Multi-terminal server data interconnection management and control system and method based on cloud computing

Abstract

The invention discloses a multi-terminal server data interconnection management and control system and method based on cloud computing, and relates to the technical field of server data processing.The method comprises the steps that online server ports are determined, a real-time state matrix sequence is constructed, and real-time state indexes of the server ports are evaluated; constructing a gradient analysis model, and performing gradient division on the real-time state index of the server port; based on the gradient level division data, state balance index analysis is carried out on each gradient level, and fluctuation analysis is carried out on the real-time state index of the server port; establishing a performance fluctuation influence function to fit the real-time performance fluctuation influence curve of each server port, analyzing the real-time performance fluctuation synchronization rate between the server ports, and outputting an optimal server interconnection group; according to the invention, the real-time operation state of the server port is subjected to aging association mining, so that the data interconnection group construction of the server port is realized, and the data processing efficiency and the compression resistance of the server in a high-concurrency scene are improved.

Description

Technical Field

[0001] This invention relates to the field of server data processing technology, specifically a multi-terminal server data interconnection and management system and method based on cloud computing. Background Technology

[0002] Driven by accelerated digital transformation and diversified business scenarios, enterprises and institutions generally build multi-terminal server architectures to support distributed business, which include local physical servers, cloud nodes and edge computing devices; such architectures enhance business elasticity and coverage.

[0003] This type of architecture increases the number of server nodes to cope with high-concurrency data scenarios. While it can meet the demand for high data interaction, the quality of data transmission is difficult to guarantee due to the differences in the real-time operating status of different servers. The high-demand intensity of a single server often leads to high latency in data interaction with other servers or even server crashes and unresponsiveness. The occurrence of such failures lacks targeted and timely correlation analysis of the real-time operating status of each server, and it is impossible to effectively plan and combine data interactions between servers. Summary of the Invention

[0004] The purpose of this invention is to provide a cloud computing-based multi-terminal server data interconnection and management system and method to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A cloud computing-based method for managing and controlling data interconnection between multiple servers, comprising the following steps:

[0007] The online server port is determined based on the cloud platform, the server port's operating status data is recorded synchronously, and a real-time status matrix sequence is constructed.

[0008] The real-time state matrix sequence is retrieved to evaluate the real-time state index of the server port; and a gradient analysis model is constructed to divide the real-time state index of the server port into gradient levels.

[0009] Based on the gradient level division data of the real-time status index of the server port, state equilibrium index analysis is performed on each gradient level, and fluctuation analysis is performed in combination with the real-time status index of the server port in each gradient level to obtain the fluctuation range of the real-time status index of each server port.

[0010] A performance fluctuation impact function is established to fit the real-time performance fluctuation impact curve of each server port, and the real-time performance fluctuation synchronization rate between server ports is analyzed to determine and output the optimal server interconnection group.

[0011] Furthermore, the system monitors the operational status of server ports in real time through a cloud network platform, locates online server ports to determine port sequences, and synchronously records the real-time operational status data of online server ports to construct a real-time status matrix sequence for the corresponding server ports.

[0012] Among them, the cloud network platform is a cloud service platform built by interconnecting several server ports through the cloud network, which is used to monitor the operating status of each server port in the cloud network in real time.

[0013] The port sequence is the cloud network identity code corresponding to each server port;

[0014] The real-time status matrix sequence is a set of real-time status matrices corresponding to online server ports, which includes the real-time status matrix of each online server port; the real-time status matrix is ​​used to record the operating status data of the server port at the current moment.

[0015] Furthermore, the real-time status matrix of the online server port is retrieved from the cloud platform to determine the current operating status data of the corresponding server port, and the real-time status index Rts(n) of the server port is evaluated; the evaluation calculation is as follows:

[0016] ;

[0017] Where Rts(n) is the real-time status index of server port n; E(m,n) is the running status data value of the m-th type of server port n; E(m,n) max Let n be the historical maximum value of the m-th type of running status data for server port n; m is the number of running status data types for server port n; n is the number of server ports.

[0018] Establish a gradient analysis model, import the real-time status index of each server port into the gradient analysis model, and determine the gradient level division data of the real-time status index of each server port.

[0019] The gradient level partitioning steps of the gradient analysis model are as follows:

[0020] T1. Collect and coordinate the real-time status indices of each server port simultaneously to construct a real-time status index set; wherein, the collection and coordination of the data set refers to constructing a data set of the real-time status indices of each server port.

[0021] T2. In the real-time status index set, the real-time status indices of each server port are sorted in descending order, and the percentage difference rate Pdr(n,n+1) of adjacent real-time status indices after processing is analyzed; the calculation is as follows:

[0022] ;

[0023] Wherein, Pdr(n,n+1) is the percentage difference rate of the real-time status index of adjacent server ports n and n+1; Rts(n) and Rts(n+1) are the real-time status indices of adjacent server ports n and n+1.

[0024] The descending order processing involves comparing the real-time status indices of each server port in the real-time status index set and sorting them from largest to smallest based on the comparison results.

[0025] T3. By constructing interval difference positions between adjacent real-time state indices, the percentage difference rate of adjacent real-time state indices is filled; set the comparison parameter Px, and perform comparison analysis on the percentage difference rate Pdr(n,n+1) filled in the interval difference positions in turn.

[0026] T4. When the comparison analysis shows that Pdr(n,n+1)≤Px, the comparison and judgment of the proportion difference rate of the next interval difference position continues until Pdr(n,n+1)>Px. Then, the real-time state index before the current interval difference position is divided into the same gradient level, denoted as the i-th gradient level; i is the gradient level number.

[0027] It should be noted that the spatial distribution of the interval difference position depends on the arrangement of the real-time state indexes after the real-time state indexes have been processed in descending order. If the processed real-time state indexes are arranged in descending order horizontally, the real-time state index before the interval difference position corresponds to the real-time state index to its left; if the processed real-time state indexes are arranged in descending order vertically, the real-time state index before the interval difference position corresponds to the real-time state index above it.

[0028] T5. Repeat step T4 for the remaining real-time state indices that have not been divided into gradient levels, until the gradient levels of the real-time state indices in the set of real-time state indices are completed.

[0029] Furthermore, based on the gradient level division results of the real-time state index of each server port, the real-time state index of the server port in each gradient level is extracted, and the gradient level is then evaluated using the state equilibrium index Sed. i The analysis and calculation are as follows:

[0030] ;

[0031] Among them, Sed i Rts(n,i) is the state equilibrium index of gradient level i; n(i) is the number of real-time state indices of server ports in gradient level i; Rts(n,i) is the real-time state index of server port n in gradient level i; Rts(ave,i) is the mean of the real-time state indices of server ports in gradient level i.

[0032] Based on the state equilibrium index of each gradient level, the fluctuation analysis of the real-time state index of the server port in each gradient level is performed; by determining the distribution of the real-time state index of the server port in each gradient level, the fluctuation range of the real-time state index of each server port [vt(n,i)] is analyzed. min vt(n,i) max The calculation is as follows:

[0033] ;

[0034] Where, vt(n,i) min and vt(n,i) max Let Rts(n,i) be the minimum and maximum volatility values ​​of the real-time state index for server port n in gradient level i. min and Rts(n,i) max These are the minimum and maximum values ​​of the real-time status index of the server port in the i-th gradient level;

[0035] It should be noted that the analysis of the real-time status index of the server port in each gradient level is determined. The purpose is to obtain the distribution range of the real-time status index of the server port in the corresponding gradient level, so as to determine the maximum and minimum values ​​of the real-time status index in the gradient level for subsequent analysis.

[0036] Furthermore, a performance fluctuation impact function is established. The real-time state index fluctuation range of the server port is input into the performance fluctuation impact function for curve mapping to obtain the real-time performance fluctuation impact curve for each server port; wherein, the expression of the performance fluctuation function is as follows:

[0037] ;

[0038] Where Y(n,i) represents the degree of impact of real-time performance fluctuations on server port n in gradient level i; vt(n,i) represents the real-time state exponential volatility of server port n in gradient level i, and its value range is the range of real-time state exponential volatility of the server port; Sed i The state equilibrium index for the i-th gradient level is represented by k; k is the volatility coefficient.

[0039] The real-time performance fluctuation curves of each server port are coordinated, mapped to the same coordinate system, and any server port is taken as the target server port. The real-time performance fluctuation synchronization rate of the target server port and the remaining server ports is analyzed.

[0040] For each server port, the curvature of the real-time performance fluctuation curve within the real-time state index fluctuation range is determined, the maximum curvature point on the real-time performance fluctuation curve is obtained, and the performance fluctuation vector is constructed based on the origin and the maximum curvature point.

[0041] The degree of overlap between the real-time performance fluctuation curve of the target server port and the real-time performance fluctuation curve of the remaining server ports is determined by analyzing the curve segment before the maximum curvature point. Combined with the performance fluctuation vectors of the target server port and the remaining server ports, the synchronization rate of their real-time performance fluctuations is analyzed, and calculated as follows:

[0042] ;

[0043] Where Spf(p,q) is the real-time performance fluctuation synchronization rate between the target server port labeled p and the remaining server port labeled q; Y(p,cmax) is the sum of curve values ​​of the real-time performance fluctuation curve of the target server port labeled p before the maximum curvature point; Y(q,cmax) is the sum of curve values ​​of the real-time performance fluctuation curve of the remaining server port labeled q before the maximum curvature point; α(p,q) is the angle between the performance fluctuation vectors of the target server port labeled p and the remaining server port labeled q; p and q are the performance fluctuation vectors of the target server port labeled p and the remaining server port labeled q, respectively.

[0044] Based on the real-time performance fluctuation synchronization rate analysis data of the target server port and the remaining server ports, a synchronization judgment parameter Spc is set to judge the real-time performance fluctuation synchronization.

[0045] If Spf(p,q)≥Spc, then it is determined that the real-time performance fluctuations of the target server port labeled p and the remaining server ports labeled q are synchronized.

[0046] If Spf(p,q) < Sp, then it is determined that the real-time performance fluctuations of the target server port labeled p and the remaining server ports labeled q are out of sync.

[0047] Based on the real-time performance fluctuation synchronization judgment results of the target server port and the remaining server ports, the server ports judged to be in real-time performance fluctuation synchronization are constructed into server interconnection groups. The server ports in each server interconnection group are traversed to ensure overlap. Server interconnection groups with the same server ports are merged and constructed, and the best server interconnection group is output.

[0048] A cloud computing-based multi-terminal server data interconnection and management system:

[0049] The system includes a server monitoring unit, a server status assessment unit, a gradient model analysis unit, a gradient-level status analysis unit, a server status fluctuation analysis unit, a performance fluctuation curve fitting unit, and an optimal server interconnection group output unit.

[0050] Furthermore, the server monitoring unit is used to monitor the operating status of server ports in the cloud network platform and record the real-time operating status data of online server ports;

[0051] The server status assessment unit retrieves the real-time status matrix of the online server port, determines the operating status data of the corresponding server port at the current moment, and assesses the real-time status index of the server port.

[0052] The gradient model analysis unit establishes a gradient analysis model, imports the real-time status index of each server port into the gradient analysis model, and determines the gradient level division data of the real-time status index of each server port.

[0053] Furthermore, the gradient level state analysis unit extracts the real-time state index of the server port in each gradient level according to the gradient level division result of the real-time state index of each server port, and performs state equilibrium index analysis on the gradient level.

[0054] The server status fluctuation analysis unit performs fluctuation analysis on the real-time status index of the server port in each gradient level based on the status equilibrium index of each gradient level; it analyzes the fluctuation range of the real-time status index of each server port by determining the distribution of the real-time status index of the server port in each gradient level.

[0055] The performance fluctuation curve fitting unit establishes a performance fluctuation impact function, inputs the real-time state index fluctuation range of the server port into the performance fluctuation impact function for curve mapping, so as to obtain the real-time performance fluctuation impact curve of each server port.

[0056] The optimal server interconnection group output unit coordinates the real-time performance fluctuation curves of each server port, maps them to the same coordinate system, and takes any server port as the target server port to perform real-time performance fluctuation synchronization rate analysis between the target server port and the remaining server ports.

[0057] Based on the analysis data of the real-time performance fluctuation synchronization rate between the target server port and the remaining server ports, synchronization judgment parameters are set to judge the real-time performance fluctuation synchronization. The server ports judged to be in real-time performance fluctuation synchronization are constructed into server interconnection groups. The server ports in each server interconnection group are traversed to ensure overlap. Server interconnection groups with the same server ports are merged and constructed, and the best server interconnection group is output.

[0058] Compared with the prior art, the beneficial effects of the present invention are:

[0059] This invention combines cloud platform monitoring to obtain real-time online server ports, synchronously record and evaluate the operational status of each server port; it constructs a gradient model to divide the operational status of each server into gradient levels, analyzes and obtains gradient level status indicators, and determines the fluctuation range of the server's real-time status index; it constructs a performance fluctuation impact function to fit the performance fluctuation impact curve of the server port, and outputs the optimal server interconnection group by analyzing the real-time performance fluctuation synchronization rate between each server port; this invention improves the data processing efficiency and stress resistance of servers in high-concurrency scenarios by mining the time-sensitivity correlation of the real-time operational status of server ports to construct data interconnection groups for server ports. Attached Figure Description

[0060] Figure 1 This is a flowchart illustrating a multi-terminal server data interconnection and management method based on cloud computing according to the present invention. Detailed Implementation

[0061] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0062] Example 1: As Figure 1 As shown, the present invention provides a technical solution:

[0063] A cloud computing-based method for managing and controlling data interconnection between multiple servers, comprising the following steps:

[0064] The online server port is determined based on the cloud platform, the server port's operating status data is recorded synchronously, and a real-time status matrix sequence is constructed.

[0065] The real-time state matrix sequence is retrieved to evaluate the real-time state index of the server port; and a gradient analysis model is constructed to divide the real-time state index of the server port into gradient levels.

[0066] Based on the gradient level division data of the real-time status index of the server port, state equilibrium index analysis is performed on each gradient level, and fluctuation analysis is performed in combination with the real-time status index of the server port in each gradient level to obtain the fluctuation range of the real-time status index of each server port.

[0067] A performance fluctuation impact function is established to fit the real-time performance fluctuation impact curve of each server port, and the real-time performance fluctuation synchronization rate between server ports is analyzed to determine and output the optimal server interconnection group.

[0068] Furthermore, the system monitors the operational status of server ports in real time through a cloud network platform, locates online server ports to determine port sequences, and synchronously records the real-time operational status data of online server ports to construct a real-time status matrix sequence for the corresponding server ports.

[0069] Among them, the cloud network platform is a cloud service platform built by interconnecting several server ports through the cloud network, which is used to monitor the operating status of each server port in the cloud network in real time.

[0070] Among them, the port sequence is the cloud network identity code corresponding to each server port;

[0071] The real-time status matrix sequence is a set of real-time status matrices for the corresponding online server ports, which contains the real-time status matrix of each online server port; the real-time status matrix is ​​used to record the operating status data of the server port at the current moment.

[0072] In this embodiment, the port sequence of the server ports is represented by a number. For example, if there are 10 server ports in the cloud network, the port sequence of each server port is assigned as 1, 2, 3, ... 10 according to the number.

[0073] It should be noted that the running status data includes, but is not limited to, the CPU utilization rate and memory utilization rate of the server port; therefore, the real-time status matrix of the server port can be constructed in the form of 2×m, where 2 is the number of rows in the matrix and m is the number of columns in the matrix; and m corresponds to the number of types of real-time running status data of the server port recorded in the real-time status matrix; if the number of data types of real-time running status data of the server port recorded m is 5, then the corresponding real-time status matrix is ​​in the format of 2×5.

[0074] Furthermore, the real-time status matrix of the online server port is retrieved from the cloud platform to determine the current operating status data of the corresponding server port, and the real-time status index Rts(n) of the server port is evaluated; the evaluation calculation is as follows:

[0075] ;

[0076] Where Rts(n) is the real-time status index of server port n; E(m,n) is the running status data value of the m-th type of server port n; E(m,n) maxLet n be the historical maximum value of the m-th type of running status data for server port n; m is the number of running status data types for server port n; n is the number of server ports.

[0077] Establish a gradient analysis model, import the real-time status index of each server port into the gradient analysis model, and determine the gradient level division data of the real-time status index of each server port.

[0078] The gradient level partitioning steps of the gradient analysis model are as follows:

[0079] T1. Collect and coordinate the real-time status indices of each server port simultaneously to construct a real-time status index set; where data collection coordination involves constructing a data set of the real-time status indices of each server port.

[0080] T2. In the real-time status index set, the real-time status indices of each server port are sorted in descending order, and the percentage difference rate Pdr(n,n+1) of adjacent real-time status indices after processing is analyzed; the calculation is as follows:

[0081] ;

[0082] Wherein, Pdr(n,n+1) is the percentage difference rate of the real-time status index of adjacent server ports n and n+1; Rts(n) and Rts(n+1) are the real-time status indices of adjacent server ports n and n+1.

[0083] The descending order processing involves comparing the real-time status indices of each server port in the real-time status index set and sorting them from largest to smallest based on the comparison results.

[0084] T3. By constructing interval difference positions between adjacent real-time state indices, the percentage difference rate of adjacent real-time state indices is filled; set the comparison parameter Px, and perform comparison analysis on the percentage difference rate Pdr(n,n+1) filled in the interval difference positions in turn.

[0085] T4. When the comparison analysis shows that Pdr(n,n+1)≤Px, the comparison and judgment of the proportion difference rate of the next interval difference position continues until Pdr(n,n+1)>Px. Then, the real-time state index before the current interval difference position is divided into the same gradient level, denoted as the i-th gradient level; i is the gradient level number.

[0086] It should be noted that the spatial distribution of the interval difference position depends on the arrangement of the real-time state indexes after the real-time state indexes have been processed in descending order. If the processed real-time state indexes are arranged in descending order horizontally, the real-time state index before the interval difference position corresponds to the real-time state index to its left; if the processed real-time state indexes are arranged in descending order vertically, the real-time state index before the interval difference position corresponds to the real-time state index above it.

[0087] T5. Repeat step T4 for the remaining real-time state indices that have not been divided into gradient levels until the real-time state indices in the set of real-time state indices are divided into gradient levels.

[0088] It should be noted that if, during steps T4 and T5, there is no case where Pdr(n,n+1)>Px during the comparison analysis of the proportion difference rate in the real-time state index set, then the comparison analysis will continue until all real-time state indices in the real-time state index set have been compared and analyzed. The real-time state indices that have been compared but not yet divided into gradient levels will then be divided into the same gradient level; the resulting gradient level index i≥1. If the proportion difference rate between adjacent real-time state indices corresponding to the interval difference position in the real-time state index set is less than the comparison parameter, then all real-time state indices in the real-time state index set will be divided into the same gradient level; or if, after dividing into the first gradient level, the proportion difference rate between the remaining real-time state indices is less than the comparison parameter, then the remaining real-time state indices will be divided into the second gradient level; the rest are the same as above.

[0089] Furthermore, based on the gradient level division results of the real-time state index of each server port, the real-time state index of the server port in each gradient level is extracted, and the gradient level is then evaluated using the state equilibrium index Sed. i The analysis and calculation are as follows:

[0090] ;

[0091] Among them, Sed i Rts(n,i) is the state equilibrium index of gradient level i; n(i) is the number of real-time state indices of server ports in gradient level i; Rts(n,i) is the real-time state index of server port n in gradient level i; Rts(ave,i) is the mean of the real-time state indices of server ports in gradient level i.

[0092] Based on the state equilibrium index of each gradient level, the fluctuation analysis of the real-time state index of the server port in each gradient level is performed; by determining the distribution of the real-time state index of the server port in each gradient level, the fluctuation range of the real-time state index of each server port [vt(n,i)] is analyzed. min vt(n,i) maxThe calculation is as follows:

[0093] ;

[0094] Where, vt(n,i) min and vt(n,i) max Let Rts(n,i) be the minimum and maximum volatility values ​​of the real-time state index for server port n in gradient level i. min and Rts(n,i) max These are the minimum and maximum values ​​of the real-time status index of the server port in the i-th gradient level;

[0095] It should be noted that the analysis of the real-time status index of the server port in each gradient level is determined. The purpose is to obtain the distribution range of the real-time status index of the server port in the corresponding gradient level, so as to determine the maximum and minimum values ​​of the real-time status index in the gradient level for subsequent analysis.

[0096] In this embodiment, the volatility analysis of the real-time state index of each server port in the gradient level is to analyze the fluctuation of the real-time state index of the server port in the corresponding gradient level; it is based on the result of gradient level division and performs fluctuation analysis within the real-time state index interval in the gradient level.

[0097] Specifically, within a certain gradient level, the real-time state index of any server port is selected. The difference between the current real-time state index and the state equilibrium index of the gradient level is used to perform fluctuation analysis on the maximum and minimum values ​​of the real-time state index within the gradient level. This is expressed as the fluctuation difference between the current real-time state index and the state equilibrium index of the gradient level, and the fluctuation rate is calculated with the maximum and minimum values ​​that the real-time state index within the gradient level can reach. This is used to determine the upper and lower limits of the fluctuation of the real-time state index of the currently selected server port.

[0098] Furthermore, a performance fluctuation impact function is established. The real-time state index fluctuation range of the server port is input into the performance fluctuation impact function for curve mapping to obtain the real-time performance fluctuation impact curve for each server port. The expression for the performance fluctuation function is as follows:

[0099] ;

[0100] Where Y(n,i) represents the degree of impact of real-time performance fluctuations on server port n in gradient level i; vt(n,i) represents the real-time state exponential volatility of server port n in gradient level i, and its value range is the range of real-time state exponential volatility of the server port; Sed iσ is the state equilibrium index of gradient level i; k is the fluctuation coefficient; in this embodiment, its value is k=Rts(σ,i) / Rts(ave,i); where Rts(σ,i) is the standard deviation of the real-time state index of the server port in gradient level i.

[0101] Among them, by fitting the performance curve to the volatility range of the real-time status index of the server port, it is used to represent the change in the degree of influence of different volatility of the real-time status index of the corresponding server port on the performance of the server port.

[0102] The real-time performance fluctuation curves of each server port are coordinated, mapped to the same coordinate system, and any server port is taken as the target server port. The real-time performance fluctuation synchronization rate of the target server port and the remaining server ports is analyzed.

[0103] For each server port, the curvature of the real-time performance fluctuation curve within the real-time state index fluctuation range is determined, the maximum curvature point on the real-time performance fluctuation curve is obtained, and a performance fluctuation vector is constructed based on the origin and the maximum curvature point; wherein the vector direction is from the origin to the maximum curvature point.

[0104] The degree of overlap between the real-time performance fluctuation curve of the target server port and the real-time performance fluctuation curve of the remaining server ports is determined by analyzing the curve segment before the maximum curvature point. Combined with the performance fluctuation vectors of the target server port and the remaining server ports, the synchronization rate of their real-time performance fluctuations is analyzed, and calculated as follows:

[0105] ;

[0106] Where Spf(p,q) is the real-time performance fluctuation synchronization rate between the target server port labeled p and the remaining server port labeled q; Y(p,cmax) is the sum of curve values ​​of the real-time performance fluctuation curve of the target server port labeled p before the maximum curvature point; Y(q,cmax) is the sum of curve values ​​of the real-time performance fluctuation curve of the remaining server port labeled q before the maximum curvature point; α(p,q) is the angle between the performance fluctuation vectors of the target server port labeled p and the remaining server port labeled q; p and q are the performance fluctuation vectors of the target server port labeled p and the remaining server port labeled q, respectively; where p and q have different values, and the value range of q is [1,n]; the value range of q is [1,n-1].

[0107] Based on the real-time performance fluctuation synchronization rate analysis data of the target server port and the remaining server ports, a synchronization judgment parameter Spc is set to judge the real-time performance fluctuation synchronization.

[0108] If Spf(p,q)≥Spc, then it is determined that the real-time performance fluctuations of the target server port labeled p and the remaining server ports labeled q are synchronized.

[0109] If Spf(p,q) < Sp, then it is determined that the real-time performance fluctuations of the target server port labeled p and the remaining server ports labeled q are out of sync.

[0110] Based on the real-time performance fluctuation synchronization judgment results of the target server port and the remaining server ports, the server ports judged to be in real-time performance fluctuation synchronization are constructed into server interconnection groups. The server ports in each server interconnection group are traversed repeatedly. Server interconnection groups with the same server ports are merged and constructed, and the best server interconnection group is output.

[0111] In this embodiment, it should be noted that the analysis of real-time performance fluctuation synchronization rate is performed by combining the target server port with the remaining server ports one by one. When selecting different target server ports in the future, it is not necessary to perform secondary analysis on the already analyzed combinations of remaining server ports, thus avoiding redundant calculations and wasting computing resources.

[0112] Secondly, when performing fusion analysis on server interconnection groups, it is necessary to determine whether there are identical server ports in each server interconnection group. For example, if there are two server interconnection groups labeled (1, 2) and (2, 5), then both of them have a server port labeled 2. In this case, the two server interconnection groups need to be merged to output the optimal server interconnection group (1, 2, 5).

[0113] Among them, data interaction between servers in the best server interconnection group is prioritized to avoid high data interaction scenarios on individual server ports, which could cause data backlog, resulting in server port data interaction delays and paralysis.

[0114] Example 2: The present invention provides another technical solution:

[0115] A cloud computing-based multi-terminal server data interconnection and management system:

[0116] The system includes a server monitoring unit, a server status assessment unit, a gradient model analysis unit, a gradient-level status analysis unit, a server status fluctuation analysis unit, a performance fluctuation curve fitting unit, and an optimal server interconnection group output unit.

[0117] Furthermore, the server monitoring unit is used to monitor the operating status of server ports in the cloud network platform and record real-time operating status data of online server ports;

[0118] The server status assessment unit retrieves the real-time status matrix of the online server port, determines the operating status data of the corresponding server port at the current moment, and evaluates the real-time status index of the server port.

[0119] The gradient model analysis unit establishes a gradient analysis model, imports the real-time status index of each server port into the gradient analysis model, and determines the gradient level division data of the real-time status index of each server port.

[0120] Furthermore, the gradient-level state analysis unit extracts the real-time state index of the server port in each gradient level based on the gradient level division results of the real-time state index of each server port, and performs state equilibrium index analysis on the gradient level.

[0121] The server status fluctuation analysis unit performs fluctuation analysis on the real-time status index of server ports in each gradient level based on the status equilibrium index of each gradient level. It analyzes the fluctuation range of the real-time status index of each server port by determining the distribution of the real-time status index of each gradient level.

[0122] The performance fluctuation curve fitting unit establishes a performance fluctuation impact function. The real-time status index fluctuation range of the server port is input into the performance fluctuation impact function for curve mapping to obtain the real-time performance fluctuation impact curve of each server port.

[0123] The optimal server interconnection group output unit coordinates the real-time performance fluctuation curves of each server port, maps them to the same coordinate system, and takes any server port as the target server port to perform real-time performance fluctuation synchronization rate analysis between the target server port and the remaining server ports.

[0124] Based on the analysis data of the real-time performance fluctuation synchronization rate between the target server port and the remaining server ports, synchronization judgment parameters are set to judge the real-time performance fluctuation synchronization. The server ports judged to be in real-time performance fluctuation synchronization are constructed into server interconnection groups. The server ports in each server interconnection group are traversed to ensure overlap. Server interconnection groups with the same server ports are merged and constructed, and the best server interconnection group is output.

[0125] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for managing and controlling data interconnection between multiple servers based on cloud computing, characterized in that: The online server port is determined based on the cloud platform, the server port's operating status data is recorded synchronously, and a real-time status matrix sequence is constructed. The real-time status index of the server port is evaluated by retrieving the real-time status matrix sequence. Furthermore, a gradient analysis model was constructed to divide the real-time status index of the server port into gradient levels; Based on the gradient level division data of the real-time status index of the server port, state equilibrium index analysis is performed on each gradient level, and fluctuation analysis is performed in combination with the real-time status index of the server port in each gradient level to obtain the fluctuation range of the real-time status index of each server port. A performance fluctuation impact function is established to fit the real-time performance fluctuation impact curve of each server port, and the real-time performance fluctuation synchronization rate between server ports is analyzed to determine and output the optimal server interconnection group.

2. The method for managing and controlling multi-terminal server data interconnection based on cloud computing according to claim 1, characterized in that: Establish a gradient analysis model, import the real-time status index of each server port into the gradient analysis model, and determine the gradient level division data of the real-time status index of each server port. The gradient level partitioning steps of the gradient analysis model are as follows: T1. Collect and coordinate the real-time status indices of each server port at the same time to construct a real-time status index set. T2. In the real-time status index set, the real-time status indices of each server port are sorted in descending order, and the percentage difference rate Pdr(n,n+1) of adjacent real-time status indices after processing is analyzed; the calculation is as follows: ； Wherein, Pdr(n,n+1) is the percentage difference rate of the real-time status index of adjacent server ports n and n+1; Rts(n) and Rts(n+1) are the real-time status indices of adjacent server ports n and n+1. T3. By constructing interval difference positions between adjacent real-time state indices, the percentage difference rate of adjacent real-time state indices is filled; set the comparison parameter Px, and perform comparison analysis on the percentage difference rate Pdr(n,n+1) filled in the interval difference positions in turn. T4. When the comparison analysis shows that Pdr(n,n+1)≤Px, the comparison and judgment of the proportion difference rate of the next interval difference position continues until Pdr(n,n+1)>Px. Then, the real-time state index before the current interval difference position is divided into the same gradient level, denoted as the i-th gradient level; i is the gradient level number. T5. Repeat step T4 for the remaining real-time state indices that have not been divided into gradient levels, until the gradient levels of the real-time state indices in the set of real-time state indices are completed.

3. The method for managing and controlling multi-terminal server data interconnection based on cloud computing according to claim 1, characterized in that: Based on the gradient level division results of the real-time state index of each server port, the real-time state index of the server port in each gradient level is extracted, and the state equilibrium index Sed is applied to the gradient level. i The analysis and calculation are as follows: ； Among them, Sed i Rts(n,i) is the state equilibrium index of gradient level i; n(i) is the number of real-time state indices of server ports in gradient level i; Rts(n,i) is the real-time state index of server port n in gradient level i; Rts(ave,i) is the mean of the real-time state index of server ports in gradient level i. Based on the state equilibrium index of each gradient level, the fluctuation analysis of the real-time state index of the server port in each gradient level is performed; by determining the distribution of the real-time state index of the server port in each gradient level, the fluctuation range of the real-time state index of each server port [vt(n,i)] is analyzed. min vt(n,i) max The calculation is as follows: ； Where, vt(n,i) min and vt(n,i) max Let Rts(n,i) be the minimum and maximum volatility values ​​of the real-time state index for server port n in gradient level i. min and Rts(n,i) max These are the minimum and maximum values ​​of the real-time status index of the server port in gradient level i.

4. The method for managing and controlling multi-terminal server data interconnection based on cloud computing according to claim 1, characterized in that: A performance fluctuation impact function is established. The real-time state index fluctuation range of the server port is input into the performance fluctuation impact function for curve mapping to obtain the real-time performance fluctuation impact curve for each server port. The expression of the performance fluctuation function is as follows: ； Where Y(n,i) represents the degree of impact of real-time performance fluctuations on server port n in gradient level i; vt(n,i) represents the real-time state exponential volatility of server port n in gradient level i, and its value range is the range of real-time state exponential volatility of the server port; Sed i The state equilibrium index for the i-th gradient level is represented by k; k is the volatility coefficient. The real-time performance fluctuation curves of each server port are coordinated, mapped to the same coordinate system, and any server port is taken as the target server port. The real-time performance fluctuation synchronization rate of the target server port and the remaining server ports is analyzed.

5. The method for managing and controlling multi-terminal server data interconnection based on cloud computing according to claim 1, characterized in that: For each server port, the curvature of the real-time performance fluctuation curve within the real-time state index fluctuation range is determined, the maximum curvature point on the real-time performance fluctuation curve is obtained, and the performance fluctuation vector is constructed based on the origin and the maximum curvature point. The degree of overlap between the real-time performance fluctuation curve of the target server port and the real-time performance fluctuation curve of the remaining server ports is determined by analyzing the curve segment before the maximum curvature point. Combined with the performance fluctuation vectors of the target server port and the remaining server ports, the synchronization rate of their real-time performance fluctuations is analyzed, and calculated as follows: ； Where Spf(p,q) is the real-time performance fluctuation synchronization rate between the target server port labeled p and the remaining server port labeled q; Y(p,cmax) is the sum of curve values ​​of the real-time performance fluctuation curve of the target server port labeled p before the maximum curvature point; Y(q,cmax) is the sum of curve values ​​of the real-time performance fluctuation curve of the remaining server port labeled q before the maximum curvature point; α(p,q) is the angle between the performance fluctuation vectors of the target server port labeled p and the remaining server port labeled q; p and q are the performance fluctuation vectors of the target server port labeled p and the remaining server port labeled q, respectively.

6. The method for managing and controlling multi-terminal server data interconnection based on cloud computing according to claim 5, characterized in that: Based on the real-time performance fluctuation synchronization rate analysis data of the target server port and the remaining server ports, a synchronization judgment parameter Spc is set to judge the real-time performance fluctuation synchronization. If Spf(p,q)≥Spc, then it is determined that the real-time performance fluctuations of the target server port labeled p and the remaining server ports labeled q are synchronized. If Spf(p,q) < Sp, then it is determined that the real-time performance fluctuations of the target server port labeled p and the remaining server ports labeled q are out of sync. Based on the real-time performance fluctuation synchronization judgment results of the target server port and the remaining server ports, the server ports judged to be in real-time performance fluctuation synchronization are constructed into server interconnection groups. The server ports in each server interconnection group are traversed to ensure overlap. Server interconnection groups with the same server ports are merged and constructed, and the best server interconnection group is output.

7. The method for managing and controlling multi-terminal server data interconnection based on cloud computing according to claim 1, characterized in that: The system monitors the operational status of server ports in real time through a cloud network platform, locates online server ports to determine port sequences, and synchronously records real-time operational status data of online server ports to construct a real-time status matrix sequence for the corresponding server ports.

8. The method for managing and controlling multi-terminal server data interconnection based on cloud computing according to claim 1, characterized in that: The real-time status matrix of the online server port is retrieved from the cloud platform to determine the current operating status data of the corresponding server port, and the real-time status index Rts(n) of the server port is evaluated; the evaluation calculation is as follows: ； Where Rts(n) is the real-time status index of server port n; E(m,n) is the running status data value of the m-th type of server port n; E(m,n) max The historical maximum value of the running status data of the m-th type for server port number n; m is the number of running status data types for server port; n is the number of server ports.

9. A system for executing a cloud computing-based multi-terminal server data interconnection and management method according to any one of claims 1-8, characterized in that: The system includes a server monitoring unit, a server status assessment unit, a gradient model analysis unit, a gradient-level status analysis unit, a server status fluctuation analysis unit, a performance fluctuation curve fitting unit, and an optimal server interconnection group output unit. The server monitoring unit is used to monitor the operating status of server ports in the cloud network platform and record the real-time operating status data of online server ports. The server status assessment unit retrieves the real-time status matrix of the online server port, determines the operating status data of the corresponding server port at the current moment, and assesses the real-time status index of the server port. The gradient model analysis unit establishes a gradient analysis model, imports the real-time status index of each server port into the gradient analysis model, and determines the gradient level division data of the real-time status index of each server port.

10. The system according to claim 9, characterized in that: The gradient level state analysis unit extracts the real-time state index of the server port in each gradient level according to the gradient level division result of the real-time state index of each server port, and performs state equilibrium index analysis on the gradient level. The server status fluctuation analysis unit performs fluctuation analysis on the real-time status index of the server port in each gradient level based on the status equilibrium index of each gradient level; it analyzes the fluctuation range of the real-time status index of each server port by determining the distribution of the real-time status index of the server port in each gradient level. The performance fluctuation curve fitting unit establishes a performance fluctuation impact function, inputs the real-time state index fluctuation range of the server port into the performance fluctuation impact function for curve mapping, so as to obtain the real-time performance fluctuation impact curve of each server port. The optimal server interconnection group output unit coordinates the real-time performance fluctuation curves of each server port, maps them to the same coordinate system, and takes any server port as the target server port to perform real-time performance fluctuation synchronization rate analysis between the target server port and the remaining server ports. Based on the analysis data of the real-time performance fluctuation synchronization rate between the target server port and the remaining server ports, synchronization judgment parameters are set to judge the real-time performance fluctuation synchronization. The server ports judged to be in real-time performance fluctuation synchronization are constructed into server interconnection groups. The server ports in each server interconnection group are traversed to ensure overlap. Server interconnection groups with the same server ports are merged and constructed, and the best server interconnection group is output.

Images