of time and space, and the smaller the data density, the simpler the analysis is.
The acquisition logic of the data complexity index is as follows:
step a21, counting attributes and data points of a data source;
step a22, pairing each attribute in pairs to analyze and calculate mutual information, wherein the calculation formula is as follows:
wherein->Representing attribute->And attribute->Is expressed by simultaneous consideration of +.>And->Probability distribution of (2);
and a step a23 of comparing the mutual information value with the mutual information threshold value, counting the number of the mutual information value which is larger than or equal to the mutual information threshold value, namely the number with stronger nonlinear relation, and calculating the ratio of the number with stronger nonlinear relation to the total number of times of calculating the nonlinear relation to obtain the data complexity index.
The greater the data complexity index, which is used to analyze the complexity of the overall data structure of the data source, the greater the structural complexity of obtaining data of the running state of the server in a unit time, and more advanced analysis tools and techniques are required, and more computing resources, including processing power and memory, are required, thus placing higher demands on the capabilities of the processing device.
The data distribution index and the data complex index are comprehensively analyzed and calculated to obtain a processing difficulty coefficient, and the calculation formula is as follows:wherein->For the treatment difficulty coefficient>Data distribution index, data complexity index, < ->Preset proportional coefficients of data distribution index and data complexity index respectively, and +.>Are all greater than 0.
The processing difficulty index is used for measuring the difficulty degree of data processing, and the value of the processing difficulty coefficient is larger, which means that the distribution and the data structure of the data source are complex, and more resources and performance are needed for processing the data; the smaller the value of the processing difficulty index, the easier the data processing task is, meaning that the data is simply distributed, the data structure is clear, and less resources and performance are required to process the data.
Comparing the processing difficulty coefficient with a processing difficulty threshold, if the processing difficulty coefficient is greater than or equal to the processing difficulty threshold, indicating that higher performance and resources are needed for processing the data, and generating a high difficulty signal; if the processing difficulty coefficient is smaller than the processing difficulty threshold, the processing difficulty coefficient indicates that the performance and the resources of processing equipment required for processing the data are lower, and a low-difficulty signal is generated.
The step S200 specifically includes the following steps:
edge devices refer to those computing and communication devices that are located at edge locations, closer to the data source, typically at or near the location where the data is generated. These devices may be of various types including sensors, cameras, smartphones, routers, embedded systems, servers, industrial devices, and the like.
The dominance information comprises a processing performance coefficient and the distance information comprises a transmission distance index.
The acquisition logic of the processing performance coefficient is as follows:
step b11, obtaining basic information of a processor of the edge equipment, including clock frequency, core number, thread number and current load condition, wherein the information can be obtained through an operating system or a hardware monitoring tool;
step b12, for each processor, using its clock frequency, number of cores and number of threads to calculate theoretical peak performance, the calculation method is as follows:
theoretical peak performance = clock frequency (GHz) x number of cores x number of threads
Step b13, considering the concurrency factor of each processor, i.e. the number of tasks or threads that each processor can process simultaneously, for each processor, considering the task and process load situation currently running on that processor, if the processor is already executing other tasks, the dominating performance will be limited by the current load, multiplying the theoretical peak performance of each processor by the concurrency factor, and adjusting according to the current load situation to calculate the supportable amount of each processor, the calculation formula is as follows:
branching amount = theoretical peak performance x concurrency factor x (1-load percentage)
And b14, collecting a plurality of supportable quantities within the time t, calculating a manageable average value, comparing the manageable average value with a manageable threshold value, and if the manageable average value is larger than the manageable threshold value, calculating the standard deviation of the plurality of supportable quantities, namely, processing performance coefficients.
The processing performance coefficient is used for measuring the processing capacity and the processing stability of the edge equipment, and the larger the processing performance coefficient is, the higher the processing capacity of the edge equipment is, which means that the edge equipment has higher controllable processing capacity in unit time, and the faster the edge equipment can process tasks or processes, and the stronger the computing performance and the computing stability are; conversely, a smaller processing performance coefficient indicates a lower processing capacity and processing stability of the edge device, meaning a weaker computing performance.
Comparing the processing performance coefficient with a processing performance threshold, if the processing performance coefficient is smaller than the processing performance threshold, the edge equipment has higher controllable processing capacity in unit time, which means that the edge equipment can process tasks or processes more rapidly, has stronger calculation performance and calculation stability, and generates a display signal; if the processing performance coefficient is greater than or equal to the processing performance threshold, the processing capability and the processing stability of the edge device are lower, which means that the computing performance is weaker, and a hidden signal is generated.
The acquisition logic of the transmission distance index is as follows:
step c1, constructing a weighted directed graph according to network topology information, wherein nodes represent devices or nodes, edges represent communication links for connecting the devices, and weights represent communication distances;
step c2, initializing a distance array for recording the shortest distance from the data source node to each node, and a marking array for marking whether the node has been accessed. Initializing a distance array to infinity, wherein the distance of the data source node is 0, and the mark array is initialized to an unaccessed state;
step c3, selecting a node with the smallest distance from the non-accessed nodes as a current node;
step c4, traversing neighbor nodes of the current node, and updating values in the distance array if the distance from the current node to the neighbor nodes is smaller than the values recorded in the distance array;
step c5, marking the current node as accessed;
step c6, repeating the steps of selecting the minimum distance node, updating the distance and marking the node until the edge equipment is accessed;
step c7, generating a shortest path from the data source to the edge device through the distance array and the structure of the graph, wherein the calculation formula of the length of the shortest path is as follows:wherein->Is the length of the shortest path, i.e. transmission distance index,/->Is the number of nodes on the path, < >>Is the>Distance of the segment edges.
The transmission distance index is used to measure the data transmission distance between the data source and the edge device.
The step S300 specifically includes the following steps:
the processing difficulty coefficient and the processing performance coefficient are comprehensively analyzed and calculated to obtain a result value, and the calculation formula is as follows:wherein->For the result value->The treatment difficulty coefficient and the treatment performance index are respectively +.>The processing difficulty threshold value and the processing performance threshold value are respectively +.>Respectively->Is a preset proportional coefficient of>Greater than 0->Less than 0.
The result value is used for indicating whether the edge device meets the processing data source;
if the result value is greater than or equal to the result threshold value, the edge equipment cannot process the data source and does not generate a signal; if the result value is smaller than the result threshold, the edge equipment can process the data source, the edge equipment meeting the requirement is counted, the first order is marked as processing equipment according to the order of the transmission distance indexes from small to large, and the processing equipment feeds back the processing result after the processing is completed and gathers the processing result to the central server.
According to the invention, the data source of the monitoring server is acquired, and the data distribution index and the data complexity index are comprehensively considered to establish the processing difficulty coefficient, so that the complexity and difficulty of data source analysis are quantified. Further, the processing performance coefficient and the transmission distance index of the edge device are considered, and the performance condition of the edge device is evaluated by these indexes. And then, comprehensively calculating the processing difficulty coefficient and the processing performance coefficient to obtain a result value, thereby being beneficial to determining which edge devices have the capability of processing the data source. In addition, the data transmission distance between the edge device and the data source is analyzed by using the transmission distance index. Finally, the edge equipment which has enough processing capacity and is nearer to the data source is conveniently screened out, so that the computing resources of the network edge node are utilized to the greatest extent; and further, delay in the data transmission process can be effectively reduced, the instantaneity and the accuracy of data processing are guaranteed, and meanwhile, the data processing pressure of the central server is obviously reduced. The method is beneficial to optimizing the data processing and analysis flow under the edge computing environment and improving the performance and efficiency of the system.
The above formulas are all formulas with dimensionality removed and numerical calculation, the formulas are formulas with the latest real situation obtained by software simulation through collecting a large amount of data, and preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present application are all or partially produced. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is merely a logical function division, and there may be other manners of division when actually implemented.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or other various media capable of storing program codes.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (3)
1. The recursive server state monitoring method based on edge calculation is characterized by comprising the following steps:
step S100, collecting a data source of a monitoring server, collecting space information and structure information of the data source, comprehensively processing and calculating the space information and the structure information to obtain a processing difficulty coefficient, analyzing the processing difficulty coefficient to generate a difficulty level signal, wherein the difficulty level signal comprises a height difficulty signal and a low difficulty signal;
step S200, collecting the dominable information and the distance information of the edge equipment, wherein the dominable information comprises a processing performance coefficient, and analyzing the processing performance coefficient to generate a display signal and a hidden signal;
step S300, comprehensively calculating a processing difficulty coefficient and a processing performance coefficient to obtain a result value, counting edge equipment which accords with the result value smaller than a result threshold, and sequencing from small to large according to a transmission distance index, wherein the first sequencing is marked as processing equipment;
the spatial information comprises a data distribution index, and the structural information comprises a data complexity index;
the data distribution index acquisition logic is as follows:
step a11, collecting data points of the spatial attribute of the data source, and ensuring that each data point comprises corresponding spatial attribute information; the data source is used for acquiring the running state data of the server in unit time;
step a12, calculating to obtain a kernel function, wherein the calculation formula is as follows:
；
in the method, in the process of the invention,representing the kernel function at variable +.>Values on spatial properties, +.>Is a variable, is，/>Spatial properties of data points, wherein->，/>Index representing data point, and->Is a positive integer>Is a bandwidth parameter, +.>Is the location where the density needs to be calculated;
step a13, for each spatial attribute, calculating the value of the kernel function on the attribute value, and adding the kernel function values of all the data points to obtain an estimated density, namely kernel density estimation, wherein the calculation formula is as follows:
；
；
in the method, in the process of the invention,representing the position of the computation on the spatial properties +.>Estimating the density at the location;
step a14, calculating the position on the time attribute according to the calculation formulaIs to be spatially attributed to the position +.>Density estimate and position on time attribute +.>Adding and averaging the density estimation values of the data to obtain a data distribution index;
the acquisition logic of the data complexity index is as follows:
step a21, counting attributes and data points of a data source;
step a22, pairing each attribute in pairs to analyze and calculate mutual information, wherein the calculation formula is as follows:wherein->Representing attribute->And attribute->Is expressed by simultaneous consideration of +.>And->Probability distribution of (2);
step a23, comparing the mutual information value with the mutual information threshold value, counting the number of the mutual information value which is larger than or equal to the mutual information threshold value, namely the number with stronger nonlinear relation, calculating the ratio of the number with stronger nonlinear relation to the total number of times of calculating the nonlinear relation, and obtaining a data complexity index;
the data distribution index and the data complex index are comprehensively analyzed and calculated to obtain a processing difficulty coefficient, and the calculation formula is as follows:wherein->For the treatment difficulty coefficient>Data distribution index, data complexity index, < ->Preset proportional coefficients of data distribution index and data complexity index respectively, andare all greater than 0;
comparing the processing difficulty coefficient with a processing difficulty threshold, if the processing difficulty coefficient is greater than or equal to the processing difficulty threshold, indicating that higher performance and resources are needed for processing the data, and generating a high difficulty signal; if the processing difficulty coefficient is smaller than the processing difficulty threshold, the processing difficulty coefficient indicates that the performance and the resources of processing equipment required for processing the data are lower, and a low-level difficulty signal is generated;
the dominance information includes a processing performance coefficient, and the distance information includes a transmission distance index;
the acquisition logic of the processing performance coefficient is as follows:
step b11, obtaining basic information of a processor of the edge equipment, including clock frequency, core number, thread number and current load condition, wherein the information can be obtained through an operating system or a hardware monitoring tool;
step b12, for each processor, using its clock frequency, number of cores and number of threads to calculate theoretical peak performance, the calculation method is as follows:
theoretical peak performance = clock frequency (GHz) x number of cores x number of threads
Step b13, considering the concurrency factor of each processor, i.e. the number of tasks or threads that each processor can process simultaneously, for each processor, considering the task and process load situation currently running on that processor, if the processor is already executing other tasks, the dominating performance will be limited by the current load, multiplying the theoretical peak performance of each processor by the concurrency factor, and adjusting according to the current load situation to calculate the supportable amount of each processor, the calculation formula is as follows:
branching amount = theoretical peak performance x concurrency factor x (1-load percentage)
Step b14, collecting a plurality of supportable quantities in the time t, calculating a manageable average value, comparing the manageable average value with a manageable threshold value, and if the manageable average value is larger than the manageable threshold value, calculating standard deviations of the plurality of supportable quantities, namely processing performance coefficients;
comparing the processing performance coefficient with a processing performance threshold, and if the processing performance coefficient is smaller than the processing performance threshold, indicating that the edge equipment has higher controllable processing capacity in unit time, and generating a display signal; if the processing performance coefficient is greater than or equal to the processing performance threshold, the processing capability and the processing stability of the edge equipment are lower, and a hidden signal is generated;
the acquisition logic of the transmission distance index is as follows:
step c1, constructing a weighted directed graph according to network topology information, wherein nodes represent devices or nodes, edges represent communication links for connecting the devices, and weights represent communication distances;
step c2, initializing a distance array for recording the shortest distance from the data source node to each node, and a mark array for marking whether the node has been accessed, initializing the distance array to infinity, except that the distance of the data source node is 0, and initializing the mark array to an unaccessed state;
step c3, selecting a node with the smallest distance from the non-accessed nodes as a current node;
step c4, traversing neighbor nodes of the current node, and updating values in the distance array if the distance from the current node to the neighbor nodes is smaller than the values recorded in the distance array;
step c5, marking the current node as accessed;
step c6, repeating the steps of selecting the minimum distance node, updating the distance and marking the node until the edge equipment is accessed;
step c7, generating a shortest path from the data source to the edge device through the distance array and the structure of the graph, wherein the calculation formula of the length of the shortest path is as follows:wherein->For the length of the shortest path, i.e. transmissionDistance index (I)>Is the number of nodes on the path, < >>Is the>Distance of the segment edges.
2. The edge computation-based recursive server state monitoring method of claim 1, wherein:
the processing difficulty coefficient and the processing performance coefficient are comprehensively analyzed and calculated to obtain a result value, and the calculation formula is as follows:wherein->For the result value->The treatment difficulty coefficient and the treatment performance index are respectively +.>The processing difficulty threshold value and the processing performance threshold value are respectively +.>Respectively->Is a preset proportional coefficient of>Greater than 0->Less than 0.
3. The edge computation-based recursive server state monitoring method of claim 2, wherein:
if the result value is greater than or equal to the result threshold value, the edge equipment cannot process the data source and does not generate a signal; if the result value is smaller than the result threshold, the edge equipment can process the data source, the edge equipment meeting the requirement is counted, the first order is marked as processing equipment according to the order of the transmission distance indexes from small to large, and the processing equipment feeds back the processing result after the processing is completed and gathers the processing result to the central server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311798152.6A CN117478681B (en) | 2023-12-26 | 2023-12-26 | Recursive server state monitoring method based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311798152.6A CN117478681B (en) | 2023-12-26 | 2023-12-26 | Recursive server state monitoring method based on edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117478681A CN117478681A (en) | 2024-01-30 |
| CN117478681B true CN117478681B (en) | 2024-03-08 |
Family
ID=89625981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311798152.6A Active CN117478681B (en) | 2023-12-26 | 2023-12-26 | Recursive server state monitoring method based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117478681B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050787A (en) * | 2013-03-12 | 2014-09-17 | 霍尼韦尔国际公司 | System and Method of Anomaly Detection with Categorical Attributes |
| CN110336703A (en) * | 2019-07-12 | 2019-10-15 | 河海大学常州校区 | Industrial big data based on edge calculations monitors system |
| CN111025969A (en) * | 2019-12-05 | 2020-04-17 | 浙江大学 | Wild animal monitoring system and method based on information fusion |
| CN111459617A (en) * | 2020-04-03 | 2020-07-28 | 南方电网科学研究院有限责任公司 | Containerized application automatic allocation optimization system and method based on cloud platform |
| CN115964655A (en) * | 2023-01-13 | 2023-04-14 | 哈尔滨工业大学 | Method for monitoring error-related potential in brain-computer interface based on mutual information quantity |
| CN116320832A (en) * | 2023-05-23 | 2023-06-23 | 常州指尖互动网络科技有限公司 | Monitoring equipment fault monitoring method and device |
| CN116894166A (en) * | 2023-09-11 | 2023-10-17 | 中国标准化研究院 | Soil environment parameter information monitoring system based on intelligent sensing network |
| CN116992245A (en) * | 2023-09-27 | 2023-11-03 | 江西珉轩大数据有限公司 | Distributed time sequence data analysis processing method |
| CN117273278A (en) * | 2023-10-18 | 2023-12-22 | 车位管家(深圳)科技有限公司 | ERP cloud management system |
-
2023
- 2023-12-26 CN CN202311798152.6A patent/CN117478681B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050787A (en) * | 2013-03-12 | 2014-09-17 | 霍尼韦尔国际公司 | System and Method of Anomaly Detection with Categorical Attributes |
| CN110336703A (en) * | 2019-07-12 | 2019-10-15 | 河海大学常州校区 | Industrial big data based on edge calculations monitors system |
| CN111025969A (en) * | 2019-12-05 | 2020-04-17 | 浙江大学 | Wild animal monitoring system and method based on information fusion |
| CN111459617A (en) * | 2020-04-03 | 2020-07-28 | 南方电网科学研究院有限责任公司 | Containerized application automatic allocation optimization system and method based on cloud platform |
| CN115964655A (en) * | 2023-01-13 | 2023-04-14 | 哈尔滨工业大学 | Method for monitoring error-related potential in brain-computer interface based on mutual information quantity |
| CN116320832A (en) * | 2023-05-23 | 2023-06-23 | 常州指尖互动网络科技有限公司 | Monitoring equipment fault monitoring method and device |
| CN116894166A (en) * | 2023-09-11 | 2023-10-17 | 中国标准化研究院 | Soil environment parameter information monitoring system based on intelligent sensing network |
| CN116992245A (en) * | 2023-09-27 | 2023-11-03 | 江西珉轩大数据有限公司 | Distributed time sequence data analysis processing method |
| CN117273278A (en) * | 2023-10-18 | 2023-12-22 | 车位管家(深圳)科技有限公司 | ERP cloud management system |
Non-Patent Citations (2)
| Title |
|---|
| 基于参数优化变分模态分解和多尺度熵偏均值的行星变速箱故障特征提取;杨大为;赵永东;冯辅周;江鹏程;丁闯;;兵工学报;20180915(09);全文 * |
| 汪进鸿 ; 韩宇星 ; .用于作物表型信息边缘计算采集的认知无线传感器网络分簇路由算法.智慧农业(中英文).(02),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117478681A (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7010641B2 (en) | Abnormality diagnosis method and abnormality diagnosis device | |
| Barrat et al. | Rate equation approach for correlations in growing network models | |
| US8180914B2 (en) | Deleting data stream overload | |
| CN109120463B (en) | Flow prediction method and device | |
| CN111212330A (en) | Method and device for determining network performance bottleneck value | |
| CN103455842A (en) | Credibility measuring method combining Bayesian algorithm and MapReduce | |
| CN113054651B (en) | Network topology optimization method, device and system | |
| Umoren et al. | Methodical Performance Modelling of Mobile Broadband Networks with Soft Computing Model | |
| Xu et al. | Challenging the limits: Sampling online social networks with cost constraints | |
| CN117478681B (en) | Recursive server state monitoring method based on edge calculation | |
| CN109560978A (en) | Network flow detection method, apparatus and system and computer readable storage medium | |
| CN111400045A (en) | Load balancing method and device | |
| Mastelic et al. | Data velocity scaling via dynamic monitoring frequency on ultrascale infrastructures | |
| Fedevych et al. | Researching measured and modeled traffic with self-similar properties for ateb-modeling method improvement | |
| Dogman et al. | Multimedia traffic quality of service management using statistical and artificial intelligence techniques | |
| CN115484624A (en) | Data processing method, architecture, electronic device and storage medium | |
| Yu et al. | Scale-free networks: evolutionary acceleration of the network survivability and its quantification | |
| Martins et al. | Hercules: A context-aware multiple application and multisensor data fusion algorithm | |
| JP7325557B2 (en) | Abnormality diagnosis method and abnormality diagnosis device | |
| Grytsenko et al. | A method of network monitoring with reduced measured data | |
| CN112311791B (en) | Statistical method and system suitable for office business flow | |
| JP2015515779A (en) | Method and server for determining the quality of a home network | |
| Khudoyarova et al. | Using Machine Learning to Analyze Network Traffic Anomalies | |
| JP2019087978A (en) | Quality estimation device and quality estimation method | |
| Villalba et al. | Analysis of mp4 videos in 5g using sdn |
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 |