Network performance real-time monitoring method and system based on micro-service platform

Abstract

The invention discloses a network performance real-time monitoring method and system based on a micro-service platform, and relates to the technical field of power grid monitoring early warning, and the method comprises the steps: collecting equipment data in real time, carrying out the preprocessing of the collected data, inputting the preprocessed data into a data analysis model, and carrying out the feature extraction and mode recognition, starting a monitoring and early warning mechanism, tracking an analysis result in real time, triggering a strategy adjustment algorithm according to an instruction output by an analysis model, executing strategy adjustment among micro-services through cooperative work, verifying interaction and response among the services through testing, and entering a real-time monitoring state; and periodic maintenance and updating work is arranged through a predictive maintenance and fault prediction model. According to the invention, the problems of low data processing capability, imperfect early warning mechanism and poor micro-service cooperative work capability in the real-time network monitoring process among micro-services are solved, and the efficiency and accuracy of network performance monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid monitoring and early warning, and in particular to a method and system for real-time monitoring of network performance based on a microservice platform. Background Art

[0002] With the rapid development of Internet technology, network performance monitoring has become an important means to ensure stable network operation and improve user experience. Traditional network performance monitoring methods often rely on manual operations, which are not only inefficient but also unable to respond to changes in network performance in real time. In order to solve these problems, in recent years, methods and systems for real-time monitoring of network performance based on microservice platforms have emerged.

[0003] The existing network performance monitoring technology mainly has the following deficiencies: insufficient data processing capacity, imperfect early warning mechanism, insufficient microservice collaboration, and insufficient predictive maintenance and fault prediction. In view of the above deficiencies, the present invention provides a method and system for real-time monitoring of network performance based on a microservice platform. The method collects device data in real time, preprocesses the collected data, and inputs the preprocessed data into a data analysis model for feature extraction and pattern recognition; starts the monitoring and early warning mechanism, tracks the analysis results in real time, and triggers the policy adjustment algorithm according to the instructions output by the analysis model, and the microservices perform policy adjustments through collaborative work; verifies the interaction and response between services through testing, enters the real-time monitoring state, and arranges periodic maintenance and update work through predictive maintenance and fault prediction models. Summary of the invention

[0004] In view of the above-mentioned existing problems, the present invention provides a method and system for real-time monitoring of network performance based on a microservice platform, which is used to solve the problems of poor data processing capability, imperfect early warning mechanism and weak working coordination between microservices in existing network performance monitoring technology.

[0005] In order to solve the above technical problems, a method for real-time monitoring of network performance based on a microservice platform is proposed, including:

[0006] Collect first device data in real time, pre-process the first data to obtain second data, and input the second data into the third analysis model for identification; start the fourth early warning mechanism, track the analysis results in real time, and execute policy adjustments according to the instructions output by the third analysis model; verify the interaction and response between services through testing, enter the real-time monitoring state, and arrange periodic maintenance and update work through the fifth maintenance model.

[0007] As a preferred solution of the method for real-time monitoring of network performance based on a microservice platform described in the present invention, the collection of first device data includes real-time collection of current data, voltage data, power data, frequency data, temperature data, environmental data, device status data, load characteristic data, historical fault data and operation log data of the device.

[0008] As a preferred solution of the method for real-time monitoring of network performance based on a microservice platform described in the present invention, wherein: the preprocessing of the first data to obtain the second data includes preprocessing the collected data using an enhanced preprocessing algorithm.

[0009] The enhanced preprocessing algorithm includes data cleaning, feature selection, feature conversion, data enhancement and dimensionality reduction.

[0010] The data cleaning includes removing non-numeric data and processing missing values; the feature selection includes correlation analysis and recursive feature elimination; and the data conversion includes standardization and normalization.

[0011] As a preferred solution of the method for real-time monitoring of network performance based on a microservice platform described in the present invention, the input of the second data into the third analysis model for identification includes loading the second data into the data analysis model, extracting features using an algorithm, selecting an analysis model according to properties, training the data analysis model using linear regression, analyzing data loss and gradient descent, and performing pattern recognition.

[0012] The data analysis model is used as the third analysis model to perform feature extraction and pattern recognition.

[0013] As a preferred solution of the method for real-time monitoring of network performance based on a microservice platform described in the present invention, the fourth early warning mechanism includes performing statistical analysis using the features output by the third analysis model and performing anomaly detection using a machine learning model, and immediately issuing an alarm when an abnormal situation occurs.

[0014] As a preferred solution of the method for real-time monitoring of network performance based on a microservice platform described in the present invention, wherein: the execution strategy adjustment includes real-time tracking and analysis according to the results of the fourth early warning mechanism, and triggering a strategy adjustment algorithm according to the indication output by the third analysis model, and the microservices perform strategy adjustment through collaborative work;

[0015] The strategy adjustment algorithm formula is expressed as:

[0016]

[0017] Where D(m,f) is the policy adjustment coefficient of the mth microservice at time f, p is the total number of monitored microservices, and Qj (s) is the performance metric of the j-th microservice at time s, N j (s) is the normalized value of the performance metric of the j-th microservice at time s, h is the sigmoid function, θ j The performance threshold of the j-th microservice, q j is the performance metric decay coefficient of the j-th microservice, f 0 is the starting time point of monitoring, m is the total number of performance metrics monitored, g l (s) is the real-time value of the l-th performance metric at time s, o l is the average value of the l-th performance metric.

[0018] Among them, the value range of D(m, f) is (0, 1). When 0 < D(m, f) ≤ 0.5, it indicates that the collaborative work effect between microservices does not meet the standard, and the microservices adjust the execution strategy through collaborative work until D(m, f) returns to the normal level. When 0.5 < D(m, f) < 1, it indicates that the collaborative work effect between microservices meets the standard, and the microservices do not need to execute strategy adjustment.

[0019] As a preferred solution of the method for real-time monitoring of network performance based on a microservice platform described in the present invention, wherein: the fifth maintenance model includes verifying the interaction and response between services through testing and entering the real-time monitoring state, and arranging periodic maintenance and update work through the predictive maintenance and fault prediction model.

[0020] The verification of the interaction and response between services through testing includes determining the typical scenarios of interaction between services, designing test cases for the scenarios, simulating service requests and responses, recording the interaction time and status code, and obtaining the total test result error, which is expressed by the formula:

[0021]

[0022] Among them, T(R) is the total error of the test result, N is the number of test cases, R z is the actual response time of the z-th test case, E z is the expected response time of the z-th test case.

[0023] Among them, the fault prediction formula is:

[0024]

[0025] Among them, F(I) is the fault prediction value at time I, v is the order of time lag considered by the model, δ τ is the coefficient of the τ-th time lag term, y I-τ is the actual observed value at time I - τ, γ is the trend term coefficient, trend(I) is the trend term at time I, εI is the error term; when F(I)≥70, the prediction system fails and is immediately repaired and the equipment parameters are adjusted until the F(I) value returns to normal levels; when F(I)<70, the prediction system is in normal operation and periodic maintenance and updates are continued as planned.

[0026] Another object of the present invention is to provide a system for real-time monitoring of network performance based on a microservice platform. The present invention improves data processing capabilities, improves early warning mechanisms, enhances microservice collaboration, and improves predictive maintenance and fault prediction capabilities. The system of the present invention collects device data in real time, analyzes data and extracts features, monitors the indications of data analysis model outputs, and takes policy adjustments between microservices to solve the problems of low data processing capabilities, imperfect early warning mechanisms, and poor microservice collaboration capabilities during real-time monitoring of networks between microservices, thereby improving the efficiency and accuracy of network performance monitoring.

[0027] As a preferred solution of the system for real-time monitoring of network performance based on a microservice platform described in the present invention, it is characterized by including a data collection module, a data processing and analysis module, a monitoring and early warning module, and a maintenance and fault prediction module.

[0028] The data collection module is used to collect device data in real time.

[0029] The data processing and analysis module is used to clean and format the collected data, and perform feature extraction and pattern recognition on the pre-processed data.

[0030] The monitoring and early warning module is used to track the analysis results in real time, and trigger the strategy adjustment algorithm according to the instructions output by the analysis model. The microservices perform strategy adjustments through collaborative work.

[0031] The maintenance and fault prediction module is used to test and verify the interaction and response between services, and enter a real-time monitoring state, and arrange periodic maintenance and update work through a predictive maintenance and fault prediction model.

[0032] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of a method for real-time monitoring of network performance based on a microservice platform are implemented.

[0033] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method for real-time monitoring of network performance based on a microservice platform are implemented.

[0034] Beneficial effects of the present invention: The present invention realizes real-time monitoring, rapid response and predictive prevention of network performance by collecting device data in real time, preprocessing data, starting monitoring and early warning mechanisms, collaborative work between microservices, testing and verifying the interaction and response between services, and arranging periodic maintenance and update work steps based on predictive maintenance and fault prediction models; the unique beneficial effects of these steps include improving data processing capabilities, improving early warning mechanisms, enhancing microservice collaborative work, and improving predictive maintenance and fault prediction capabilities, thereby improving the efficiency and accuracy of network performance monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0036] Figure 1 An overall flow chart of a method for real-time monitoring of network performance based on a microservice platform provided by an embodiment of the present invention.

[0037] Figure 2 A system solution flow chart of a system for real-time monitoring of network performance based on a microservice platform provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0039] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0040] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0041] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0042] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0043] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0044] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a method for real-time monitoring of network performance based on a microservice platform, including:

[0045] S1: Collect device data in real time, pre-process the collected data, and input the pre-processed data into the data analysis model for feature extraction and pattern recognition.

[0046] The collected equipment data includes real-time collection of equipment current data, voltage data, power data, frequency data, temperature data, environmental data, equipment status data, load characteristic data, historical fault data and operation log data.

[0047] The current data includes real-time current value and current harmonic content; the voltage data includes real-time voltage value, voltage fluctuation and flicker; the power data includes active power and reactive power; the environmental data includes temperature, humidity, wind direction and wind speed; the equipment status data includes switch status and protection device action record; the historical fault data includes fault type, time and frequency.

[0048] Furthermore, the preprocessing includes preprocessing the collected data using an enhanced preprocessing algorithm.

[0049] The enhanced preprocessing algorithm includes data cleaning, feature selection, feature conversion, data enhancement and dimensionality reduction.

[0050] The data cleaning includes removing non-numeric data and processing missing values; the feature selection includes correlation analysis and recursive feature elimination; and the data conversion includes standardization and normalization.

[0051] The normalization formula is:

[0052]

[0053] Among them, X is the original eigenvalue, X min is the minimum value of the feature, X max is the maximum value of the feature, X norm is the normalized eigenvalue.

[0054] The standardized formula is:

[0055]

[0056] Among them, X std is the standardized eigenvalue, X is the original eigenvalue, μ is the mean of the feature, and σ is the standard deviation of the feature.

[0057] The dimension reduction formula is:

[0058]

[0059] Among them, S W is the intra-class scatter matrix, S B is the inter-class scatter matrix, w is the projection direction, and λ is the eigenvalue.

[0060] Furthermore, the data analysis model includes loading the preprocessed data into the data analysis model, extracting features using an algorithm, selecting an analysis model based on properties, training the data analysis model using linear regression, analyzing data loss and gradient descent, and performing pattern recognition.

[0061] The feature extraction formula is:

[0062]

[0063] Among them, PC is the main component. is the eigenvector, X std is the standardized feature value.

[0064] The training formula of the data analysis model is:

[0065]

[0066] in, is the predicted value, Z is the feature matrix, β is the weight coefficient, and ∈ is the error term.

[0067] The data loss formula is:

[0068]

[0069] Among them, MSE is the mean square error, n is the number of samples, and y i is the ith actual value, is the i-th predicted value.

[0070] The gradient descent formula is:

[0071]

[0072] Among them, β (t) is the weight coefficient of the tth iteration, α is the learning rate, J(β) is the loss function, is the gradient of the loss function with respect to the weight coefficient, β (t+1) is the weight coefficient for the t+1th iteration.

[0073] The pattern recognition formula is:

[0074]

[0075] Where P(y=1|X) is the probability of label y=1 given feature X, e is the base of the natural logarithm, β 0 , β 1 , β 2 , …, β n is the model parameter, X 1 , X 2 ,…X n is the characteristic value.

[0076] S2: Start the monitoring and early warning mechanism, track the analysis results in real time, and trigger the strategy adjustment algorithm according to the instructions output by the analysis model. The microservices perform strategy adjustments through collaborative work.

[0077] The early warning mechanism includes using the extracted data features for statistical analysis and using a machine learning model for anomaly detection.

[0078] The statistical analysis formula is:

[0079] θ t =a t +k·b t

[0080] Among them, θ t is the threshold at time t, t is time, a tis the mean value of the monitoring index at time t, b t is the standard deviation of the monitoring indicator at time t, and k is the threshold coefficient.

[0081] The machine learning model formula is:

[0082] A(y t )=IForest({y 1 ,y 2 ,...,y t})

[0083] Among them, A(y t ) is the data point y t The degree of abnormality, y t is the monitoring indicator data point at time t, t is time, IForest({y 1 ,y 2 ,...,y t}) is the isolation forest model; when y t >θ t When y t ≤θ t , it indicates that the data point is normal and no warning is triggered.

[0084] The strategy adjustment algorithm includes real-time tracking and analysis based on the results of the early warning mechanism, and triggering the strategy adjustment algorithm based on the instructions output by the analysis model, and executing strategy adjustment through collaborative work between microservices.

[0085] The strategy adjustment algorithm formula is expressed as:

[0086]

[0087] Where D(m,f) is the policy adjustment coefficient of the mth microservice at time f, p is the total number of monitored microservices, and Q j (s) is the performance indicator of the jth microservice at time s, N j (s) is the normalized value of the performance index of the jth microservice at time s, h is the sigmoid function, θ j The performance threshold of the jth microservice, q j is the performance index attenuation coefficient of the jth microservice, f 0 is the time point when monitoring starts, m is the total number of monitored performance indicators, and g l (s) is the real-time value of the lth performance indicator at time s, o l is the average value of the lth performance indicator.

[0088] Among them, the value range of D(m,f) is (0,1). When 0 < D(m,f) ≤ 0.5, it indicates that the collaborative work effect between microservices does not meet the standard, and the microservices adjust the execution strategy through collaborative work until D(m,f) returns to the normal level. When 0.5 < D(m,f) < 1, it indicates that the collaborative work effect between microservices meets the standard, and the microservices do not need to execute strategy adjustment.

[0089] S3: Verify the interaction and response between services through testing and enter the real-time monitoring state. Arrange periodic maintenance and update work through predictive maintenance and fault prediction models.

[0090] The predictive maintenance and fault prediction model includes verifying the interaction and response between services through testing and entering the real-time monitoring state. Arrange periodic maintenance and update work through predictive maintenance and fault prediction models.

[0091] The verification of the interaction and response between services through testing includes determining typical scenarios of interaction between services, designing test cases for the scenarios, simulating service requests and responses, recording interaction time and status codes, and obtaining the total test result error, which is expressed by the formula:

[0092]

[0093] where T(R) is the total error of the test result, N is the number of test cases, R z is the actual response time of the z-th test case, and E z is the expected response time of the z-th test case.

[0094] Among them, the fault prediction formula is:

[0095]

[0096] where F(I) is the fault prediction value at time I, v is the order of time lag considered by the model, δ τ is the coefficient of the τ-th time lag term, y I-τ is the actual observed value at time I - τ, γ is the coefficient of the trend term, trend(I) is the trend term at time I, and ε I is the error term; when F(I) ≥ 70, the prediction system fails, and immediate repair is carried out and the equipment parameters are adjusted until the value of F(I) returns to the normal level; when F(I) < 70, the prediction system is in a normal operation state, and periodic maintenance and update are continued according to the plan.

[0097] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0098] Embodiment 2, the second embodiment of the present invention, is different from the previous embodiment in that:

[0099] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0100] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0101] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0102] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0103] Example 3, reference Figure 2 , which is the third embodiment of the present invention, and provides a system for real-time monitoring of network performance based on a microservice platform, including a data collection module 100, a data processing and analysis module 200, a monitoring and early warning module 300, and a maintenance and fault prediction module 400;

[0104] The data collection module 100 is used to collect device data in real time;

[0105] The data processing and analysis module 200 is used to clean and format the collected data, and perform feature extraction and pattern recognition on the pre-processed data;

[0106] The monitoring and early warning module 300 is used to track the analysis results in real time and trigger the strategy adjustment algorithm according to the instructions output by the analysis model. The microservices perform strategy adjustment through collaborative work;

[0107] The maintenance and fault prediction module 400 is used to test and verify the interaction and response between services, and enter a real-time monitoring state, and arrange periodic maintenance and update work through a predictive maintenance and fault prediction model.

[0108] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A real-time monitoring method for network performance based on microservice architecture, characterized in that: including, collecting first device data in real time, preprocessing the first data to obtain second data, and inputting the second data into a third analysis model for identification; starting a fourth warning mechanism, tracking the analysis results in real time, and performing policy adjustment according to the instructions output by the third analysis model; verifying the interaction and response between services through testing and entering the real-time monitoring state, and arranging periodic maintenance and update work through a fifth maintenance model.

2. A method for real-time monitoring of network performance based on a microservice platform as claimed in claim 1, characterized in that: The collecting of the first device data includes collecting the current data, voltage data, power data, frequency data, temperature data, environmental data, device status data, load characteristic data, historical fault data, and operation log data of the device in real time.

3. A method for real-time monitoring of network performance based on a microservice platform as claimed in claim 2, characterized in that: The preprocessing of the first data to obtain second data includes preprocessing the collected data using an enhanced preprocessing algorithm; The enhanced preprocessing algorithm includes data cleaning, feature selection, feature transformation, data augmentation, and dimensionality reduction; The data cleaning includes removing non-numerical data and handling missing values; the feature selection includes correlation analysis and recursive feature elimination; the data transformation includes standardization and normalization.

4. A method for real-time monitoring of network performance based on a microservice platform as claimed in claim 3, characterized in that: The inputting of the second data into the third analysis model for identification includes loading the second data into the data analysis model, extracting features using an algorithm, selecting an analysis model according to the nature, training the data analysis model using linear regression, analyzing data loss and gradient descent, and performing pattern recognition; Using the data analysis model as the third analysis model for feature extraction and pattern recognition.

5. A method for real-time monitoring of network performance based on a microservice platform as claimed in claim 4, characterized in that: The fourth warning mechanism includes performing statistical analysis using the features output by the third analysis model and performing anomaly detection using a machine learning model, and immediately giving an alarm when an abnormal situation occurs.

6. A method for real-time monitoring of network performance based on a microservice platform as claimed in claim 5, characterized in that: The performing of policy adjustment includes tracking the analysis in real time according to the results of the fourth warning mechanism, and triggering a policy adjustment algorithm according to the instructions output by the third analysis model, and the microservices perform policy adjustment through collaborative work; The formula of the policy adjustment algorithm is expressed as: Where D(m,f) is the policy adjustment coefficient of the mth microservice at time f, p is the total number of monitored microservices, and Q j (s) is the performance indicator of the jth microservice at time s, N j (s) is the normalized value of the performance index of the jth microservice at time s, h is the sigmoid function, θ j The performance threshold of the jth microservice, q j is the performance indicator attenuation coefficient of the jth microservice, f0 is the time point when monitoring starts, m is the total number of monitored performance indicators, and g l (s) is the real-time value of the lth performance indicator at time s, o l is the average value of the lth performance indicator; where the value range of D(m,f) is (0,1). When 0 < D(m,f) ≤ 0.5, it means that the collaborative work effect between microservices does not meet the standard, and the microservices perform policy adjustment through collaborative work until D(m,f) returns to the normal level. When 0.5 < D(m,f) < 1, it means that the collaborative work effect between microservices meets the standard, and the microservices do not need to perform policy adjustment.

7. A method for real-time monitoring of network performance based on a microservice platform as claimed in claim 6, characterized in that: The fifth maintenance model includes verifying the interaction and response between services through testing and entering the real-time monitoring state, and arranging periodic maintenance and update work through a predictive maintenance and fault prediction model; The verifying of the interaction and response between services through testing includes determining the typical scenarios of the interaction between services, designing test cases for the scenarios, simulating service requests and responses, recording the interaction time and status code, and obtaining the total test result error, and the formula is expressed as: Where T(R) is the total error of the test result, N is the number of test cases, and R z is the actual response time of the zth test case, E z is the expected response time of the zth test case; where the fault prediction formula is: Where F(I) is the fault prediction value at time I, v is the time lag order considered by the model, and δ τ is the coefficient of the τth time lag term, y I-τ is the actual observed value at time I-τ, γ is the trend term coefficient, trend(I) is the trend term at time I, ε I is the error term; when F(I)≥70, the prediction system fails and is immediately repaired and the equipment parameters are adjusted until the F(I) value returns to normal levels; when F(I)<70, the prediction system is in normal operation and periodic maintenance and updates are continued as planned.

8. A system using a method for real-time monitoring of network performance based on a microservice platform as claimed in any one of claims 1 to 7, characterized in that: including a data collection module, a data processing and analysis module, a monitoring and warning module, and a maintenance and fault prediction module; The data collection module is used to collect device data in real time; The data processing and analysis module is used to clean and format the collected data, and perform feature extraction and pattern recognition on the pre-processed data; The monitoring and early warning module is used to track the analysis results in real time and trigger the strategy adjustment algorithm according to the instructions output by the analysis model. The microservices perform strategy adjustment through collaborative work; The maintenance and fault prediction module is used to test and verify the interaction and response between services, and enter a real-time monitoring state, and arrange periodic maintenance and update work through a predictive maintenance and fault prediction model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a method for real-time monitoring of network performance based on a microservice platform according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for real-time monitoring of network performance based on a microservice platform according to any one of claims 1 to 7 are implemented.

Images